CN116305160A - Configuration method and system for algorithm quantity transmission calculation for algorithm tracing - Google Patents
Configuration method and system for algorithm quantity transmission calculation for algorithm tracing Download PDFInfo
- Publication number
- CN116305160A CN116305160A CN202310291802.1A CN202310291802A CN116305160A CN 116305160 A CN116305160 A CN 116305160A CN 202310291802 A CN202310291802 A CN 202310291802A CN 116305160 A CN116305160 A CN 116305160A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- reference data
- standard reference
- module
- traced
- 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.)
- Pending
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 281
- 238000004364 calculation method Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000005540 biological transmission Effects 0.000 title claims abstract description 51
- 238000011156 evaluation Methods 0.000 claims abstract description 25
- 238000005259 measurement Methods 0.000 claims abstract description 24
- 239000000470 constituent Substances 0.000 claims abstract description 5
- 238000012795 verification Methods 0.000 claims description 35
- 239000007787 solid Substances 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 11
- 102000009027 Albumins Human genes 0.000 description 8
- 108010088751 Albumins Proteins 0.000 description 8
- 238000003908 quality control method Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 5
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 238000012067 mathematical method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010339 medical test Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013522 software testing Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/57—Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Security & Cryptography (AREA)
- Quality & Reliability (AREA)
- Storage Device Security (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Stored Programmes (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A configuration method for algorithm quantity transmission calculation of algorithm tracing includes the steps: s100, logging in a standard reference data maker; s200, verifying the identity of a standard reference data maker; s300, filling basic information of a target tracing algorithm by a standard reference data maker; s400, uploading a corresponding standard reference data packet by a standard reference data maker; s500, generating standard reference data ID for each group of standard reference data in the standard reference data packet, and marking three constituent parts of the standard reference data in the same group as the same ID; s600, the standard reference data maker configures an algorithm quantity transmission software module corresponding to the standard reference data packet. The present disclosure discloses a complete set of algorithm tracing correlation methods and systems, which lays a solid quantitative measurement and evaluation technical foundation for online algorithm tracing.
Description
Technical Field
The disclosure relates to the field of metering, and in particular relates to a configuration method and a configuration system for algorithm quantity transmission calculation for algorithm tracing so as to ensure and evaluate accuracy and reliability of a software algorithm in magnitude.
Background
The software is used for expanding human thinking, and has the remarkable advantages of low cost, flexibility, functional complexity and the like. However, from the metering perspective, the software also has the defects of easy cheating and tampering, difficult Bug discovery, poor compliance of laws and regulations and the like, and the software also exposes some problems in the use of metering devices.
The biggest difficulty faced in the metering field at present is how to guarantee and evaluate the influence of a software algorithm in a metering device on the accuracy and reliability of the value. For example, inputting the same data into functionally identical programs written by different programmers may differ in the output results, making it difficult to determine the accuracy of both software algorithms in terms of metering requirements. Even if the output results are the same, it is difficult to judge compliance of the software algorithm with the metering regulations.
How to guarantee and evaluate the accuracy and reliability of the software algorithm in magnitude is the focus of attention in the field of global metering, but until the present, the related research on the accuracy and reliability of the software algorithm is still in the algorithm evaluation level, and belongs to qualitative judgment. The method aims to ensure and evaluate the accuracy and reliability of the software algorithm in magnitude, and most importantly, the method can trace the source of the algorithm.
Disclosure of Invention
In order to solve the technical problems, the present disclosure provides a whole set of methods and systems related to algorithm tracing, so as to ensure and evaluate accuracy and reliability of the software algorithm in magnitude.
The present disclosure discloses a configuration method for algorithm quantity transmission calculation for algorithm tracing, which comprises the following steps:
s100, logging in a standard reference data maker;
s200, verifying the identity of a standard reference data maker;
s300, filling basic information of a target tracing algorithm by a standard reference data maker;
s400, uploading a corresponding standard reference data packet by a standard reference data maker;
s500, generating standard reference data ID for each group of standard reference data in the standard reference data packet, and marking three constituent parts of the standard reference data in the same group as the same ID;
s600, the standard reference data maker configures an algorithm quantity transmission software module corresponding to the standard reference data packet.
In addition, the disclosure also discloses a configuration system for algorithm quantity transmission calculation of algorithm tracing, which comprises:
a login module, an identity verification module, a filling algorithm basic information module, an uploading standard reference data packet module, a standard reference data ID generation module and a configuration algorithm quantity transmission software module, wherein,
the login module is used for logging in by a standard reference data maker;
the identity verification module is used for verifying the identity of the standard reference data maker;
the filling algorithm basic information module is used for filling basic information of a target tracing algorithm by a standard reference data maker;
the standard reference data packet uploading module is used for uploading corresponding standard reference data packets;
the standard reference data ID generation module is used for generating standard reference data IDs for each group of standard reference data in the standard reference data packet, and marking three components of the standard reference data in the same group as the same ID;
and configuring an algorithm quantity transmission software module, wherein the algorithm quantity transmission software module is used for configuring the algorithm quantity transmission software module corresponding to the standard reference data packet by the standard reference data maker.
In addition, the disclosure also discloses a method for acquiring standard reference data, which comprises the following steps:
ST100, logging in a user of a to-be-traced algorithm;
ST200, user identity verification of a to-be-traced algorithm;
ST300, filling algorithm tracing application information of a to-be-traced algorithm by a to-be-traced algorithm user;
ST400, according to the algorithm tracing application information, inquiring basic information of a target tracing algorithm in the configuration system of the algorithm quantity transmission calculation, and generating a standard reference data packet when the algorithm tracing application information is matched with the basic information of the target tracing algorithm;
ST500, the algorithm user to be traced acquires standard reference data from the standard reference data packet.
Preferably, the method comprises the steps of,
in ST300, the algorithm tracing application information includes: the name of the algorithm to be traced, the name of the applicant, the contact way, the unit to which the applicant belongs, the application date and the like.
Preferably, the method comprises the steps of,
in ST500, the standard reference data includes standard reference input data.
In addition, the disclosure also discloses a standard reference data system for implementing any standard reference data acquisition method, which comprises the following steps:
the system comprises a login module, an identity verification module, a filling algorithm tracing application information module, a standard reference data packet generation module and a standard reference data acquisition module, wherein,
the login module is used for logging in the to-be-traced algorithm user;
the identity verification module is used for user identity verification of the algorithm to be traced;
the filling algorithm tracing application information module is used for filling algorithm tracing application information of the algorithm to be traced by the user of the algorithm to be traced;
the standard reference data packet generation module is used for inquiring basic information of a target tracing algorithm in the configuration system of the algorithm quantity transmission calculation according to the algorithm tracing application information, and generating a standard reference data packet when the algorithm tracing application information is matched with the basic information of the target tracing algorithm;
the standard reference data acquisition module is used for acquiring standard reference data from the standard reference data packet by the algorithm user to be traced.
In addition, the disclosure also discloses a method for acquiring the algorithm tracing result, which comprises the following steps:
STE100, logging in a user of the algorithm to be traced;
STE200, user identity verification of the algorithm to be traced;
STE300, a user of the algorithm to be traced fills in a calculation result of the algorithm to be traced corresponding to the applied standard reference data;
STE400, inquiring standard reference data in the configuration system of the algorithm quantity transmission calculation to verify the applied standard reference data, and calculating an indication error according to the calculation result of the algorithm to be traced and the corresponding standard reference data after verifying that the error is absent;
STE500, evaluating measurement uncertainty of the indication error;
STE600, based on the evaluation, generates a digital/electronic certificate or digital/electronic report with a measurement uncertainty rating as an algorithmic traceability result.
Preferably, the method further comprises the following steps:
STE700, the user of the algorithm to be traced obtains the digital/electronic certificate or digital/electronic report.
Preferably, STE500 further comprises the sub-steps of:
STE501, transmitting the calculation result of the algorithm to be traced to an algorithm quantity transmission software module, calculating the evaluation index Y of the algorithm to be traced, and evaluating the measurement uncertainty.
In addition, the disclosure further discloses an algorithm quantity transmission system for implementing any method for acquiring the algorithm tracing result, which comprises the following steps:
the system comprises a login module, an identity verification module, an algorithm calculation result module for filling in an algorithm to be traced, a value error calculation module, an evaluation module, an algorithm tracing result generation module and an algorithm tracing result acquisition module, wherein,
the login module is used for logging in the to-be-traced algorithm user;
the identity verification module is used for user identity verification of the algorithm to be traced;
the algorithm calculation result module is used for filling the algorithm to be traced, and is used for filling the calculation result of the algorithm to be traced corresponding to the applied standard reference data by the user of the algorithm to be traced;
the indicating value error calculation module is used for inquiring standard reference data in the configuration system of the algorithm quantity transmission calculation to verify the applied standard reference data, and calculating the indicating value error according to the calculation result of the algorithm to be traced and the corresponding standard reference data after the verification is correct;
the evaluation module is used for evaluating uncertainty of the indication error measurement;
the algorithm tracing result generation module is used for generating a digital/electronic certificate or a digital/electronic report as an algorithm tracing result based on the evaluation;
and the algorithm tracing result acquisition module is used for acquiring the digital/electronic certificate or the digital/electronic report by the algorithm user to be traced.
In summary, the present disclosure tightly combines a metering technology and a software testing technology, takes standard reference data generated by a standard reference data maker as the highest standard of tracing, obtains a calculation result by inputting standard reference data into an algorithm to be traced, calculates an indication error according to the calculation result and the standard reference data, performs measurement uncertainty assessment on the indication error, and finally generates an algorithm tracing evidence (report) to complete the tracing of the algorithm. In the process, the method and the system for configuring algorithm quantity transmission calculation for algorithm tracing, the method and the system for acquiring standard reference data, the method and the system for acquiring algorithm tracing results are all innovated, a whole set of algorithm tracing method and system are completely disclosed, and the method and the system for realizing online algorithm tracing for the algorithm to be traced are designed, so that a solid quantitative measurement and evaluation technical basis is laid for the algorithm to be traced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the disclosure and together with the description serve to explain the principles of the disclosure.
FIG. 1 is a flow chart of a configuration method for algorithm metric calculation for algorithm tracing in an embodiment of the disclosure;
FIG. 2 is a flow chart of a method for obtaining standard reference data in one embodiment of the present disclosure;
fig. 3 is a flowchart of a method for obtaining an algorithm tracing result in an embodiment of the disclosure.
Detailed Description
The present disclosure is described in further detail below with reference to the drawings and the embodiments. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant content and not limiting of the present disclosure. It should be further noted that, for convenience of description, only a portion relevant to the present disclosure is shown in the drawings.
In addition, embodiments of the present disclosure and features of the embodiments may be combined with each other without conflict. The technical aspects of the present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Unless otherwise indicated, the exemplary implementations/embodiments shown are to be understood as providing exemplary features of various details of some ways in which the technical concepts of the present disclosure may be practiced. Thus, unless otherwise indicated, features of the various implementations/embodiments may be additionally combined, separated, interchanged, and/or rearranged without departing from the technical concepts of the present disclosure.
The use of cross-hatching and/or shading in the drawings is typically used to clarify the boundaries between adjacent components. As such, the presence or absence of cross-hatching or shading does not convey or represent any preference or requirement for a particular material, material property, dimension, proportion, commonality between illustrated components, and/or any other characteristic, attribute, property, etc. of a component, unless indicated. In addition, in the drawings, the size and relative sizes of elements may be exaggerated for clarity and/or descriptive purposes. While the exemplary embodiments may be variously implemented, the specific process sequences may be performed in a different order than that described. For example, two consecutively described processes may be performed substantially simultaneously or in reverse order from that described. Moreover, like reference numerals designate like parts.
When an element is referred to as being "on" or "over", "connected to" or "coupled to" another element, it can be directly on, connected or coupled to the other element or intervening elements may be present. However, when an element is referred to as being "directly on," "directly connected to," or "directly coupled to" another element, there are no intervening elements present. For this reason, the term "connected" may refer to physical connections, electrical connections, and the like, with or without intermediate components.
For descriptive purposes, the present disclosure may use spatially relative terms such as "under … …," under … …, "" under … …, "" lower, "" above … …, "" upper, "" above … …, "" higher "and" side (e.g., as in "sidewall"), etc., to describe one component's relationship to another (other) component as illustrated in the figures. In addition to the orientations depicted in the drawings, the spatially relative terms are intended to encompass different orientations of the device in use, operation, and/or manufacture. For example, if the device in the figures is turned over, elements described as "under" or "beneath" other elements or features would then be oriented "over" the other elements or features. Thus, the exemplary term "below" … … can include both "above" and "below" orientations. Furthermore, the device may be otherwise positioned (e.g., rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Furthermore, when the terms "comprises" and/or "comprising," and variations thereof, are used in the present specification, the presence of stated features, integers, steps, operations, elements, components, and/or groups thereof is described, but the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof is not precluded. It is also noted that, as used herein, the terms "substantially," "about," and other similar terms are used as approximation terms and not as degree terms, and as such, are used to explain the inherent deviations of measured, calculated, and/or provided values that would be recognized by one of ordinary skill in the art.
In order to facilitate further understanding of the present disclosure, first, description will be made of an execution body related to the present disclosure, and in the present disclosure, the following definitions are mainly related in the whole algorithm tracing process:
1. the user of the algorithm to be traced refers to a party with the algorithm to be traced;
2. the standard reference data system is a system which allows a standard reference data maker to upload standard reference data packets and configure algorithm quantity transmission software modules and can respond to the application of a to-be-traced algorithm user and issue standard reference data; wherein, the liquid crystal display device comprises a liquid crystal display device,
for standard reference data, taking the detection data of an albumin laboratory of a patient in medical test as an example, preparing and generating standard reference data of the subdivision field by experts of China's measurement science institute and experts in related industries according to the national republic of China (metering method), reference to the American standard reference data method (US), combination of clinical industry standard (clinical test quantitative determination indoor quality control (WS/T641-2018) and detection data characteristics of the albumin laboratory of the patient;
the standard reference data packet comprises three types of standard reference data sets, wherein each type of standard reference data set comprises a plurality of groups of standard reference data so as to form a data set, and each group of standard reference data comprises three parts: standard reference input data (e.g., including 10 detection data), standard reference output data (e.g., tag 0 or 1), measurement uncertainty for the set of standard reference data;
3. the algorithm quantity transmission software module is a module for realizing quantity transmission calculation for a to-be-traced algorithm; wherein, the liquid crystal display device comprises a liquid crystal display device,
the quantitative transmission calculation means that two types of data sets are calculated through a statistical or other mathematical method, and finally an evaluation index Y of a to-be-traced algorithm and corresponding measurement uncertainty are obtained; one of the two types of data sets is an output result data set obtained by substituting standard reference input data in a standard reference data packet into a user to-be-traced algorithm, and the other type is a standard reference output data set in a corresponding standard reference data packet;
4. the algorithm quantity transmission system is a system for providing an algorithm tracing function for a user of an algorithm to be traced.
Referring to fig. 1, in one embodiment, the present disclosure discloses a configuration method for algorithm metric calculation for algorithm tracing, including the following steps:
s100, logging in a standard reference data maker;
s200, verifying the identity of a standard reference data maker;
as mentioned above, the standard reference data maker can be the expert of China national institute of metrology and the expert of related industries, which should be authorized by related departments;
s300, filling basic information of a target tracing algorithm by a standard reference data maker;
s400, uploading a corresponding standard reference data packet by a standard reference data maker;
s500, generating standard reference data ID for each group of standard reference data in the standard reference data packet, and marking three constituent parts of the standard reference data in the same group as the same ID;
s600, the standard reference data maker configures an algorithm quantity transmission software module corresponding to the standard reference data packet.
To facilitate understanding of the above embodiments, for example:
in medical examination, before the patient albumin examination report is formally released, quality control is required to be carried out on the detection data of the patient albumin laboratory obtained by detection so as to infer and evaluate the reliability degree of the detection result, thereby judging whether the examination report can be sent out or not, and timely finding out and removing unreliable factors of a quality link;
a certain software developer develops a machine learning quality control algorithm of the patient albumin laboratory detection data; in order to meter and evaluate the algorithm, a configuration method of the algorithm metric calculation needs to be applied for the specific algorithm of the subdivision domain, wherein,
the standard reference data maker logs in the system, fills in the machine learning quality control algorithm information of the detection data of the albumin laboratory of the patient through identity verification, and comprises the following steps: algorithm names, standard reference data maker names and contact ways, units of the algorithm, simple description of the algorithm and the like;
as for uploading the standard reference data packet, the three constituent parts of the standard reference data of the same group are marked with the same ID, such as D0001;
as for the configuration algorithm quantity transmission software module, specific statistical or other mathematical methods can be configured for the two types of data sets, and the specific statistical or other mathematical methods are taken as key of measurement, so that the evaluation index Y of the algorithm to be traced and the corresponding measurement uncertainty are obtained through the method; one of the two types of data sets is an output result data set obtained by substituting standard reference input data in a standard reference data packet into a user to-be-traced algorithm, and the other type is a standard reference output data set in a corresponding standard reference data packet.
Therefore, the configuration method for algorithm quantity transmission calculation for algorithm tracing is realized through the configuration method, and compared with the traditional qualitative judgment, the configuration method can ensure quantitative measurement and evaluate algorithm tracing.
In another embodiment, the present disclosure discloses a configuration system for algorithm metric computation for algorithm tracing, comprising:
a login module, an identity verification module, a filling algorithm basic information module, an uploading standard reference data packet module, a standard reference data ID generation module and a configuration algorithm quantity transmission software module, wherein,
the login module is used for logging in by a standard reference data maker;
the identity verification module is used for verifying the identity of the standard reference data maker;
the filling algorithm basic information module is used for filling basic information of a target tracing algorithm by a standard reference data maker;
the standard reference data packet uploading module is used for uploading corresponding standard reference data packets;
the standard reference data ID generation module is used for generating standard reference data IDs for each group of standard reference data in the standard reference data packet, and marking three components of the standard reference data in the same group as the same ID;
and configuring an algorithm quantity transmission software module, wherein the algorithm quantity transmission software module is used for configuring the algorithm quantity transmission software module corresponding to the standard reference data packet by the standard reference data maker.
Referring to fig. 2, in another embodiment, the disclosure discloses a method for obtaining standard reference data, including the following steps:
ST100, logging in a user of a to-be-traced algorithm;
ST200, user identity verification of a to-be-traced algorithm;
ST300, filling algorithm tracing application information of a to-be-traced algorithm by a to-be-traced algorithm user;
ST400, according to the algorithm tracing application information, inquiring basic information of a target tracing algorithm in the configuration system of the algorithm quantity transmission calculation, and generating a standard reference data packet when the algorithm tracing application information is matched with the basic information of the target tracing algorithm;
ST500, the algorithm user to be traced acquires standard reference data from the standard reference data packet.
In a further embodiment of the present invention,
in ST300, the algorithm tracing application information includes: the name of the algorithm to be traced, the name of the applicant, the contact way, the unit to which the applicant belongs, the application date and the like.
In a further embodiment of the present invention,
in ST500, the standard reference data includes standard reference input data.
Thus, the user of the algorithm to be traced can test the algorithm to be traced according to the standard reference input data as the input of the algorithm to be traced, so as to obtain the output of the algorithm to be traced.
It can be appreciated that the testing process prioritizes testing in a trusted environment, such as the testing entrusting a trusted and authoritative third party to conduct testing or to conduct supervision. The algorithm tracing can be realized by carrying out data processing on the output and the standard reference output data corresponding to the standard reference data packet according to a standard program; or directly transmitting the output to an algorithm quantity transmission software module, and calculating an evaluation index Y and corresponding measurement uncertainty of the algorithm to be traced.
Further optionally, the standard reference data comprises a standard reference input data set. Substituting the acquired standard reference input data set into the algorithm to be traced by the user of the algorithm to be traced, and operating the algorithm to obtain an output result set; logging in again by the user of the traceability algorithm, and uploading the obtained output result set through identity verification; and the output result set is transmitted to an algorithm quantity transmission software module, and an evaluation index Y and corresponding measurement uncertainty of the algorithm to be traced are calculated.
In another embodiment, the disclosure discloses a standard reference data system for implementing the method for acquiring standard reference data, which includes:
the system comprises a login module, an identity verification module, a filling algorithm tracing application information module, a standard reference data packet generation module and a standard reference data acquisition module, wherein,
the login module is used for logging in the to-be-traced algorithm user;
the identity verification module is used for user identity verification of the algorithm to be traced;
the filling algorithm tracing application information module is used for filling algorithm tracing application information of the algorithm to be traced by the user of the algorithm to be traced;
the standard reference data packet generation module is used for inquiring basic information of a target tracing algorithm in the configuration system of the algorithm quantity transmission calculation according to the algorithm tracing application information, and generating a standard reference data packet when the algorithm tracing application information is matched with the basic information of the target tracing algorithm;
the standard reference data acquisition module is used for acquiring standard reference data from the standard reference data packet by the algorithm user to be traced.
Referring to fig. 3, in another embodiment, the disclosure further discloses a method for obtaining an algorithm tracing result, including the following steps:
STE100, logging in a user of the algorithm to be traced;
STE200, user identity verification of the algorithm to be traced;
STE300, a user of the algorithm to be traced fills in a calculation result of the algorithm to be traced corresponding to the applied standard reference data;
STE400, inquiring standard reference data in the configuration system of the algorithm quantity transmission calculation to verify the applied standard reference data, and calculating an indication error according to the calculation result of the algorithm to be traced and the corresponding standard reference data after verifying that the error is absent;
STE500, evaluating measurement uncertainty of the indication error;
STE600, based on the evaluation, generates a digital/electronic certificate or digital/electronic report with a measurement uncertainty rating as an algorithmic traceability result.
In another embodiment, the method further comprises the steps of:
STE700, the user of the algorithm to be traced obtains the digital/electronic certificate or digital/electronic report.
In another embodiment, STE500 further comprises the sub-steps of:
STE501, transmitting the calculation result of the algorithm to be traced to an algorithm quantity transmission software module, calculating the evaluation index Y of the algorithm to be traced, and evaluating the measurement uncertainty.
Thus, when the STE600 generates the algorithm tracing result, the algorithm tracing result further comprises the evaluation index Y of the algorithm to be traced.
In another embodiment, the disclosure discloses an algorithm quantity transmission system for implementing the method for acquiring the tracing result of the algorithm, which includes:
the system comprises a login module, an identity verification module, an algorithm calculation result module for filling in an algorithm to be traced, a value error calculation module, an evaluation module, an algorithm tracing result generation module and an algorithm tracing result acquisition module, wherein,
the login module is used for logging in the to-be-traced algorithm user;
the identity verification module is used for user identity verification of the algorithm to be traced;
the algorithm calculation result module is used for filling the algorithm to be traced, and is used for filling the calculation result of the algorithm to be traced corresponding to the applied standard reference data by the user of the algorithm to be traced;
the indicating value error calculation module is used for inquiring standard reference data in the configuration system of the algorithm quantity transmission calculation to verify the applied standard reference data, and calculating the indicating value error according to the calculation result of the algorithm to be traced and the corresponding standard reference data after the verification is correct;
the evaluation module is used for evaluating uncertainty of the indication error measurement;
the algorithm tracing result generation module is used for generating a digital/electronic certificate or a digital/electronic report as an algorithm tracing result based on the evaluation;
and the algorithm tracing result acquisition module is used for acquiring the digital/electronic certificate or the digital/electronic report by the algorithm user to be traced.
For example, machine learning a quality control algorithm for a patient albumin laboratory test data as described above, the final algorithm traceability result may be as follows:
the value range of the evaluation index Y is [0,100% ], and when the value of Y tends to 100%, the output result of the algorithm to be traced is accurate and reliable enough. When the Y value tends to 0, the implementation process of the algorithm to be traced is not in accordance with the quality control requirement of laboratory detection data. The corresponding measurement uncertainty then accounts for the dispersion of the Y values. In this case, the evaluation index Y of the machine learning quality control algorithm of the patient albumin laboratory detection data is 71.3%, which indicates that the output result of the algorithm is basically accurate and reliable, but the design of the algorithm has some defects, for example, in this case, the input vectors corresponding to different features of the machine learning algorithm should be mutually independent, but in fact, through analysis of the data features of the training set, a certain correlation exists between the input vectors, which is related to the importing sequence of the whole detection data when the abnormal value is removed by the floating average method in the data preprocessing stage, and the algorithm formulator is suggested to mainly solve the problem in this aspect.
In the description of the present specification, reference to the terms "one embodiment/manner," "some embodiments/manner," "example," "specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment/manner or example is included in at least one embodiment/manner or example of the present disclosure. In this specification, the schematic representations of the above terms are not necessarily for the same embodiment/manner or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments/modes or examples. Furthermore, the various embodiments/modes or examples described in this specification and the features of the various embodiments/modes or examples can be combined and combined by persons skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, the meaning of "a plurality" is at least two, such as two, three, etc., unless explicitly specified otherwise.
It will be appreciated by those skilled in the art that the above-described embodiments are merely for clarity of illustration of the disclosure, and are not intended to limit the scope of the disclosure. Other variations or modifications will be apparent to persons skilled in the art from the foregoing disclosure, and such variations or modifications are intended to be within the scope of the present disclosure.
Claims (10)
1. A configuration method for algorithm quantity transmission calculation of algorithm tracing includes the following steps:
s100, logging in a standard reference data maker;
s200, verifying the identity of a standard reference data maker;
s300, filling basic information of a target tracing algorithm by a standard reference data maker;
s400, uploading a corresponding standard reference data packet by a standard reference data maker;
s500, generating standard reference data ID for each group of standard reference data in the standard reference data packet, and marking three constituent parts of the standard reference data in the same group as the same ID;
s600, the standard reference data maker configures an algorithm quantity transmission software module corresponding to the standard reference data packet.
2. A configuration system for algorithmic quantitative computation for algorithmic tracing, comprising:
a login module, an identity verification module, a filling algorithm basic information module, an uploading standard reference data packet module, a standard reference data ID generation module and a configuration algorithm quantity transmission software module, wherein,
the login module is used for logging in by a standard reference data maker;
the identity verification module is used for verifying the identity of the standard reference data maker;
the filling algorithm basic information module is used for filling basic information of a target tracing algorithm by a standard reference data maker;
the standard reference data packet uploading module is used for uploading corresponding standard reference data packets;
the standard reference data ID generation module is used for generating standard reference data IDs for each group of standard reference data in the standard reference data packet, and marking three components of the standard reference data in the same group as the same ID;
and configuring an algorithm quantity transmission software module, wherein the algorithm quantity transmission software module is used for configuring the algorithm quantity transmission software module corresponding to the standard reference data packet by the standard reference data maker.
3. A standard reference data acquisition method comprises the following steps:
ST100, logging in a user of a to-be-traced algorithm;
ST200, user identity verification of a to-be-traced algorithm;
ST300, filling algorithm tracing application information of a to-be-traced algorithm by a to-be-traced algorithm user;
ST400, according to the algorithm tracing application information, inquiring basic information of a target tracing algorithm in the configuration system of the algorithm quantity transmission calculation, and generating a standard reference data packet when the algorithm tracing application information is matched with the basic information of the target tracing algorithm;
ST500, the algorithm user to be traced acquires standard reference data from the standard reference data packet.
4. The method of claim 3, wherein,
in ST300, the algorithm tracing application information includes: the name of the algorithm to be traced, the name of the applicant, the contact way, the unit to which the applicant belongs, the application date and the like.
5. The method of claim 3, wherein,
in ST500, the standard reference data includes standard reference input data.
6. A standard reference data system for implementing the standard reference data acquisition method of any one of claims 4 to 5, comprising:
the system comprises a login module, an identity verification module, a filling algorithm tracing application information module, a standard reference data packet generation module and a standard reference data acquisition module, wherein,
the login module is used for logging in the to-be-traced algorithm user;
the identity verification module is used for user identity verification of the algorithm to be traced;
the filling algorithm tracing application information module is used for filling algorithm tracing application information of the algorithm to be traced by the user of the algorithm to be traced;
the standard reference data packet generation module is used for inquiring basic information of a target tracing algorithm in the configuration system of the algorithm quantity transmission calculation according to the algorithm tracing application information, and generating a standard reference data packet when the algorithm tracing application information is matched with the basic information of the target tracing algorithm;
the standard reference data acquisition module is used for acquiring standard reference data from the standard reference data packet by the algorithm user to be traced.
7. The method for acquiring the algorithm tracing result comprises the following steps:
STE100, logging in a user of the algorithm to be traced;
STE200, user identity verification of the algorithm to be traced;
STE300, a user of the algorithm to be traced fills in a calculation result of the algorithm to be traced corresponding to the applied standard reference data;
STE400, inquiring standard reference data in the configuration system of the algorithm quantity transmission calculation to verify the applied standard reference data, and calculating an indication error according to the calculation result of the algorithm to be traced and the corresponding standard reference data after verifying that the error is absent;
STE500, evaluating measurement uncertainty of the indication error;
STE600, based on the evaluation, generates a digital/electronic certificate or digital/electronic report with a measurement uncertainty rating as an algorithmic traceability result.
8. The method of claim 7, further comprising the step of:
STE700, the user of the algorithm to be traced obtains the digital/electronic certificate or digital/electronic report.
9. The method of claim 7, STE500 further comprising the sub-steps of:
STE501, transmitting the calculation result of the algorithm to be traced to an algorithm quantity transmission software module, calculating the evaluation index Y of the algorithm to be traced, and evaluating the measurement uncertainty.
10. An algorithm quantity transmission system for implementing the method for acquiring the traceability result of the algorithm according to any one of claims 7 to 9, comprising:
the system comprises a login module, an identity verification module, an algorithm calculation result module for filling in an algorithm to be traced, a value error calculation module, an evaluation module, an algorithm tracing result generation module and an algorithm tracing result acquisition module, wherein,
the login module is used for logging in the to-be-traced algorithm user;
the identity verification module is used for user identity verification of the algorithm to be traced;
the algorithm calculation result module is used for filling the algorithm to be traced, and is used for filling the calculation result of the algorithm to be traced corresponding to the applied standard reference data by the user of the algorithm to be traced;
the indicating value error calculation module is used for inquiring standard reference data in the configuration system of the algorithm quantity transmission calculation to verify the applied standard reference data, and calculating the indicating value error according to the calculation result of the algorithm to be traced and the corresponding standard reference data after the verification is correct;
the evaluation module is used for evaluating uncertainty of the indication error measurement;
the algorithm tracing result generation module is used for generating a digital/electronic certificate or a digital/electronic report as an algorithm tracing result based on the evaluation;
and the algorithm tracing result acquisition module is used for acquiring the digital/electronic certificate or the digital/electronic report by the algorithm user to be traced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310291802.1A CN116305160A (en) | 2022-05-07 | 2022-05-07 | Configuration method and system for algorithm quantity transmission calculation for algorithm tracing |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210492943.5A CN114912089B (en) | 2022-05-07 | 2022-05-07 | Configuration method and system for algorithm quantity transmission calculation for algorithm tracing |
| CN202310291802.1A CN116305160A (en) | 2022-05-07 | 2022-05-07 | Configuration method and system for algorithm quantity transmission calculation for algorithm tracing |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210492943.5A Division CN114912089B (en) | 2022-05-07 | 2022-05-07 | Configuration method and system for algorithm quantity transmission calculation for algorithm tracing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116305160A true CN116305160A (en) | 2023-06-23 |
Family
ID=82767114
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210492943.5A Active CN114912089B (en) | 2022-05-07 | 2022-05-07 | Configuration method and system for algorithm quantity transmission calculation for algorithm tracing |
| CN202310291802.1A Pending CN116305160A (en) | 2022-05-07 | 2022-05-07 | Configuration method and system for algorithm quantity transmission calculation for algorithm tracing |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210492943.5A Active CN114912089B (en) | 2022-05-07 | 2022-05-07 | Configuration method and system for algorithm quantity transmission calculation for algorithm tracing |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN114912089B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117953334A (en) * | 2024-03-26 | 2024-04-30 | 中国计量科学研究院 | Visual detection equipment dosage traceability metering device and method thereof |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102479351B (en) * | 2010-11-25 | 2015-11-25 | 西安计量技术研究院 | A kind of intelligent management method and system to newly-built measurement standard |
| CN106934630B (en) * | 2015-12-31 | 2021-07-27 | 济南大陆机电股份有限公司 | Measuring instrument quantity value tracing method |
| CN112036673A (en) * | 2019-05-17 | 2020-12-04 | 向友刚 | Measuring instrument quantity tracing method and measuring instrument management system |
| CN112577542A (en) * | 2019-09-27 | 2021-03-30 | 广州中测检测技术有限公司 | Measuring instrument and remote quantity transmission/tracing method thereof |
| CN111352998B (en) * | 2020-02-28 | 2021-09-21 | 中国计量科学研究院 | Trusted alliance block chain digital calibration certificate system and operation method thereof |
| CN111899034A (en) * | 2020-07-28 | 2020-11-06 | 安徽高山科技有限公司 | Anti-counterfeiting tracing query method for product tracing based on block chain |
| CN114255047A (en) * | 2020-09-25 | 2022-03-29 | 续科天下(北京)科技有限公司 | Pork traceability system based on block chain technology |
| CN114253995B (en) * | 2022-03-01 | 2022-05-27 | 深圳市明源云科技有限公司 | Data tracing method, device, equipment and computer readable storage medium |
-
2022
- 2022-05-07 CN CN202210492943.5A patent/CN114912089B/en active Active
- 2022-05-07 CN CN202310291802.1A patent/CN116305160A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN114912089A (en) | 2022-08-16 |
| CN114912089B (en) | 2023-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7027931B1 (en) | System for statistical analysis of quality control data | |
| Berge Kristensen et al. | Interpretation of EQA results and EQA-based trouble shooting | |
| Westgard | Managing quality vs. measuring uncertainty in the medical laboratory | |
| CN113049873B (en) | Current sensor, current measuring device, system, apparatus, and storage medium | |
| CN108427093A (en) | A kind of calibrating and measuring system and method for watt-hour meter automatic verification device | |
| CN114912089B (en) | Configuration method and system for algorithm quantity transmission calculation for algorithm tracing | |
| CN109444340A (en) | Flammable gas alarm automatic calibrator and its operating method based on image recognition | |
| CN109375142A (en) | Mutual-inductor tester calibration method and system based on kaiser window FFT filtering | |
| WO2023045216A1 (en) | Automatic measurement calibration method and device for ventilator, and storage medium | |
| CN110006588A (en) | A kind of pressure transmitter calibrating implementation method obtained automatically based on data | |
| CN111739274B (en) | Instrument management system, management platform, industrial instrument and method | |
| CN106200523B (en) | Flue-cured tobacco workshop condition monitors system | |
| CN114884657B (en) | Whole-course online automatic execution algorithm tracing method and system | |
| CN209764337U (en) | Automatic detection system | |
| CN112923967A (en) | Instrument calibration system supporting rapid assessment of instrument calibration uncertainty | |
| Flores et al. | Robust bootstrapped Mandel's h and k statistics for outlier detection in interlaboratory studies | |
| KR101438893B1 (en) | The apparatus and method for generation of two dimensional plot for trueness verification of In Vitro Diagnostic (IVD) quantitative laboratory test | |
| CN112988567A (en) | Crowdsourcing test automated evaluation method and device | |
| CN112305245B (en) | Sample analysis method and sample analysis system | |
| RU2764359C1 (en) | Device for diagnosing condition of equipment (options), method for diagnosing condition of equipment and system for diagnosing condition of equipment (options) | |
| CN106125646B (en) | A kind of data collecting system of flue-cured tobacco controller | |
| CN113959476B (en) | Intelligent instrument and meter verification system and method | |
| US7614274B1 (en) | Method for calibration adjustment verification | |
| CN209311427U (en) | Flammable gas alarm automatic calibrator based on image recognition | |
| CN115936936A (en) | On-line examination system for power cable accessory installation process |
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 |