CN114936207B - Method for evaluating quality of sensing data of sensing equipment of Internet of things - Google Patents

Method for evaluating quality of sensing data of sensing equipment of Internet of things Download PDF

Info

Publication number
CN114936207B
CN114936207B CN202210875069.3A CN202210875069A CN114936207B CN 114936207 B CN114936207 B CN 114936207B CN 202210875069 A CN202210875069 A CN 202210875069A CN 114936207 B CN114936207 B CN 114936207B
Authority
CN
China
Prior art keywords
things
sensing
internet
data
sensing equipment
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
CN202210875069.3A
Other languages
Chinese (zh)
Other versions
CN114936207A (en
Inventor
林涛
张兵
邹忱
许华杰
吕国林
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.)
Shenzhen Urban Transport Planning Center Co Ltd
Original Assignee
Shenzhen Urban Transport Planning Center 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 Shenzhen Urban Transport Planning Center Co Ltd filed Critical Shenzhen Urban Transport Planning Center Co Ltd
Priority to CN202210875069.3A priority Critical patent/CN114936207B/en
Publication of CN114936207A publication Critical patent/CN114936207A/en
Application granted granted Critical
Publication of CN114936207B publication Critical patent/CN114936207B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
    • G16Y20/00—Information sensed or collected by the things
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Evolutionary Biology (AREA)
  • Medical Informatics (AREA)
  • Signal Processing (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Health & Medical Sciences (AREA)
  • Algebra (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Telephonic Communication Services (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention provides a method for evaluating the quality of sensing data of sensing equipment of the Internet of things, and belongs to the technical field of evaluation of the quality of sensing data of sensing equipment of the Internet of things. The method comprises the steps that real-time sensing data of the sensing equipment of the Internet of things are acquired by the acquisition and docking equipment and are stored in a database; the method comprises the steps of obtaining sensing data of the sensing equipment of the Internet of things from a database, wherein the sensing data of the sensing equipment of the Internet of things comprises sensing data of sensing equipment of the discrete Internet of things and sensing data of sensing equipment of the continuous Internet of things, respectively carrying out data quality evaluation on the sensing data of the sensing equipment of the discrete Internet of things and the sensing data of the sensing equipment of the continuous Internet of things to obtain a process sigma value, determining data quality according to the process sigma value, and creating a linear regression model to predict the sensing data quality of the sensing equipment of the Internet of things. The method and the system effectively filter the defective equipment data and mark the problematic equipment in time, thereby improving the correctness of service decision. The technical problem of low data quality accuracy rate in the prior art is solved.

Description

Method for evaluating quality of sensing data of sensing equipment of Internet of things
Technical Field
The application relates to a quality evaluation method, in particular to a quality evaluation method for sensing data of sensing equipment of the Internet of things, and belongs to the technical field of quality evaluation of sensing data of sensing equipment of the Internet of things.
Background
The internet of things is also called a sensing network. The internet of things is a network which connects any article with the internet according to an agreed protocol through information sensing equipment such as Radio Frequency Identification (RFID), an infrared sensor, a global positioning system, a laser scanner and the like to exchange and communicate information so as to realize intelligent identification, positioning, tracking, monitoring and management.
The concept of the internet of things and related technical products have widely penetrated into various fields of social and economic lives and play a key role in more and more industrial innovation. The internet of things plays an important role in promoting transformation and upgrading, improving social services, improving service lives, promoting efficiency and energy conservation and the like by virtue of deep integration and comprehensive application of a new generation of information technology, and brings real 'intelligent' application in partial fields.
With the further development and breakthrough of the technology in the related field and the gradual improvement of the cognition degree of the client, the internet of things can be more widely applied to various fields such as industry, agriculture, electric power, building, traffic, logistics, environmental protection, medical treatment, security, home furnishing and the like. The internet of things market has great potential and will develop at a high speed in the coming years, and the good development prospect of the internet of things market also brings opportunities and challenges for numerous manufacturers.
The Internet of things equipment serves as a sensing terminal and feeds back accurate and effective sensing information in time based on different needs of services. The condition of the quality of the sensing data can seriously affect the analysis and calculation of the final result, the quality of the sensing data is ensured, and invalid equipment and the sensing data are necessary to be checked and removed in time. Current data quality inspection algorithms generally count the overall yield, rather than judge the yield based on the deviation of individual data, which results in high yield of part of the equipment within the specified deviation, but low data quality accuracy due to the deviation.
Disclosure of Invention
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to determine the key or critical elements of the present invention, nor is it intended to limit the scope of the present invention. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.
In view of this, in order to solve the technical problem of low data quality accuracy rate in the prior art, the invention provides a method for evaluating the sensing data quality of sensing equipment of the internet of things.
The first scheme is as follows: the method for evaluating the quality of the sensing data of the sensing equipment of the Internet of things is characterized by comprising the steps of acquiring real-time sensing data of the sensing equipment of the Internet of things obtained by butt joint equipment and storing the sensing data into a database; the method comprises the steps of obtaining sensing data of the sensing equipment of the Internet of things from a database, wherein the sensing data of the sensing equipment of the Internet of things comprises sensing data of sensing equipment of the discrete Internet of things and sensing data of sensing equipment of the continuous Internet of things, respectively carrying out data quality evaluation on the sensing data of the sensing equipment of the discrete Internet of things and the sensing data of the sensing equipment of the continuous Internet of things to obtain a process sigma value, determining data quality according to the process sigma value, and creating a linear regression model to predict the sensing data quality of the sensing equipment of the Internet of things.
Preferably, the quality evaluation method of the sensing data of the discrete internet of things sensing device comprises the following steps:
s1, selecting N pieces of sensing data of discrete Internet of things sensing equipment in a certain time period from a database, and recording the data of each piece of Internet of things sensing equipment as i 1 ,i 2 ,i 3 .....i n (ii) a Verifying each piece of Internet of things sensing equipment data from six dimensions respectively to obtain W pieces of defect data;
s2, calculating the probability of defect DPO;
s3, calculating the DPMO of million opportunity defects;
s4, inquiring a corresponding relation table of DMPO and sigma to obtain a process sigma value Z of sensing data of the sensing equipment of the current Internet of things;
and S5, evaluating the quality of the sensing data of the discrete Internet of things sensing equipment according to the flow sigma value Z.
Preferably, the six dimensions include completeness, normalization, consistency, accuracy, uniqueness and relevance; the sensing data of the sensing equipment of the Internet of things which does not conform to one of six dimensions is the sensing equipment data of the defective Internet of things, and each sensing data of the sensing equipment of the Internet of things has six defect opportunities.
Preferably, the calculation method of the opportunistic defect rate DPO is as follows:
DPO = number of defects/(number of products × number of opportunities for defects);
the calculation method of the DPMO with the million chance defect number is as follows:
DPMO=DPO*10^6
the number of the products is the number of sensing data of the sensing equipment of the Internet of things, the number of the defects is the number of the defects of the sensing data of the sensing equipment of the Internet of things, and the number of the opportunities of the defects is the proportion of the number of the defects of the sensing data of each sensing equipment of the Internet of things to the number of the defects of the sensing data of all sensing equipment of the Internet of things.
Preferably, the method for evaluating the quality of the sensing data of the internet of things sensing device according to the process sigma value Z is that the greater the process sigma value Z is, the better the quality of the sensing data of the internet of things sensing device is.
Preferably, the quality evaluation method for sensing data of the continuous internet of things sensing equipment comprises the following steps:
step one, selecting N pieces of sensing data of continuous Internet of things sensing equipment in a certain time period from a database, and respectively recording the sensing data result of each piece of Internet of things sensing equipment as i 1 ,i 2 ,i 3 .....i n Acquiring an average value of sensing data of the continuous Internet of things sensing equipment;
secondly, calculating the variance of the sensing data and the average value of the continuous Internet of things sensing equipment;
thirdly, calculating probability density according to the average value and the variance to obtain the perception data qualification rate P of the continuous Internet of things sensing equipment good So as to obtain the sensing data opportunity defect rate 1-P of the continuous Internet of things sensing equipment good ；
Step four, calculating the DPMO with the million chance defect number, wherein the DPMO = DPO 10^6, and the DPO value is 1-P good Inquiring a corresponding relation table of DMPO and sigma to obtain a process sigma value Z of sensing data of the current sensing equipment of the internet of things;
and fifthly, evaluating the quality of the sensing data of the continuous Internet of things sensing equipment according to the flow sigma value Z.
Preferably, the specific method for calculating the probability density according to the mean and the variance to obtain the yield is as follows:
function of probability density
Figure 966793DEST_PATH_IMAGE001
=
Figure 132195DEST_PATH_IMAGE002
exp(-
Figure 839251DEST_PATH_IMAGE003
)
When in use
Figure 406499DEST_PATH_IMAGE004
=0，
Figure 298231DEST_PATH_IMAGE005
When =1, the normal distribution is a standard normal distribution, and the probability density function is simplified as follows:
Figure 75563DEST_PATH_IMAGE006
=
Figure 445365DEST_PATH_IMAGE007
exp
Figure 867119DEST_PATH_IMAGE008
the cumulative probability area function is: p (X) = (8709 =)
Figure 929753DEST_PATH_IMAGE009
=
Figure 679534DEST_PATH_IMAGE010
=1
According to the formula, the fraction defective under the tolerance lower bound LSL is calculated as follows:
P（X<LSL）=
Figure 118606DEST_PATH_IMAGE011
=
Figure 394866DEST_PATH_IMAGE012
the result of calculating the fraction defective above the tolerance upper bound USL is as follows:
P（X>USL）=
Figure 18614DEST_PATH_IMAGE013
=
Figure 380326DEST_PATH_IMAGE014
the cumulative probability area of the region between the lower tolerance bound and the upper tolerance bound is:
P(LSL≤
Figure 91930DEST_PATH_IMAGE015
≤USL)=
Figure 488276DEST_PATH_IMAGE016
=
Figure 768079DEST_PATH_IMAGE017
-
Figure 617086DEST_PATH_IMAGE011
therefore, the yield is P good =P(LSL≤
Figure 132381DEST_PATH_IMAGE015
≤USL)。
Preferably, the method for predicting the sensing data quality of the sensing equipment of the internet of things by establishing the linear regression model comprises the following steps: the linear regression model is: y =
Figure 773447DEST_PATH_IMAGE018
(x)=
Figure 348785DEST_PATH_IMAGE019
0 +
Figure 685088DEST_PATH_IMAGE019
1 x, wherein
Figure 4074DEST_PATH_IMAGE018
(x) Representing a functional mapping from x to y,
Figure 984799DEST_PATH_IMAGE020
0 and
Figure 731038DEST_PATH_IMAGE020
1 the method comprises the steps that regression parameters are adopted, x is an independent variable, corresponding time T and y are target output variables, the target output variables are inquired through a corresponding relation table of DMPO and sigma to obtain a process sigma value Z of sensing data of current sensing equipment, and the larger the process sigma value Z is, the better the sensing data quality of the sensing equipment of the Internet of things is.
The second scheme is that the electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the first scheme when executing the computer program.
Solution three, a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of solution one.
The invention has the following beneficial effects: the method and the system can effectively filter out defective equipment data, mark out the defective equipment in time and improve the correctness of service decision. The method and the device can analyze the data quality of the equipment in a segmented manner, dynamically evaluate the perceived data quality condition of the equipment, and give an alarm in time when the perceived data quality condition is lower than a set quality standard condition.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a schematic diagram of a normal distribution curve according to the present invention.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Embodiment 1, this embodiment is described with reference to fig. 1 to 2, and a method for evaluating sensing data quality of internet of things sensing equipment includes acquiring real-time sensing data of the internet of things sensing equipment acquired by docking equipment and storing the data in a database; the method comprises the steps of obtaining sensing data of the sensing equipment of the Internet of things from a database, wherein the sensing data of the sensing equipment of the Internet of things comprises sensing data of sensing equipment of the discrete Internet of things and sensing data of sensing equipment of the continuous Internet of things, respectively carrying out data quality evaluation on the sensing data of the sensing equipment of the discrete Internet of things and the sensing data of the sensing equipment of the continuous Internet of things to obtain a process sigma value, determining data quality according to the process sigma value, and creating a linear regression model to predict the sensing data quality of the sensing equipment of the Internet of things.
Specifically, the acquisition of the real-time device perception data by the docking device includes the following contents: firstly, introducing and acquiring a sensing result parameter standard deviation value (tolerance upper bound (USL)/tolerance lower bound (LSL)) of equipment through national standards and an Internet of things sensing equipment product; and secondly, connecting the sensing equipment of the Internet of things to a power grid, verifying whether the equipment is normal, checking and confirming whether the voltage and the network bandwidth of the sensing equipment of the Internet of things are normal, checking whether the voltage and the network bandwidth of the sensing equipment of the Internet of things meet the normal working environment requirements of the equipment, continuing to perform the next step if the voltage and the network bandwidth meet the normal working environment requirements of the equipment, otherwise, giving an alarm and stopping detection. And finally, after the normal work of the equipment is confirmed, acquiring the perception information of the equipment for modeling analysis, and evaluating the quality condition of the perception data of the equipment.
Specifically, the quality evaluation method for sensing data of the discrete internet of things sensing equipment comprises the following steps:
s1, selecting a discrete object in a certain time period from a databaseThe sensing data of the networking sensing equipment is N, and the sensing data of each discrete type Internet of things sensing equipment is respectively recorded as i 1 ,i 2 ,i 3 .....i n (ii) a And verifying the sensing data of each discrete Internet of things sensing device from six dimensions of integrity, normalization, consistency, accuracy, uniqueness and relevance to obtain W pieces of defect data, wherein the six dimensions are six defect opportunities, and the sensing data of each Internet of things sensing device has six defect opportunities as long as the sensing data of the Internet of things sensing device does not conform to one of the six dimensions, namely the defect data.
S2, calculating the chance defect rate DPO according to an opportunity defect rate DPO calculation formula, wherein the ratio of the defect occurrence rate in each chance represents the proportion of the defect number in each sample amount to the total chance number, and therefore, the chance defect rate DPO is calculated according to the following calculation method:
DPO = number of defects/(number of products × number of opportunities for defects); i.e. DPO = W/(6 × n).
S3, calculating the DPMO (number of million opportunity defects); the calculation method is as follows:
DPMO = DPO 10^6; i.e. DMPO = (10 ^6 x w)/(6 x n).
The number of the products is the number of sensing data of the sensing equipment of the Internet of things, the number of the defects is the number of the defects of the sensing data of the sensing equipment of the Internet of things, and the number of the opportunities of the defects is the proportion of the number of the defects of the sensing data of each sensing equipment of the Internet of things to the number of the defects of the sensing data of all sensing equipment of the Internet of things.
S4, inquiring a flow sigma value Z of the sensing data of the current discrete type Internet of things sensing equipment through a corresponding relation table (DMPO and sigma) of DMPO and sigma;
table-DMPO and sigma correspondence table
Figure 289059DEST_PATH_IMAGE021
And S5, evaluating the quality of the sensing data of the discrete Internet of things sensing equipment according to the flow sigma value Z, wherein the larger the flow sigma value Z is, the better the quality of the sensing data of the Internet of things sensing equipment is.
Specifically, the quality evaluation method for sensing data of the continuous internet of things sensing equipment comprises the following steps:
step one, selecting N pieces of sensing data of continuous Internet of things sensing equipment in a certain time period from a database, and respectively recording the sensing data result of each piece of Internet of things sensing equipment as i 1 ,i 2 ,i 3 .....i n And acquiring the average value of the sensing data of the continuous Internet of things sensing equipment.
The method for obtaining the average value is realized by the following formula: μ =
Figure 801949DEST_PATH_IMAGE022
And μ represents the average value of the sensing data of the N pieces of sensing equipment of the Internet of things.
Step two, variance calculation is carried out on the sensing data and the average value of the continuous Internet of things sensing equipment, and the specific calculation method is as follows:
σ 2 =(1/N)
Figure 761814DEST_PATH_IMAGE023
wherein i n Values, σ, representing each successive datum 2 The variance obtained for N data is shown.
Thirdly, calculating probability density according to the average value and the variance to obtain the perception data qualification rate P of the continuous Internet of things sensing equipment good So as to obtain the sensing data opportunity defect rate 1-P of the continuous Internet of things sensing equipment good ；
Step four, calculating the DPMO with the million chance defect number, wherein the DPMO = DPO 10^6, and the DPO value is 1-P good Inquiring a flow sigma value Z of the data of the current sensing equipment through a corresponding relation table of DMPO and sigma;
and step five, evaluating the quality of the continuous sensing data according to the flow sigma value Z.
Specifically, the normal distribution data N to (. Mu.,. Sigma.) will be described with reference to FIG. 2 2 ) The axis of symmetry of a normal distribution curve is the average of normal samples, with the average of the samples increasing, the curve shifting to the right, the average of the samples decreasing, and the curve to the leftAnd (7) measuring translation. The larger the standard deviation of a normal sample, the flatter the normal distribution curve, the smaller the peak, and the total probability Area under the distribution curve is 1 (Rejected Area is a bad Area).
Specifically, the method for calculating the probability density according to the mean and the variance to obtain the yield is that,
function of probability density
Figure 678955DEST_PATH_IMAGE024
=
Figure 989850DEST_PATH_IMAGE025
exp(-
Figure 526005DEST_PATH_IMAGE026
)
When in use
Figure 340377DEST_PATH_IMAGE004
=0，
Figure 693998DEST_PATH_IMAGE027
When =1, the normal distribution is a standard normal distribution, and the probability density function is simplified as follows:
Figure 226611DEST_PATH_IMAGE028
=
Figure 815724DEST_PATH_IMAGE029
exp(-
Figure 750182DEST_PATH_IMAGE030
) The cumulative probability area function is: p (X) = (8709 =)
Figure 274704DEST_PATH_IMAGE031
=
Figure 904400DEST_PATH_IMAGE032
=1
According to the formula, we calculate the reject ratio below the lower tolerance limit LSL as:
P（X<LSL）=
Figure 172570DEST_PATH_IMAGE011
=
Figure 961534DEST_PATH_IMAGE012
the result of calculating the reject ratio above the tolerance upper bound USL is as follows:
P（X>USL）=
Figure 781592DEST_PATH_IMAGE013
=
Figure 288796DEST_PATH_IMAGE033
the cumulative probability area of the region between the lower tolerance bound and the upper tolerance bound is:
P(LSL≤
Figure 95078DEST_PATH_IMAGE015
≤USL)=
Figure 738549DEST_PATH_IMAGE016
=
Figure 480240DEST_PATH_IMAGE017
-
Figure 474741DEST_PATH_IMAGE011
therefore, the yield is P good =P(LSL≤
Figure 84714DEST_PATH_IMAGE015
≤USL)；
Therefore, DPMO = (1-P) in million chance defect number good ）*
Figure 972905DEST_PATH_IMAGE034
The flow sigma value Z of the data of the current sensing equipment is obtained through inquiring a corresponding relation table I of DMPO and sigma, the quality of the sensing data of the current sensing equipment of the Internet of things can be determined according to the Z value, and the larger the Z value is, the higher the data quality of the sensing equipment of the Internet of things isThe better the amount.
Specifically, the method for predicting the sensing data quality of the sensing equipment of the internet of things by establishing a linear regression model comprises the following steps: the linear regression model is: y =
Figure 744552DEST_PATH_IMAGE018
(x)=
Figure 226348DEST_PATH_IMAGE020
0 +
Figure 374433DEST_PATH_IMAGE020
1 x, wherein
Figure 867862DEST_PATH_IMAGE018
(x) Representing a functional mapping from x to y,
Figure 810411DEST_PATH_IMAGE020
0 and
Figure 513924DEST_PATH_IMAGE020
1 and inquiring the target output variable through a corresponding relation table of DMPO and sigma to obtain a process sigma value Z of the data of the current sensing equipment.
Specifically, the detailed process of the method for establishing the model to predict the sensing data quality of the sensing equipment of the internet of things is as follows:
a. the corresponding sigma level Z values are calculated for the data of different time periods T, i.e. assuming the data set S = { (T) 1 ,Z 1 ),(T 2 ,Z 2 ),...(T 3 ,Z 3 )}；
b. Assuming a linear regression model as: y =
Figure 855913DEST_PATH_IMAGE018
(x)=
Figure 328483DEST_PATH_IMAGE020
0 +
Figure 707511DEST_PATH_IMAGE020
1 x is wherein
Figure 898321DEST_PATH_IMAGE018
(x) Representing a functional mapping from x to y,
Figure 263575DEST_PATH_IMAGE020
0 and
Figure 818687DEST_PATH_IMAGE020
1 is a regression parameter, x is an independent variable, corresponding to time T, y is a target output variable, corresponding to sigma level Z;
c. quantifying a loss function such that the regression parameters
Figure 514197DEST_PATH_IMAGE020
0 And
Figure 722958DEST_PATH_IMAGE020
1 the optimal regression parameters to be calculated in step a can be continuously optimized in the solving process
Figure 554648DEST_PATH_IMAGE020
0 And
Figure 259802DEST_PATH_IMAGE020
1 can be converted into min (
Figure 895182DEST_PATH_IMAGE018
(x)-y)；
Assuming the loss function is: j (J)
Figure 316936DEST_PATH_IMAGE019
)=
Figure 520516DEST_PATH_IMAGE037
Where m represents the number of instances in the training set,
Figure 394931DEST_PATH_IMAGE038
、
Figure 568423DEST_PATH_IMAGE039
represents the ith observation instance;
find out a group
Figure 844684DEST_PATH_IMAGE020
0 And
Figure 202853DEST_PATH_IMAGE020
1 minimizing the value of the loss function, the solution J (b) can be
Figure 564564DEST_PATH_IMAGE020
) The partial derivative is 0, and the calculation is derived as follows:
Figure 541747DEST_PATH_IMAGE040
J(
Figure 938094DEST_PATH_IMAGE020
)=
Figure 217896DEST_PATH_IMAGE041
=0 (formula 1.3) handle
Figure 66904DEST_PATH_IMAGE020
0 And
Figure 847778DEST_PATH_IMAGE020
1 the equation yields a system of equations as follows:
Figure 223264DEST_PATH_IMAGE042
J(
Figure 798602DEST_PATH_IMAGE020
)=
Figure 869326DEST_PATH_IMAGE043
= 0
Figure 188312DEST_PATH_IMAGE044
J(
Figure 434617DEST_PATH_IMAGE020
)=
Figure 180856DEST_PATH_IMAGE045
= 0
it can be solved that:
Figure 4456DEST_PATH_IMAGE046
=
Figure 986187DEST_PATH_IMAGE047
Figure 211632DEST_PATH_IMAGE048
=
Figure 128772DEST_PATH_IMAGE049
to obtain
Figure 174089DEST_PATH_IMAGE020
Figure 975823DEST_PATH_IMAGE019
0 And
Figure 55774DEST_PATH_IMAGE020
Figure 143816DEST_PATH_IMAGE019
1 values of two parameters, so the linear regression model y =
Figure 801062DEST_PATH_IMAGE018
(x)=
Figure 265542DEST_PATH_IMAGE020
0 +
Figure 200000DEST_PATH_IMAGE020
1 x can be used for predicting a sigma horizontal Z value corresponding to the time period T, the quality of the sensing data quality of the sensing equipment of the Internet of things can be predicted according to the Z value, and the larger the Z value of the sigma value of the process is, the better the sensing data quality of the sensing equipment of the Internet of things is.
Specifically, in different time periods, the prediction model can predict sigma level values corresponding to different time periods.
In embodiment 2, the computer device of the present invention may be a device including a processor, a memory, and the like, for example, a single chip microcomputer including a central processing unit, and the like. And the processor is used for implementing the steps of the recommendation method for modifying the relationship-driven recommendation data based on the CREO software when executing the computer program stored in the memory.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Embodiment 3 computer-readable storage Medium embodiment
The computer readable storage medium of the present invention may be any form of storage medium read by a processor of a computer device, including but not limited to non-volatile memory, ferroelectric memory, etc., on which a computer program is stored, which when read and executed by the processor of the computer device, may implement the steps of the above-described CREO software-based modeling method that can modify relationship-driven modeling data.
The computer program comprises computer program code which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer-readable medium may contain suitable additions or subtractions depending on the requirements of legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer-readable media may not include electrical carrier signals or telecommunication signals in accordance with legislation and patent practice.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The present invention has been disclosed in an illustrative rather than a restrictive sense, and the scope of the present invention is defined by the appended claims.

Claims (3)

1. The method for evaluating the quality of the sensing data of the sensing equipment of the Internet of things is characterized by comprising the steps of acquiring real-time sensing data of the sensing equipment of the Internet of things obtained by butt joint equipment and storing the sensing data into a database; acquiring sensing data of the sensing equipment of the Internet of things from a database, wherein the sensing data of the sensing equipment of the Internet of things comprises sensing data of sensing equipment of a discrete Internet of things and sensing data of sensing equipment of a continuous Internet of things, respectively carrying out data quality evaluation on the sensing data of the sensing equipment of the discrete Internet of things and the sensing data of the sensing equipment of the continuous Internet of things to obtain a process sigma value, determining the data quality according to the process sigma value, and establishing a linear regression model to predict the quality of the sensing data of the sensing equipment of the Internet of things;
the quality evaluation method of the sensing data of the discrete Internet of things sensing equipment specifically comprises the following steps:
s1, selecting N pieces of sensing data of discrete Internet of things sensing equipment in a certain time period from a database, and recording the data of each piece of Internet of things sensing equipment as i 1 ,i 2 ,i 3 .....i n (ii) a Verifying each piece of Internet of things sensing equipment data from six dimensions respectively to obtain W pieces of defect data, wherein the six dimensions comprise integrity, normalization, consistency, accuracy, uniqueness and relevance; the sensing data of the IOT sensing equipment which does not conform to one of six dimensions is defect IOT sensing equipment data, and each sensing data of the IOT sensing equipment has six defect opportunities;
s2, calculating the probability of the computer fault, DPO, according to the following method:
DPO = number of defects/(number of products × number of opportunities for defects);
s3, calculating the DPMO of million chance defects, wherein the calculation method is as follows:
DPMO=DPO*10^6
the product number is the number of sensing data of the sensing equipment of the Internet of things, the defect number is the defect number of the sensing data of the sensing equipment of the Internet of things, and the defect opportunity number is the proportion of the defect number of the sensing data of each sensing equipment of the Internet of things to the defect number of the sensing data of all the sensing equipment of the Internet of things;
s4, inquiring a corresponding relation table of DMPO and sigma to obtain a process sigma value Z of sensing data of the sensing equipment of the current Internet of things;
s5, evaluating the quality of sensing data of the discrete Internet of things sensing equipment according to the process sigma value Z, wherein the larger the process sigma value Z is, the better the quality of the sensing data of the Internet of things sensing equipment is, and the quality evaluation method of the sensing data of the continuous Internet of things sensing equipment specifically comprises the following steps:
step one, selecting N pieces of sensing data of continuous Internet of things sensing equipment in a certain time period from a database, and respectively recording the sensing data result of each piece of Internet of things sensing equipment as i 1 ,i 2 ,i 3 .....i n Acquiring an average value of sensing data of the continuous Internet of things sensing equipment;
step two, variance calculation is carried out on sensing data and the average value of the continuous Internet of things sensing equipment;
thirdly, calculating probability density according to the mean value and the variance to obtain the perception data qualification rate P of the continuous Internet of things sensing equipment good So as to obtain the sensing data opportunity defect rate 1-P of the continuous Internet of things sensing equipment good The specific method comprises the following steps:
function of probability density
Figure 787513DEST_PATH_IMAGE002
When in use
Figure DEST_PATH_IMAGE003
=0，
Figure 547659DEST_PATH_IMAGE004
When =1, the normal distribution is a standard normal distribution, and the probability density function is simplified as follows:
Figure 549113DEST_PATH_IMAGE006
the cumulative probability area function is: p (x) = (8709 =, x) =
Figure 200543DEST_PATH_IMAGE008
=
Figure 338263DEST_PATH_IMAGE010
=1
According to the formula, the fraction defective under the tolerance lower bound LSL is calculated as follows:
Figure DEST_PATH_IMAGE012
the result of calculating the reject ratio above the tolerance upper bound USL is as follows:
Figure DEST_PATH_IMAGE014
the cumulative probability area of the region between the lower tolerance bound and the upper tolerance bound is:
Figure DEST_PATH_IMAGE016
therefore, the yield is P good =P(LSL≤
Figure 190682DEST_PATH_IMAGE017
≤USL)；
Step four, calculating the DPMO of million chance defects, wherein the DPMO = DPO 10^6, and the DPO value is 1-P good Inquiring a corresponding relation table of DMPO and sigma to obtain a process sigma value Z of sensing data of the current sensing equipment of the Internet of things;
step five, evaluating the quality of sensing data of the continuous Internet of things sensing equipment according to the flow sigma value Z, and creating a linear regression model to predict the quality of the sensing data of the Internet of things sensing equipment, wherein the method comprises the following steps: the linear regression model is: y =
Figure DEST_PATH_IMAGE018
(x)=
Figure 131962DEST_PATH_IMAGE019
0 +
Figure 603394DEST_PATH_IMAGE019
1 x, wherein
Figure DEST_PATH_IMAGE020
(x) Representing a functional mapping from x to y,
Figure 330042DEST_PATH_IMAGE021
0 and
Figure 228728DEST_PATH_IMAGE021
1 and inquiring the target output variable through a corresponding relation table of DMPO and sigma to obtain a process sigma value Z of the sensing data of the current sensing equipment, wherein the larger the process sigma value Z is, the better the sensing data quality of the sensing equipment of the internet of things is.
2. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method for evaluating the perceptual data quality of the internet-of-things sensing device according to claim 1 when executing the computer program.
3. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method for estimating perceptual data quality of an internet of things sensing device according to claim 1.
CN202210875069.3A 2022-07-25 2022-07-25 Method for evaluating quality of sensing data of sensing equipment of Internet of things Active CN114936207B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210875069.3A CN114936207B (en) 2022-07-25 2022-07-25 Method for evaluating quality of sensing data of sensing equipment of Internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210875069.3A CN114936207B (en) 2022-07-25 2022-07-25 Method for evaluating quality of sensing data of sensing equipment of Internet of things

Publications (2)

Publication Number Publication Date
CN114936207A CN114936207A (en) 2022-08-23
CN114936207B true CN114936207B (en) 2022-11-25

Family

ID=82868892

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210875069.3A Active CN114936207B (en) 2022-07-25 2022-07-25 Method for evaluating quality of sensing data of sensing equipment of Internet of things

Country Status (1)

Country Link
CN (1) CN114936207B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117708615B (en) * 2024-02-04 2024-05-17 芯联集成电路制造股份有限公司 Product detection method and processing equipment monitoring method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101477653A (en) * 2008-12-29 2009-07-08 大唐软件技术股份有限公司 Processing method and system for data quality
CN110727665B (en) * 2019-09-23 2022-11-08 江河瑞通（北京）技术有限公司 Internet of things equipment reported data quality analysis method and system
CN113592314B (en) * 2021-08-02 2024-03-26 红云红河烟草(集团)有限责任公司 Sigma level-based silk making process quality evaluation method
CN115114348A (en) * 2022-01-30 2022-09-27 希望知舟技术(深圳)有限公司 Parameter quality management method, related device and medium program product

Also Published As

Publication number Publication date
CN114936207A (en) 2022-08-23

Similar Documents

Publication Publication Date Title
CN112543470B (en) Terminal positioning method and system based on machine learning
CN114936207B (en) Method for evaluating quality of sensing data of sensing equipment of Internet of things
CN105719033A (en) Method and device for identifying risk in object
CN113408947B (en) Intelligent manufacturing industrial production data acquisition and analysis method, equipment and computer storage medium
CN105468922B (en) A kind of live electromagnetic environment Signal online analysis and intimidation estimating method
CN113449703B (en) Quality control method and device for environment online monitoring data, storage medium and equipment
CN113407517A (en) Data quality health degree analysis method and system based on multidimensional analysis technology
CN108009740B (en) Intelligent fine identification system and method for tobacco essence and flavor
CN116879831A (en) Intelligent ammeter monitoring method and system based on Internet of things
CN113110961B (en) Equipment abnormality detection method and device, computer equipment and readable storage medium
CN114202179A (en) Target enterprise identification method and device
Giacobbe et al. Evaluating information quality in delivering IoT-as-a-service
CN112565422B (en) Method, system and storage medium for identifying fault data of power internet of things
CN116257926B (en) BIM-based Internet of things data binding method, device, equipment and storage medium
CN112561333A (en) Assessment data processing method and device, electronic equipment and storage medium
CN114419034B (en) Automatic detection method, system and medium for intelligent wearable silica gel material
CN116341653A (en) Analytic hierarchy process model weight obtaining method and related equipment
CN116341793A (en) Block chain-based method and device for determining carbon emission of product
WO2023085992A1 (en) Image analysis of cut flowers
CN109242578A (en) Value of house prediction technique, device, computer equipment and storage medium
CN114971532A (en) Enterprise full-channel member management method and system based on big data
Potter et al. Antecedents and consequences of supply network enabled innovation: evidence from Toyota
CN114189506B (en) Equipment inspection method, device and system
CN113342872B (en) PUE energy consumption monitoring-based method and electronic equipment
CN116664021B (en) Factory inspection auxiliary decision-making system and method based on mobile terminal

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