CN115935191A - Big data analysis-based capacity measurement method and device - Google Patents
Big data analysis-based capacity measurement method and device Download PDFInfo
- Publication number
- CN115935191A CN115935191A CN202310011014.2A CN202310011014A CN115935191A CN 115935191 A CN115935191 A CN 115935191A CN 202310011014 A CN202310011014 A CN 202310011014A CN 115935191 A CN115935191 A CN 115935191A
- Authority
- CN
- China
- Prior art keywords
- capability
- capacity
- test
- factor
- item
- 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
- 238000007405 data analysis Methods 0.000 title claims abstract description 22
- 238000000691 measurement method Methods 0.000 title claims abstract description 15
- 238000012360 testing method Methods 0.000 claims abstract description 298
- 238000004458 analytical method Methods 0.000 claims abstract description 96
- 238000009826 distribution Methods 0.000 claims abstract description 75
- 238000005259 measurement Methods 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000010606 normalization Methods 0.000 claims description 30
- 238000013507 mapping Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 claims description 7
- 238000005192 partition Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 5
- 238000009795 derivation Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 34
- 238000010835 comparative analysis Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 238000011056 performance test Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 239000000470 constituent Substances 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 108700024394 Exon Proteins 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of intelligent measurement, and discloses a capacity measurement method and device based on big data analysis, wherein the method comprises the following steps: acquiring an application scene of capacity to be measured, identifying a capacity dimension factor of the capacity to be measured, and performing fuzzification processing on the capacity dimension factor to obtain a fuzzy capacity level; constructing an incidence relation between the capacity dimension factor and the capacity to be measured, and constructing a capacity analysis model according to the capacity dimension factor, the fuzzy capacity level and the incidence relation; testing a historical capability test object by using a pre-constructed capability test item to obtain historical test data; training the capacity analysis model to obtain a trained capacity analysis model; and determining the test data distribution of the real-time test data and the test item distribution of the capability test items by using the trained capability analysis model, and obtaining a capability measurement result according to the test data distribution and the test item distribution. The invention can improve the accuracy of capability measurement.
Description
Technical Field
The invention relates to the field of intelligent measurement, in particular to a capacity measurement method and device based on big data analysis.
Background
The ability measurement is an evaluation of the degree of ability level of an ability test subject by evaluating the performance or emotional judgment ability of the exons of the ability test subject.
Most conventional capability measures employ a capability quantization table or a single research measurement object for analysis, such as capability analysis of a tested object or quality capability analysis related to a test item or a test paper, and there is less comparative analysis between the research measurement object and the test item, so that capability difference analysis cannot be performed between different test items, between different research measurement object groups, and between a test item and a research measurement object group, thereby reducing accuracy of the capability measure.
Disclosure of Invention
The invention provides a capacity measurement method and device based on big data analysis, and mainly aims to improve the accuracy of capacity measurement.
In order to achieve the above object, the present invention provides a capacity measurement method based on big data analysis, including:
acquiring an application scene of capacity to be measured, identifying a capacity dimension factor of the capacity to be measured according to the application scene, and fuzzifying the capacity dimension factor by using a fuzzy rule of a pre-constructed capacity factor to obtain a fuzzy capacity level;
constructing an incidence relation between the ability dimension factor and the ability to be measured, and constructing an ability analysis model according to the ability dimension factor, the fuzzy ability level and the incidence relation;
acquiring a historical capability test object, and testing the historical capability test object by using a pre-constructed capability test item to obtain historical test data;
training the capability analysis model based on the historical test data to obtain a trained capability analysis model;
acquiring real-time test data, determining the test data distribution of the real-time test data and the test item distribution of the capability test items by using the trained capability analysis model, and acquiring a capability measurement result according to the test data distribution and the test item distribution.
Optionally, before the step of performing fuzzification processing on the capability dimension factor by using a pre-constructed factor fuzzy rule to obtain a fuzzy capability level, the method further includes: constructing the factor fuzzy rule, including:
constructing a factor space domain and a factor fuzzy set corresponding to the capability dimension factor,
constructing a membership function of the capability dimension factor by using the following formula:
wherein, mu (x) represents a membership function, x represents a capability dimension factor, and a, b and c represent critical constants;
constructing a fuzzy mapping relation between the factor space domain and the factor fuzzy set by utilizing a pre-constructed fuzzy logic algorithm according to the membership function, the factor space domain and the factor fuzzy set;
and determining the factor fuzzy rule according to the fuzzy mapping relation.
Optionally, the fuzzifying the capability dimension factor by using a pre-constructed factor fuzzy rule to obtain a fuzzy capability level includes:
identifying a membership function and a factor fuzzy set in a pre-constructed factor fuzzy rule, and fuzzifying the capability dimensionality factor according to the membership function to obtain the membership of the capability dimensionality factor;
and determining a pre-constructed competence factor level in the factor fuzzy set according to the membership and the factor fuzzy rule, and determining the fuzzy competence level according to the competence factor level.
Optionally, the constructing an association relationship between the capability dimension factor and the capability to be measured includes:
carrying out similar dimension division on the capacity dimension factor to obtain a division factor dimension, and carrying out capacity gradient division on the capacity to be measured to obtain a division capacity gradient;
and constructing an incidence relation between the capacity dimension factor and the capacity to be measured according to the division factor dimension and the division capacity gradient.
Optionally, the constructing an association relationship between the capability dimension factor and the capability to be measured according to the partition factor dimension and the partition capability gradient includes:
respectively extracting factor semantic information and capability semantic information of the division factor dimension and the division capability gradient, and vectorizing the factor semantic information and the capability semantic information to obtain a factor semantic vector and a capability semantic vector;
calculating semantic similarity between each factor semantic vector and the capability semantic vector, calculating the maximum similarity of the semantic similarities, and identifying the mapping relation between the factor semantic vector corresponding to the maximum similarity and the capability semantic vector;
and determining the association relationship between the capability dimension factor corresponding to the factor semantic vector and the capability to be measured corresponding to the capability semantic vector according to the mapping relationship.
Optionally, the training the capability analysis model based on the historical test data to obtain a trained capability analysis model includes:
identifying a historical capability test object and a capability test item corresponding to the historical test data, adjusting the historical test data according to the historical capability test object and the capability test item, and constructing an object item data table;
according to the object item data table, the following formula is utilized:
wherein the content of the first and second substances,
indicates the probability that the mth historical capability test subject answered the ith test item correctly, and ` H `>
Represents the capability value, based on the status of the mth historical capability test subject>
Represents the difficulty value of the ith test item, <' > based on the comparison>
The test result of the mth historical ability test object to answer the ith test item is shown, exp represents an exponential function with a natural constant as a base,
constructing a likelihood function of the object item data table, and identifying parameter variables in the likelihood function;
carrying out logarithm processing on the likelihood function to obtain a logarithm likelihood function, and carrying out derivation processing on the parameter variable by the logarithm likelihood function to obtain a likelihood equation;
solving the likelihood equation to obtain a likelihood solution of the likelihood equation, and determining a parameter variable value of the parameter variable according to the likelihood solution, wherein the parameter variable comprises object capacity and project difficulty;
respectively calculating a capacity mean value and a difficulty mean value of each object capacity and each project difficulty according to the parameter variable values, and taking the capacity mean value and the difficulty mean value as a capacity estimation value and a difficulty estimation value;
constructing a logarithm scale, and carrying out normalization processing on the capacity estimated value and the difficulty estimated value to obtain a normalization capacity estimated value and a normalization difficulty estimated value under the logarithm scale;
selecting an analysis index of the ability analysis model, calculating an index value of the analysis index according to the normalization ability estimation value and the normalization difficulty estimation value, carrying out analysis processing and adjustment processing on the ability analysis model according to the index value to obtain an ability analysis adjustment model, and determining the trained ability analysis model according to the ability analysis adjustment model.
Optionally, the constructing a likelihood function of the object item data table includes:
identifying correct item numbers and wrong item numbers which are tested correctly and tested wrongly in the object item data table, and constructing a correct item set and a wrong item set according to the correct item numbers and the wrong item numbers;
according to the correct item set and the wrong item set, constructing a likelihood function of the object item data table by using the following formula:
wherein, the first and the second end of the pipe are connected with each other,
likelihood function representing a table of target item data, based on the likelihood value of the target item data>
Represents the capability value, based on the status of the mth historical capability test subject>
Represents the difficulty value of the 1 st to nth test item>
Represents the probability that the mth historical capability test object correctly answered the ith test item, L represents the correct set of items, Q represents the incorrect set of items, i represents the test item number of the correct set of items, and/or ` H `>
A test item number representing a set of erroneous items.
Optionally, the determining, by using the trained capability analysis model, the test data distribution of the real-time test data and the test item distribution of the capability test item includes:
calculating a real-time capability value and a real-time project difficulty value of the real-time test data, and carrying out normalization processing on the real-time capability value and the real-time project difficulty value to obtain a normalization capability value and a normalization difficulty value;
constructing a nostalgic graph of the real-time test data and the ability test items according to the normalization ability values and the normalization difficulty values;
and determining the test data distribution and the test item distribution according to the Huai diagram.
Optionally, the obtaining a capability measurement result according to the test data distribution and the test item distribution includes:
acquiring a capability test object corresponding to the test data distribution, calculating a capability value range of the capability test object, and calculating a capability value span according to the capability value range;
acquiring capability test items corresponding to the distribution of the test items, calculating the difficulty value range of the capability test items, and calculating the difficulty value span according to the difficulty value range;
calculating the matching degree of the capability test object and the capability test item according to the capability value span and the difficulty value span;
calculating the tested capacity mean value and the project difficulty mean value of the test data distribution and the test project distribution, and comparing the tested capacity mean value and the project difficulty mean value to obtain a comparison result;
and analyzing the matching degree and the comparison result to obtain a capability measurement result.
In order to solve the above problems, the present invention further provides a capacity measuring apparatus based on big data analysis, the apparatus including:
the capacity factor identification module is used for acquiring an application scene of capacity to be measured, identifying a capacity dimension factor of the capacity to be measured according to the application scene, and fuzzifying the capacity dimension factor by using a fuzzy rule of a pre-constructed capacity factor to obtain a fuzzy capacity level;
the capacity analysis model building module is used for building an incidence relation between the capacity dimension factor and the capacity to be measured and building a capacity analysis model according to the capacity dimension factor, the fuzzy capacity level and the incidence relation;
the historical data acquisition module is used for acquiring a historical capability test object, and testing the historical capability test object by using a pre-constructed capability test item to obtain historical test data;
the capability model training module is used for training the capability analysis model based on the historical test data to obtain a trained capability analysis model;
and the capability measurement result generation module is used for acquiring real-time test data, determining the test data distribution of the real-time test data and the test item distribution of the capability test items by using the trained capability analysis model, and obtaining a capability measurement result according to the test data distribution and the test item distribution.
The embodiment of the invention can determine the service background of the capacity to be measured by acquiring the application scene of the capacity to be measured, identify the capacity dimension factor of the capacity to be measured as the basis for the subsequent capacity measurement and evaluation, and utilize the pre-constructed factor fuzzy rule to fuzzify the capacity dimension factor to establish the capacity factor characteristic which is more in line with the actual application scene and has more practical interpretation significance; secondly, the embodiment of the invention can indirectly measure the capacity to be measured by measuring the capacity dimension factor by constructing the incidence relation between the capacity dimension factor and the capacity to be measured, which has great influence on the accuracy of the capacity measurement, and according to the capacity dimension factor, the fuzzy capacity level and the incidence relation, a basic analysis model which can determine the capacity measurement is constructed by a capacity analysis model, so as to obtain a source basis of historical data which can be provided by a historical capacity test object for realizing the multi-dimensional measurement of the capacity subsequently, and the historical capacity test object is tested by utilizing a pre-constructed capacity test item to obtain historical test data which is used as a training sample for constructing the capacity analysis model subsequently; furthermore, in the embodiment of the present invention, based on the historical test data, the trained capability analysis model may be determined by training the capability analysis model to implement comparative analysis on capability measurement from multiple dimensions, obtain real-time test data to provide raw data for real-time capability measurement, and by using the trained capability analysis model, the test data distribution of the real-time test data and the test item distribution of the capability test items may be determined and calculated to implement comparative analysis between capability test objects, between capability test items, and between a capability test object and a capability test item in the following, and a final more accurate capability measurement result may be obtained according to the test data distribution and the test item distribution, and a multidimensional comparison may be implemented, thereby providing a guidance direction for a real-situation adjustment strategy. Therefore, the capacity measurement method and device based on big data analysis provided by the embodiment of the invention can improve the accuracy of capacity measurement.
Drawings
Fig. 1 is a schematic flowchart of a capability measurement method based on big data analysis according to an embodiment of the present invention;
FIG. 2 is a block diagram of a capacity measuring device based on big data analysis according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the invention provides a capacity measuring method based on big data analysis. The execution subject of the big data analysis-based capability measurement method includes, but is not limited to, at least one of the electronic devices of the server, the terminal, and the like, which can be configured to execute the method provided by the embodiment of the present invention. In other words, the capability measurement method based on big data analysis may be performed by software or hardware installed in a terminal device or a server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like.
Fig. 1 is a schematic flow chart of a capacity measurement method based on big data analysis according to an embodiment of the present invention. In an embodiment of the present invention, the capacity measurement method based on big data analysis includes:
s1, acquiring an application scene of capacity to be measured, identifying a capacity dimension factor of the capacity to be measured according to the application scene, and fuzzifying the capacity dimension factor by using a pre-constructed factor fuzzy rule to obtain a fuzzy capacity level.
In the embodiment of the present invention, the application scenario refers to an overview scenario of a group of situations that may occur in a service environment, and the overview scenario may be understood as a combination of events and factors that constitute a current condition of a service and some predictions of events that may occur in the future, which may be obtained through a data script that may be compiled through a JS script language.
Furthermore, according to the application scenario, the ability dimension factor for identifying the ability to be measured can be used as a basis for subsequent measurement and evaluation of the ability level. The ability dimension factor refers to a multidimensional standard for measuring the ability level, for example, the ability dimension factor for calculating thinking ability includes abstract thinking, simulation thinking, organizational thinking, logic thinking, model thinking and the like, and the ability dimension factor for language ability includes listening, speaking, reading, writing and the like.
Further, as an optional embodiment of the present invention, the identifying, according to the application scenario, a capability dimension factor of the capability to be measured includes: analyzing the service requirement and the service target of the capacity to be measured according to the application scene; determining a capacity measurement index of the capacity to be measured according to the service requirement, the service target and a pre-constructed index construction principle; and analyzing the constituent factors of the capacity measurement indexes, and identifying capacity dimension factors in the constituent factors.
The index construction principle refers to a principle to be followed for the purpose of making the index system scientific and standardized when constructing the index system, such as a scientific principle, a device optimization principle, a general comparability principle, a practical principle, a target guidance principle, and the like.
Further, as an optional embodiment of the present invention, the ability dimension factor identifying the constituent factors may be identified by a principal component analysis algorithm.
Furthermore, the embodiment of the invention can establish the capability factor characteristics which are more in line with the actual application scene by utilizing the pre-constructed factor fuzzy rule to fuzzify the capability dimension factor and has more practical interpretation significance. Wherein the fuzzy rule refers to the representation of the regularity of the capability factor. The fuzzy ability level refers to the ability classification grades after fuzzification treatment, such as excellent, good, medium and poor.
It should be understood that before the fuzzifying the capability dimension factor by using the pre-constructed factor fuzzy rule to obtain the fuzzy capability level, the method further includes: constructing the factor fuzzy rule, including:
constructing a factor space domain and a factor fuzzy set corresponding to the capability dimension factor,
constructing a membership function of the capability dimension factor by using the following formula:
wherein, mu (x) represents a membership function, x represents a capability dimension factor, and a, b and c represent critical constants;
constructing a fuzzy mapping relation between the factor space domain and the factor fuzzy set by utilizing a pre-constructed fuzzy logic algorithm according to the membership function, the factor space domain and the factor fuzzy set;
and determining the factor fuzzy rule according to the fuzzy mapping relation.
Wherein the fuzzy sets are sets used to express fuzzy concepts. The membership function is a function which is used for representing the trueness degree of an element belonging to a fuzzy set and is represented by A (x) when x varies in U, wherein if any element x in a domain of interest (research range) U has a number A (x) epsilon [0,1] corresponding to the element x. The fuzzy logic algorithm is an algorithm which is established on the basis of multi-valued logic and is used for researching fuzzy thinking, language forms and rules thereof by using a fuzzy set method.
Further, as an optional embodiment of the present invention, the fuzzifying, by using a pre-constructed factor fuzzy rule, the capability dimension factor to obtain a fuzzy capability level includes: identifying a membership function and a factor fuzzy set in a pre-constructed factor fuzzy rule, and fuzzifying the capability dimensionality factor according to the membership function to obtain the membership of the capability dimensionality factor; and determining a pre-constructed ability factor level in the factor fuzzy set according to the membership degree and the factor fuzzy rule, and determining the fuzzy ability level according to the ability factor level.
S2, establishing an incidence relation between the ability dimension factor and the ability to be measured, and establishing an ability analysis model according to the ability dimension factor, the fuzzy ability level and the incidence relation.
According to the embodiment of the invention, the capacity to be measured can be indirectly measured by measuring the capacity dimension factor by constructing the incidence relation between the capacity dimension factor and the capacity to be measured, and the accuracy of the capacity measurement is greatly influenced.
Further, as an optional embodiment of the present invention, the constructing the association relationship between the capability dimension factor and the capability to be measured includes: performing similar dimension division on the capacity dimension factor to obtain a division factor dimension, and performing capacity gradient division on the capacity to be measured to obtain a division capacity gradient; and constructing an incidence relation between the capacity dimension factor and the capacity to be measured according to the division factor dimension and the division capacity gradient.
Further, as an optional embodiment of the present invention, the constructing an association relationship between the capability dimension factor and the capability to be measured according to the partition factor dimension and the partition capability gradient includes: respectively extracting factor semantic information and capability semantic information of the division factor dimension and the division capability gradient, and vectorizing the factor semantic information and the capability semantic information to obtain a factor semantic vector and a capability semantic vector; calculating semantic similarity between each factor semantic vector and the ability semantic vector, calculating the maximum similarity of the semantic similarities, and identifying the mapping relation between the factor semantic vector corresponding to the maximum similarity and the ability semantic vector; and determining the association relationship between the capability dimension factor corresponding to the factor semantic vector and the capability to be measured corresponding to the capability semantic vector according to the mapping relationship.
Further, according to the capacity dimension factor, the fuzzy capacity level and the incidence relation, a basic analysis model capable of determining capacity measurement is constructed by the capacity analysis model, so that the capacity can be measured in a multi-dimensional mode subsequently.
Further, as an optional embodiment of the present invention, the constructing a capability analysis model according to the capability dimension factor, the fuzzy capability level and the association relationship includes: acquiring the capacity to be measured corresponding to the capacity dimension factor, and constructing a test item of the capacity to be measured by using a uniform distribution algorithm according to the fuzzy capacity level; and constructing a scoring standard of the test item, and constructing a capability analysis model according to the scoring standard, the test item, the capability dimension factor, the fuzzy capability level and the association relation.
Alternatively, the scoring criteria for constructing the test item may be constructed using the Likter scale 4 (1-poor; 2-poor; 3-good; 4-excellent).
And S3, acquiring a historical capability test object, and testing the historical capability test object by using a pre-constructed capability test item to obtain historical test data.
In the embodiment of the invention, the historical ability test object refers to a past object which is used as a target in a process of quantizing a non-quantized object according to a certain rule and can be obtained by a target sampling method.
Furthermore, the historical capability test object is tested by utilizing the pre-constructed capability test item to obtain historical test data which is used as a training sample for subsequently constructing a capability analysis model.
Further, as an optional embodiment of the present invention, the testing the historical performance test object by using the pre-constructed performance test item, and obtaining the historical test data may be implemented by counting test conditions of the historical performance test object on the performance test item, where the test conditions include correct test and incorrect test.
And S4, training the capability analysis model based on the historical test data to obtain the trained capability analysis model.
According to the embodiment of the invention, the trained capability analysis model can be determined by training the capability analysis model based on the historical test data, so that the capability measurement can be compared and analyzed from multiple dimensions.
Further, as an optional embodiment of the present invention, the training the capability analysis model based on the historical test data to obtain a trained capability analysis model includes:
identifying a historical capability test object and a capability test item corresponding to the historical test data, adjusting the historical test data according to the historical capability test object and the capability test item, and constructing an object item data table;
according to the object item data table, the following formula is utilized:
wherein the content of the first and second substances,
indicates the probability that the mth historical capability test subject answered the ith test item correctly, and ` H `>
Represents the capability value, based on the status of the mth historical capability test subject>
Represents the difficulty value of the ith test item, <' > based on the comparison>
The test result of the mth historical ability test object to answer the ith test item is shown, exp represents an exponential function with a natural constant as the base,
constructing a likelihood function of the object item data table, and identifying parameter variables in the likelihood function;
carrying out logarithm processing on the likelihood function to obtain a logarithm likelihood function, and carrying out derivation processing on the parameter variable by the logarithm likelihood function to obtain a likelihood equation;
solving the likelihood equation to obtain a likelihood solution of the likelihood equation, and determining a parameter variable value of the parameter variable according to the likelihood solution, wherein the parameter variable comprises object capacity and project difficulty;
respectively calculating the capacity mean value and the difficulty mean value of each object capacity and each project difficulty according to the parameter variable values, and taking the capacity mean value and the difficulty mean value as a capacity estimation value and a difficulty estimation value;
constructing a logarithm scale, and carrying out normalization processing on the capacity estimation value and the difficulty estimation value to obtain a normalization capacity estimation value and a normalization difficulty estimation value under the logarithm scale;
selecting an analysis index of the ability analysis model, calculating an index value of the analysis index according to the normalization ability estimation value and the normalization difficulty estimation value, carrying out analysis processing and adjustment processing on the ability analysis model according to the index value to obtain an ability analysis adjustment model, and determining the trained ability analysis model according to the ability analysis adjustment model.
The analysis index refers to a unit or a method for analyzing and measuring the development degree of the object, such as a weighted residual mean square, a weighted residual mean square t statistic, a standard residual mean square, a separation degree, a reliability and other analysis indexes.
Further, as an optional embodiment of the present invention, the constructing a likelihood function of the object item data table includes:
identifying correct item numbers and wrong item numbers which are tested correctly and tested wrongly in the object item data table, and constructing a correct item set and a wrong item set according to the correct item numbers and the wrong item numbers;
according to the correct item set and the wrong item set, constructing a likelihood function of the object item data table by using the following formula:
wherein the content of the first and second substances,
a likelihood function representing a table of object item data, <' >>
Indicates the ability value of the mth historical ability test subject, based on the status of the device, and the status of the device>
Represents the difficulty value of the 1 st to nth test item>
Represents the probability that the mth historical capability test subject answered the ith test item correctly, L represents the correct set of items, and ` Ks `>
A set of erroneous items is represented and, i denotes the test item number of the correct item set, based on the status of the item set>
A test item number representing a set of erroneous items.
Further, as an optional embodiment of the present invention, the analysis index of selecting the capability analysis model may be selected according to expert experience of the capability model. And calculating the index value of the analysis index according to the capability estimation value and the difficulty estimation value by utilizing Winsteps software. And optionally, for example, for an index of a weighted residual mean square in the analysis index, the index value represents the fitting degree of a test object or a test item, and when the fitting degree is not within a preset fitting threshold interval, the test object or the test item corresponding to the fitting degree is deleted or adjusted to obtain the capability analysis adjustment model. The fitting threshold interval is a critical range generated for the degree of goodness of fit, and is generally set to [0.5,1.5].
And S5, acquiring real-time test data, determining the test data distribution of the real-time test data and the test project distribution of the capability test projects by utilizing the trained capability analysis model, and obtaining a capability measurement result according to the test data distribution and the test project distribution.
The real-time test data in the embodiment of the invention refers to the current input provided for the model in the test execution process, and can be obtained through a data script, and the data script can be compiled through a JS script language.
According to the embodiment of the invention, the trained capability analysis model is utilized to determine the test data distribution of the real-time test data and calculate the test item distribution of the capability test items, so that comparative analysis can be subsequently performed among capability test objects, among capability test items and between the capability test objects and the capability test items.
Further, as an optional embodiment of the present invention, the determining, by using the trained capability analysis model, a test data distribution of the real-time test data and a test item distribution of the capability test items includes: calculating a real-time capability value and a real-time project difficulty value of the real-time test data, and carrying out normalization processing on the real-time capability value and the real-time project difficulty value to obtain a normalization capability value and a normalization difficulty value; constructing a nostalgic graph of the real-time test data and the ability test items according to the normalization ability values and the normalization difficulty values; and determining the test data distribution and the test item distribution according to the Huai diagram.
The Huai diagram is a diagram formed by marking the distribution positions of the characteristic values of the subject item and the tested characteristic values by using a scale with the same scale, and can be uniformly compared from two dimensions of the subject item and the tested characteristic values.
Furthermore, the embodiment of the invention can obtain the final capability measurement result according to the test data distribution and the test item distribution, and realize multi-dimensional comparison, thereby providing a guidance direction for the adjustment strategy of the actual situation.
Further, as an optional embodiment of the present invention, the obtaining a capability measurement result according to the test data distribution and the test item distribution includes: acquiring a capability test object corresponding to the test data distribution, calculating a capability value range of the capability test object, and calculating a capability value span according to the capability value range; acquiring capability test items corresponding to the distribution of the test items, calculating the difficulty value range of the capability test items, and calculating the difficulty value span according to the difficulty value range; calculating the matching degree of the capability test object and the capability test item according to the capability value span and the difficulty value span; calculating the tested capacity mean value and the project difficulty mean value of the test data distribution and the test project distribution, and comparing the tested capacity mean value and the project difficulty mean value to obtain a comparison result; and analyzing the matching degree and the comparison result to obtain a capability measurement result.
Further, as an optional embodiment of the present invention, the calculating, according to the capability value span and the difficulty value span, a matching degree of the capability test object and the capability test item includes:
calculating the matching degree of the capability test object and the capability test item by using the following formula:
wherein the content of the first and second substances,
represents a degree of match of a capacity test subject with the capacity test item, <' > based on the status of the subject>
Represents a span of capability values, based on the status of the device>
Representing the span of difficulty values.
Further, as an optional embodiment of the present invention, the calculating a tested capability mean and a project difficulty mean of the test data distribution and the test project distribution includes:
calculating a mean value of the tested capacity and a mean value of the project difficulty of the test data distribution and the test project distribution by using the following formulas:
wherein, the first and the second end of the pipe are connected with each other,
represents the mean value of the tested ability>
Indicates the fifth->
Individual capacity test data, based on the status of the individual>
A serial number representing capability test data, and->
Represents the amount of capability test data, and>
represents the item difficulty mean, <' > >>
Indicates the fifth->
A number of test item difficulty values, <' > based upon>
Indicates a sequence number for the test item>
Indicating the number of test items.
The embodiment of the invention can determine the service background of the capacity to be measured by acquiring the application scene of the capacity to be measured, identify the capacity dimension factor of the capacity to be measured as the basis for the subsequent capacity measurement and evaluation, and utilize the pre-constructed factor fuzzy rule to fuzzify the capacity dimension factor to establish the capacity factor characteristic which is more in line with the actual application scene and has more practical interpretation significance; secondly, the embodiment of the invention can indirectly measure the capacity to be measured by measuring the capacity dimension factor by constructing the incidence relation between the capacity dimension factor and the capacity to be measured, which has great influence on the accuracy of the capacity measurement, and according to the capacity dimension factor, the fuzzy capacity level and the incidence relation, a basic analysis model which can determine the capacity measurement is constructed by a capacity analysis model, so as to obtain a source basis of historical data which can be provided by a historical capacity test object for realizing the multi-dimensional measurement of the capacity subsequently, and the historical capacity test object is tested by utilizing a pre-constructed capacity test item to obtain historical test data which is used as a training sample for constructing the capacity analysis model subsequently; furthermore, in the embodiment of the present invention, based on the historical test data, the trained capability analysis model may be determined by training the capability analysis model to implement comparative analysis on capability measurement from multiple dimensions, obtain real-time test data to provide raw data for real-time capability measurement, and by using the trained capability analysis model, the test data distribution of the real-time test data and the test item distribution of the capability test items may be determined and calculated to implement comparative analysis between capability test objects, between capability test items, and between a capability test object and a capability test item in the following, and a final more accurate capability measurement result may be obtained according to the test data distribution and the test item distribution, and a multidimensional comparison may be implemented, thereby providing a guidance direction for a real-situation adjustment strategy. Therefore, the capacity measurement method and device based on big data analysis provided by the embodiment of the invention can improve the accuracy of capacity measurement.
Fig. 2 is a functional block diagram of the capacity measuring device based on big data analysis according to the present invention.
The big data analysis-based capability measuring apparatus 100 of the present invention may be installed in an electronic device. According to the implemented functions, the capability measuring device based on big data analysis may include a capability factor identification module 101, a capability analysis model construction module 102, a historical data acquisition module 103, a capability model training module 104, and a capability measurement result generation module 105. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and can perform a fixed function, and is stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the capacity factor identification module 101 is configured to acquire an application scenario of a capacity to be measured, identify a capacity dimension factor of the capacity to be measured according to the application scenario, and perform fuzzification processing on the capacity dimension factor by using a fuzzy rule of a pre-constructed capacity factor to obtain a fuzzy capacity level;
the capability analysis model building module 102 is configured to build an association relationship between the capability dimension factor and the capability to be measured, and build a capability analysis model according to the capability dimension factor, the fuzzy capability level and the association relationship;
the historical data acquisition module 103 is configured to acquire a historical capability test object, and test the historical capability test object by using a pre-constructed capability test item to obtain historical test data;
the capability model training module 104 is configured to train the capability analysis model based on the historical test data to obtain a trained capability analysis model;
the capability measurement result generation module 105 is configured to obtain real-time test data, determine test data distribution of the real-time test data and test item distribution of the capability test items by using the trained capability analysis model, and obtain a capability measurement result according to the test data distribution and the test item distribution.
In detail, when the modules in the capability measuring apparatus 100 based on big data analysis in the embodiment of the present invention are used, the same technical means as the capability measuring method based on big data analysis described in fig. 1 above is adopted, and the same technical effects can be produced, which is not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the invention can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application device that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the apparatus claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not to denote any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A method for capacity measurement based on big data analysis, the method comprising:
acquiring an application scene of capacity to be measured, identifying a capacity dimension factor of the capacity to be measured according to the application scene, and fuzzifying the capacity dimension factor by using a fuzzy rule of a pre-constructed capacity factor to obtain a fuzzy capacity level;
constructing an incidence relation between the ability dimension factor and the ability to be measured, and constructing an ability analysis model according to the ability dimension factor, the fuzzy ability level and the incidence relation;
acquiring a historical capability test object, and testing the historical capability test object by using a pre-constructed capability test item to obtain historical test data;
training the capability analysis model based on the historical test data to obtain a trained capability analysis model;
obtaining real-time test data, determining test data distribution of the real-time test data and test item distribution of the capability test items by using the trained capability analysis model, and obtaining a capability measurement result according to the test data distribution and the test item distribution.
2. The method of claim 1, wherein before the step of blurring the capability dimension factor by using the pre-constructed factor blurring rule to obtain the blurred capability level, the method further comprises: constructing the factor fuzzy rule, including:
constructing a factor space domain and a factor fuzzy set corresponding to the capability dimension factor,
constructing a membership function of the capability dimension factor by using the following formula:
wherein, mu (x) represents a membership function, x represents a capability dimension factor, and a, b and c represent critical constants;
constructing a fuzzy mapping relation between the factor space domain and the factor fuzzy set by utilizing a pre-constructed fuzzy logic algorithm according to the membership function, the factor space domain and the factor fuzzy set;
and determining the factor fuzzy rule according to the fuzzy mapping relation.
3. The method for measuring capacity of claim 1, wherein the fuzzifying the capacity dimension factor by using the pre-constructed factor fuzzy rule to obtain the fuzzy capacity level comprises:
identifying a membership function and a factor fuzzy set in a pre-constructed factor fuzzy rule, and fuzzifying the capability dimensionality factor according to the membership function to obtain the membership of the capability dimensionality factor;
and determining a pre-constructed ability factor level in the factor fuzzy set according to the membership degree and the factor fuzzy rule, and determining the fuzzy ability level according to the ability factor level.
4. The method for measuring the capacity according to claim 1, wherein the constructing the association relationship between the capacity dimension factor and the capacity to be measured comprises:
performing similar dimension division on the capacity dimension factor to obtain a division factor dimension, and performing capacity gradient division on the capacity to be measured to obtain a division capacity gradient;
and constructing an incidence relation between the capacity dimension factor and the capacity to be measured according to the division factor dimension and the division capacity gradient.
5. The capacity measurement method according to claim 4, wherein the constructing the association between the capacity dimension factor and the capacity to be measured according to the partition factor dimension and the partition capacity gradient comprises:
respectively extracting factor semantic information and capacity semantic information of the division factor dimension and the division capacity gradient, and performing vectorization processing on the factor semantic information and the capacity semantic information to obtain a factor semantic vector and a capacity semantic vector;
calculating semantic similarity between each factor semantic vector and the ability semantic vector, calculating the maximum similarity of the semantic similarities, and identifying the mapping relation between the factor semantic vector corresponding to the maximum similarity and the ability semantic vector;
and determining the association relationship between the capability dimension factor corresponding to the factor semantic vector and the capability to be measured corresponding to the capability semantic vector according to the mapping relationship.
6. The method of claim 1, wherein training the capability analysis model based on the historical test data to obtain a trained capability analysis model comprises:
identifying a historical capability test object and a capability test item corresponding to the historical test data, adjusting the historical test data according to the historical capability test object and the capability test item, and constructing an object item data table;
according to the object item data table, the following formula is utilized:
wherein the content of the first and second substances,
indicates the probability that the mth historical ability test subject answered correctly for the ith test item, and->
Indicates the ability value of the mth historical ability test subject, based on the status of the device, and the status of the device>
Represents the difficulty value of the ith test item,
the test result of the mth historical ability test object to answer the ith test item is shown, exp represents an exponential function with a natural constant as the base,
constructing a likelihood function of the object item data table, and identifying parameter variables in the likelihood function;
carrying out logarithm processing on the likelihood function to obtain a logarithm likelihood function, and carrying out derivation processing on the parameter variable by the logarithm likelihood function to obtain a likelihood equation;
solving the likelihood equation to obtain a likelihood solution of the likelihood equation, and determining a parameter variable value of the parameter variable according to the likelihood solution, wherein the parameter variable comprises object capacity and project difficulty;
respectively calculating the capacity mean value and the difficulty mean value of each object capacity and each project difficulty according to the parameter variable values, and taking the capacity mean value and the difficulty mean value as a capacity estimation value and a difficulty estimation value;
constructing a logarithm scale, and carrying out normalization processing on the capacity estimated value and the difficulty estimated value to obtain a normalization capacity estimated value and a normalization difficulty estimated value under the logarithm scale;
selecting an analysis index of the ability analysis model, calculating an index value of the analysis index according to the normalization ability estimation value and the normalization difficulty estimation value, carrying out analysis processing and adjustment processing on the ability analysis model according to the index value to obtain an ability analysis adjustment model, and determining the trained ability analysis model according to the ability analysis adjustment model.
7. The capability measurement method of claim 6, wherein said constructing a likelihood function of said object item data table comprises:
identifying correct item numbers and wrong item numbers which are tested correctly and tested wrongly in the object item data table, and constructing a correct item set and a wrong item set according to the correct item numbers and the wrong item numbers;
according to the correct item set and the wrong item set, constructing a likelihood function of the object item data table by using the following formula:
wherein, the first and the second end of the pipe are connected with each other,
a likelihood function representing a table of object item data, <' >>
Indicates the fifth->
Personal historical ability testThe value of the ability of the subject to be tested, device for selecting or keeping>
Denotes the 1 st to the ^ th>
Difficulty values for a test item>
Represents a fifth or fifth party>
Individual History ability test subject answers fifth ÷ th>
Probability of a test item, based on the number of test items in the test area>
Represents the correct set of items>
Represents a set of erroneous items>
Test item numbers representing the correct set of items>
A test item number representing a set of erroneous items.
8. The method of claim 1, wherein determining the distribution of test data for the real-time test data and the distribution of test items for the capability test items using the trained capability analysis model comprises:
calculating a real-time capability value and a real-time project difficulty value of the real-time test data, and carrying out normalization processing on the real-time capability value and the real-time project difficulty value to obtain a normalization capability value and a normalization difficulty value;
constructing a nostalgic graph of the real-time test data and the ability test items according to the normalization ability values and the normalization difficulty values;
and determining the test data distribution and the test item distribution according to the Huai diagram.
9. The method of claim 1, wherein obtaining the capability measurement based on the test data distribution and the test item distribution comprises:
acquiring a capability test object corresponding to the test data distribution, calculating a capability value range of the capability test object, and calculating a capability value span according to the capability value range;
acquiring capability test items corresponding to the distribution of the test items, calculating the difficulty value range of the capability test items, and calculating the difficulty value span according to the difficulty value range;
calculating the matching degree of the capability test object and the capability test item according to the capability value span and the difficulty value span;
calculating the tested capacity mean value and the project difficulty mean value of the test data distribution and the test project distribution, and comparing the tested capacity mean value and the project difficulty mean value to obtain a comparison result;
and analyzing the matching degree and the comparison result to obtain a capability measurement result.
10. A capability measurement device, the device comprising:
the capacity factor identification module is used for acquiring an application scene of capacity to be measured, identifying a capacity dimension factor of the capacity to be measured according to the application scene, and fuzzifying the capacity dimension factor by using a fuzzy rule of a pre-constructed capacity factor to obtain a fuzzy capacity level;
the capacity analysis model building module is used for building an incidence relation between the capacity dimension factor and the capacity to be measured and building a capacity analysis model according to the capacity dimension factor, the fuzzy capacity level and the incidence relation;
the historical data acquisition module is used for acquiring a historical capability test object, and testing the historical capability test object by using a pre-constructed capability test item to obtain historical test data;
the capability model training module is used for training the capability analysis model based on the historical test data to obtain a trained capability analysis model;
and the capability measurement result generation module is used for acquiring real-time test data, determining the test data distribution of the real-time test data and the test item distribution of the capability test item by using the trained capability analysis model, and obtaining a capability measurement result according to the test data distribution and the test item distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310011014.2A CN115935191A (en) | 2023-01-05 | 2023-01-05 | Big data analysis-based capacity measurement method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310011014.2A CN115935191A (en) | 2023-01-05 | 2023-01-05 | Big data analysis-based capacity measurement method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115935191A true CN115935191A (en) | 2023-04-07 |
Family
ID=86697909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310011014.2A Pending CN115935191A (en) | 2023-01-05 | 2023-01-05 | Big data analysis-based capacity measurement method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115935191A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190079469A1 (en) * | 2017-09-11 | 2019-03-14 | International Business Machines Corporation | Adaptive control of negative learning for limited reconstruction capability auto encoder |
| CN110245826A (en) * | 2019-05-07 | 2019-09-17 | 平安科技（深圳）有限公司 | A kind of data analysing method and device |
| CN111626420A (en) * | 2020-03-31 | 2020-09-04 | 杨阳 | Self-adaptive evaluation method and system for cognitive ability and use method of system |
| CN112446591A (en) * | 2020-11-06 | 2021-03-05 | 太原科技大学 | Evaluation system for student comprehensive capacity evaluation and zero sample evaluation method |
| CN115458112A (en) * | 2022-08-31 | 2022-12-09 | 北京津发科技股份有限公司 | Cognitive ability evaluation method and system |
-
2023
- 2023-01-05 CN CN202310011014.2A patent/CN115935191A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190079469A1 (en) * | 2017-09-11 | 2019-03-14 | International Business Machines Corporation | Adaptive control of negative learning for limited reconstruction capability auto encoder |
| CN110245826A (en) * | 2019-05-07 | 2019-09-17 | 平安科技（深圳）有限公司 | A kind of data analysing method and device |
| CN111626420A (en) * | 2020-03-31 | 2020-09-04 | 杨阳 | Self-adaptive evaluation method and system for cognitive ability and use method of system |
| CN112446591A (en) * | 2020-11-06 | 2021-03-05 | 太原科技大学 | Evaluation system for student comprehensive capacity evaluation and zero sample evaluation method |
| CN115458112A (en) * | 2022-08-31 | 2022-12-09 | 北京津发科技股份有限公司 | Cognitive ability evaluation method and system |
Non-Patent Citations (1)
| Title |
|---|
| 刘宇;: "ILSS中的认知能力测试与模糊评价", 教育信息化 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178456B (en) | Abnormal index detection method and device, computer equipment and storage medium | |
| CN116148656B (en) | Portable analog breaker fault detection method | |
| CN109685321A (en) | Event risk method for early warning, electronic equipment and medium based on data mining | |
| CN116308963A (en) | Government affair data analysis method and system | |
| CN111767192A (en) | Service data detection method, device, equipment and medium based on artificial intelligence | |
| CN111177500A (en) | Data object classification method and device, computer equipment and storage medium | |
| CN110544047A (en) | Bad data identification method | |
| CN112464281B (en) | Network information analysis method based on privacy grouping and emotion recognition | |
| CN114298299A (en) | Model training method, device, equipment and storage medium based on course learning | |
| CN113889274B (en) | Method and device for constructing risk prediction model of autism spectrum disorder | |
| CN110096708A (en) | A kind of determining method and device of calibration collection | |
| CN115935191A (en) | Big data analysis-based capacity measurement method and device | |
| CN115392375A (en) | Intelligent evaluation method and system for multi-source data fusion degree | |
| CN114818945A (en) | Small sample image classification method and device integrating category adaptive metric learning | |
| CN113888600A (en) | Trajectory determination method and apparatus, electronic device and computer-readable storage medium | |
| CN113516229A (en) | Credible user optimization selection method facing crowd sensing system | |
| WO2022139402A1 (en) | Diagnostic classification device and method | |
| CN117354053B (en) | Network security protection method based on big data | |
| CN117809140B (en) | Image preprocessing system and method based on image recognition | |
| CN113191433B (en) | Data classification method, device and equipment | |
| CN115831339B (en) | Medical system risk management and control pre-prediction method and system based on deep learning | |
| Liu et al. | Structure simplification of neural network for smile classification. | |
| CN111881287B (en) | Classification ambiguity analysis method and device | |
| CN118015430A (en) | Intelligent government affair service training method and system based on deep learning | |
| Brandenstein et al. | To follow or not to follow-Estimating public opinion from Twitter data using network analysis and machine learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230407 |