CN115859911A - Label automatic generation evolution method and device adaptive to dynamic data change - Google Patents
Label automatic generation evolution method and device adaptive to dynamic data change Download PDFInfo
- Publication number
- CN115859911A CN115859911A CN202310038824.7A CN202310038824A CN115859911A CN 115859911 A CN115859911 A CN 115859911A CN 202310038824 A CN202310038824 A CN 202310038824A CN 115859911 A CN115859911 A CN 115859911A
- Authority
- CN
- China
- Prior art keywords
- data
- matrix
- label
- dynamic
- static
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000008859 change Effects 0.000 title claims abstract description 29
- 230000003044 adaptive effect Effects 0.000 title claims description 12
- 230000003068 static effect Effects 0.000 claims abstract description 121
- 239000013598 vector Substances 0.000 claims abstract description 50
- 238000003066 decision tree Methods 0.000 claims abstract description 38
- 230000004927 fusion Effects 0.000 claims abstract description 31
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000005516 engineering process Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 130
- 230000006870 function Effects 0.000 claims description 45
- 229940050561 matrix product Drugs 0.000 claims description 20
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 230000006978 adaptation Effects 0.000 claims 1
- 230000011218 segmentation Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 239000000047 product Substances 0.000 description 11
- 230000008569 process Effects 0.000 description 7
- 230000004913 activation Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an artificial intelligence technology, and discloses an automatic label generation evolution method suitable for dynamic data change, which comprises the following steps: acquiring static data, calculating the data intensity of the static data, determining the static data with the intensity greater than the preset intensity as key data, and integrating the key data into a static label; acquiring real-time data of the dynamic webpage by using a preset webpage data grabbing tool, determining an API (application programming interface) interface between the dynamic webpage and a preset cloud server by using a classification decision tree, and returning the real-time data to the cloud server through the API interface to obtain a real-time data document; extracting ternary information in the real-time data document by using an event extraction model and integrating the ternary information into a dynamic tag; and splicing the static label and the dynamic label into a fusion label by using a vector splicing technology, and determining the fusion label as an automatic generation label. The invention also provides a label automatic generation evolution device suitable for the dynamic change of the data. The invention can automatically generate the label under the dynamic change of the data.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for automatically generating and evolving a label under the condition of adapting to dynamic data change.
Background
With the rapid development of the big data age, replacing data or documents with tags can simplify people operating on a large amount of similar data. To simplify the cumbersome process of generating labels, a method is needed that can automatically generate a representation as the data dynamically changes.
Most of existing label generation methods analyze existing data documents and generate corresponding document labels, for example, when a certain user uses a certain type of push software, the user can generate preference labels according to historical data of the user after using the certain type of push software for a period of time, and the preference data of the user cannot be analyzed in real time. In practical application, dynamic data is difficult to operate, and different data documents are complex to operate, so that the situation that labels are inaccurate to generate or cannot be generated easily occurs.
Disclosure of Invention
The invention provides a method and a device for automatically generating and evolving a label under the condition of adapting to dynamic change of data, and mainly aims to solve the problem of how to generate the label under the condition of dynamic change of the data.
In order to achieve the above object, the present invention provides a method for automatically generating and evolving a tag adaptive to dynamic change of data, comprising:
acquiring preset static data, calculating the data intensity of the static data, determining the static data with the intensity greater than the preset intensity as key data, and integrating the key data into a static label;
acquiring a preset dynamic webpage, acquiring real-time data of the dynamic webpage by using a preset webpage data grabbing tool, determining an API (application programming interface) interface between the dynamic webpage and a preset cloud server by using a preset classification decision tree, and returning the real-time data to the cloud server through the API interface to obtain a real-time data document;
extracting ternary information in the real-time data document by using a preset event extraction model, and integrating the ternary information into a dynamic tag;
and splicing the static label and the dynamic label into a fusion label by using a vector splicing technology, and determining the fusion label as an automatic generation label.
Optionally, the calculating the data strength of the static data includes:
calculating the data intensity of the static data by using the following intensity calculation formula:
wherein, the
Is the first->
Each static data->
Is greater than or equal to>
For the total number of all static data>
Is the first->
Data frequency count of static data, and->
Is the first->
Total number of occurrences of the static data.
Optionally, the integrating the key data into a static tag includes:
carrying out vector coding on the key data one by one to obtain key vectors;
acquiring the maximum length in the key vector as a standard length;
extending the key vectors to a standard length by using preset vector parameters to obtain standard vectors;
and merging the column dimensions of the standard vectors to obtain a merged result, and determining the merged result as a static label.
Optionally, the determining, by using a preset classification decision tree, an API interface between the dynamic webpage and a preset cloud server includes:
acquiring a webpage interface of the dynamic webpage;
determining the API of the webpage interface and a preset cloud server by using the following classification decision tree functions:
wherein ,
for the output value of the classification decision tree function, < > H>
For the parameters of the classification decision tree function,
is an input value of the classification decision tree function;
taking the webpage interface as a classification decision tree function input value, and calculating and outputting an API (application programming interface) interface of the cloud server corresponding to the webpage interface through the classification decision tree function;
when the input value is less than the parameters of the classification decision tree function, the output label is
I.e. the API interface of the cloud server corresponding to the web interface->
；
When the input value is greater than the classification decision tree functionWhen the parameters are in the range of (1), the output label is
I.e. the API interface of the cloud server corresponding to the web interface->
；
When the input value is equal to the parameter of the classification decision tree function, the output label is
I.e. the API interface of the cloud server corresponding to the web interface->
。
Optionally, the returning the real-time data to the cloud server through the API interface includes:
creating a real-time database exclusive to the real-time data in the cloud server;
butting a webpage interface of the dynamic webpage with the API interface to form a data transmission channel;
and uploading the real-time data to a real-time database, namely a cloud server, by using the data transmission channel.
Optionally, the extracting, by using a preset event extraction model, ternary information in the real-time data document includes:
paragraph clauses are carried out on the real-time data document to obtain document clauses;
mapping the document clauses into dimensions which accord with the ternary labels one by utilizing a preset mapping function in an event extraction model;
and outputting the ternary label corresponding to the document clause on a model output layer, and determining that the ternary label is ternary information.
Optionally, the stitching the static label and the dynamic label into a fusion label by using a vector stitching technique includes:
converting the static label into a static matrix;
converting the dynamic label into a dynamic matrix;
and calculating a product matrix of the static matrix and the dynamic matrix, and determining the product matrix as a fusion tag.
Optionally, the calculating a product matrix of the static matrix and the dynamic matrix includes:
respectively acquiring the matrix row number and the matrix column number of the static matrix and the dynamic matrix;
taking the maximum value in the matrix row number and the matrix column number as the standard row number and the standard column number;
expanding the number of matrix rows and the number of matrix columns of the static matrix to the number of standard rows and standard columns by using preset matrix parameters to obtain a standard static matrix;
expanding the matrix row number and the matrix column number of the dynamic matrix to a standard row number and a standard column number by using preset matrix parameters to obtain a standard dynamic matrix;
and calculating the matrix product of the standard static matrix and the standard dynamic matrix by using a preset matrix product formula.
Optionally, the calculating a matrix product of the standard static matrix and the standard dynamic matrix by using a preset matrix product formula includes:
calculating the matrix product of the standard static matrix and the standard dynamic matrix by using the following matrix product formula:
wherein ,
is a product matrix, is based on>
For the purpose of the standard static matrix, the matrix is,
for said standard dynamic matrix>
For a matrix parameter in the product matrix, < > H>
For a matrix parameter in the standard static matrix, <' > H>
Are matrix parameters within the standard dynamic matrix.
In order to solve the above problem, the present invention further provides an apparatus for automatically generating and evolving a tag adapted to a dynamic change of data, where the apparatus includes:
a static data acquisition module: acquiring preset static data, calculating the data intensity of the static data, determining the static data with intensity greater than the preset intensity as key data, and integrating the key data into a static label;
a dynamic data acquisition module: acquiring a preset dynamic webpage, acquiring real-time data of the dynamic webpage by using a preset webpage data grabbing tool, determining an API (application program interface) interface between the dynamic webpage and a preset cloud server by using a preset classification decision tree, and returning the real-time data to the cloud server through the API interface to obtain a real-time data document;
and a dynamic label generation module: extracting ternary information in the real-time data document by using a preset event extraction model, and integrating the ternary information into a dynamic tag;
and a label fusion module is carried out: and splicing the static label and the dynamic label into a fusion label by using a vector splicing technology, and determining the fusion label as an automatic generation label.
According to the embodiment of the invention, the static label corresponding to the static webpage is obtained to be used as supplement and is fused with the dynamic data, so that accurate label information is generated; acquiring real-time data of the dynamic webpage by using a preset webpage data grabbing tool, extracting ternary information in a real-time data document by using a preset event extraction model, and integrating the ternary information into a dynamic label; the static label and the dynamic label are spliced into a fusion label by using a vector splicing technology, the fusion label is determined as an automatic generation label, the label characteristics of the static label and the dynamic label can be reserved by a maximum program, the obtained automatic generation label is more accurate, the operation is simple, and the method is easy to realize; the matrix fusion process is visually expressed through the formula through the matrix product formula, so that the calculation is convenient to understand, the formula using process is simple, the method is simple and is not easy to generate errors, and the fusion label can be accurately obtained. Therefore, the label automatic generation evolution method and device adaptive to the dynamic data change can solve the problem of low accuracy of the short-circuit impedance tester.
Drawings
Fig. 1 is a schematic flowchart of a method for automatically generating and evolving a tag adaptive to dynamic change of data according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of generating a static tag according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a process for extracting ternary information according to an embodiment of the present invention;
fig. 4 is a functional block diagram of an apparatus for automatically generating and evolving tags adapted to dynamic changes of data according to an embodiment of the present invention;
the implementation, functional features and advantages of the present invention will be further described 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 application provides an automatic label generation evolution method adaptive to dynamic data change. The execution subject of the label automatic generation evolution method under the dynamic change of the adaptive data includes but is not limited to at least one of electronic devices, such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the method for automatically generating and evolving the tag under the condition of adapting to the dynamic change of the data may be performed by software or hardware installed in the terminal device or the 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 method for automatically generating and evolving a tag adaptive to dynamic data changes according to an embodiment of the present invention. In this embodiment, the method for automatically generating and evolving a tag adaptive to dynamic change of data includes:
s1, acquiring preset static data, calculating the data intensity of the static data, determining the static data with intensity greater than the preset intensity as key data, and integrating the key data into a static label;
because web page data usually includes static data and dynamic data, and information provided by only depending on the dynamic data is limited and incomplete, the static data needs to be acquired as a supplement to be fused with the dynamic data, so as to generate accurate tag information.
In the embodiment of the invention, the static data comprises information which is stored in a hard disk of the computer and does not change along with the operation of a program. Such as the name of an entity, employee information, system parameters, etc.
In this embodiment of the present invention, the calculating the data strength of the static data includes:
calculating the data intensity of the static data by using the following intensity calculation formula:
wherein, the
Is the first->
Each static data->
Is greater than or equal to>
For the total number of all static data, <' >>
Is the first->
Data frequency count of static data, and->
Is the first->
Total number of occurrences of each static datum.
The data intensity calculated by the intensity calculation formula in detail is accurate and efficient, the data intensity of all static data can be rapidly acquired in a short time, the calculation efficiency is high, and the data intensity can be visually represented by numbers to facilitate subsequent comparison.
In the embodiment of the present invention, referring to fig. 2, the integrating the key data into a static tag includes:
s21, carrying out vector coding on the key data one by one to obtain key vectors;
s22, acquiring the maximum length in the key vector as a standard length;
s23, extending the key vectors to a standard length by using preset vector parameters to obtain standard vectors;
and S24, carrying out column dimension combination on the standard vectors to obtain a combination result, and determining the combination result as a static label.
In detail, since the vectors with different lengths cannot be column dimension merged, all the key vectors to be merged need to be unified in vector length first, so that subsequent merging operation can be facilitated, errors are not prone to occurring, and the format is more standard and complete.
Further, the key vectors are all extended to a standard length by using preset vector parameters, such as: the key vector A: [11, 36, 22], key vector B: [14, 25, 31, 27], where the criterion length is 5, the key vector a may be vector extended by using a preset vector parameter (e.g. 0) until the vector length of the key vector a and the vector length of the key vector B are both 5, so as to obtain an extended key vector a: [11, 36, 22, 0] and an extended key vector B [14, 25, 31, 27,0].
In detail, the static data with higher data intensity in all the static data are integrated into a static label, so that the data characteristics of the static data can be kept as much as possible, the formed static label is more accurate, and the accuracy, the rigor and the high efficiency of the steps are ensured.
S2, acquiring a preset dynamic webpage, acquiring real-time data of the dynamic webpage by using a preset webpage data grabbing tool, determining an API (application programming interface) interface between the dynamic webpage and a preset cloud server by using a preset classification decision tree, and returning the real-time data to the cloud server through the API interface to obtain a real-time data document;
in the embodiment of the invention, the webpage data grabbing tool is simple to operate, has good universality, can automatically grab data information on a page, has a strong acquisition function, and can randomly convert a data format. In the embodiment of the present invention, the Web page data crawling tool includes, but is not limited to, import.
In an embodiment of the present invention, the determining, by using a preset classification decision tree, an API interface between the dynamic webpage and a preset cloud server includes:
acquiring a webpage interface of the dynamic webpage;
determining the API of the webpage interface and a preset cloud server by using the following classification decision tree functions:
wherein ,
for the output value of the classification decision tree function, < > H>
For the parameters of the classification decision tree function,
is an input value of the classification decision tree function;
taking the webpage interface as a classification decision tree function input value, and calculating and outputting an API (application programming interface) interface of the cloud server corresponding to the webpage interface through the classification decision tree function;
when the input value is less than the parameters of the classification decision tree function, the output label is
I.e. the API interface of the cloud server corresponding to the web interface->
；
When the input value is greater than the parameters of the classification decision tree function, the output label is
I.e. the API interface of the cloud server corresponding to the web interface->
；
When the input value is equal to the parameter of the classification decision tree function, the output label is
I.e. the API interface of the cloud server corresponding to the web interface->
。
In detail, the classification decision tree function can be used for accurately identifying the API of the server corresponding to the webpage interface of the dynamic webpage, efficient determination and accurate transmission can be achieved, classification efficiency is high, accuracy is high, cost can be saved, and low-cost and high-efficiency data transmission is achieved.
In an embodiment of the present invention, returning the real-time data to the cloud server through the API interface includes:
creating a real-time database exclusive to the real-time data in the cloud server;
butting a webpage interface of the dynamic webpage with the API interface to form a data transmission channel;
and uploading the real-time data to a real-time database, namely a cloud server, by using the data transmission channel.
In detail, since the cloud service includes a large amount of data of different types, once the real-time data is uploaded, the real-time data is merged with the mass data and is difficult to call and identify, and therefore a database needs to be created in the cloud server independently so as to store the real-time data, and data confusion is avoided.
S3, extracting ternary information in the real-time data document by using a preset event extraction model, and integrating the ternary information into a dynamic label;
in the embodiment of the invention, the ternary information consists of three pieces of information, namely an event name, an occurrence time and an event type, for example, an example sentence is that a small red goes shopping on the weekend, and the ternary information extracted according to the requirement is { "shopping", "weekend" and "entertainment" }.
In the embodiment of the present invention, referring to fig. 3, the extracting, by using a preset event extraction model, ternary information in the real-time data document includes:
s31, paragraph clauses are carried out on the real-time data document to obtain document clauses;
s32, mapping the document clauses into dimensions which accord with ternary labels one by utilizing a preset mapping function in an event extraction model;
and S33, outputting the ternary label corresponding to the document clause on a model output layer, and determining that the ternary label is ternary information.
In detail, the document clauses are mapped one by one into dimensions conforming to the ternary labels by using a preset mapping Function in the event extraction model, and the mapping Function includes a gaussian Function, a gaussian Function and the like in an MATLAB library.
For example, if the document clause is a point in a two-dimensional plane and the ternary label is a point in a three-dimensional plane, a mapping function may be used to calculate two-dimensional coordinates of the point in the two-dimensional plane to convert the two-dimensional coordinates into three-dimensional coordinates, and the calculated three-dimensional coordinates are used to map the point to a pre-constructed three-dimensional space, so as to map the document clause into dimensions conforming to the ternary label.
In the embodiment of the present invention, the output value of the model output layer may be calculated by using a preset activation function, and the output value greater than a preset threshold is determined as the ternary label, where the activation function includes, but is not limited to, a sigmoid activation function, a tanh activation function, and a relu activation function.
In the embodiment of the present invention, the step of integrating the ternary information into the dynamic tag is similar to the step of integrating the key data into the static tag, and details are not repeated here.
And S4, splicing the static label and the dynamic label into a fusion label by using a vector splicing technology, and determining the fusion label as an automatic generation label.
The fusion label can reserve the label characteristics of the static label and the dynamic label in a maximum program, so that the obtained automatic generation label is more accurate, the operation is simple, and the method is easy to realize. Therefore, the static label and the dynamic label are fused to realize the optimal realization method of the automatic label generation under the dynamic change of the data.
In the embodiment of the present invention, the splicing the static tag and the dynamic tag into the fusion tag by using the vector splicing technology includes:
converting the static label into a static matrix;
converting the dynamic label into a dynamic matrix;
and calculating a product matrix of the static matrix and the dynamic matrix, and determining the product matrix as a fusion tag.
In an embodiment of the present invention, the calculating a product matrix of the static matrix and the dynamic matrix includes:
respectively acquiring the matrix row number and the matrix column number of the static matrix and the dynamic matrix;
taking the maximum value in the matrix row number and the matrix column number as the standard row number and the standard column number;
expanding the number of matrix rows and the number of matrix columns of the static matrix to the number of standard rows and standard columns by using preset matrix parameters to obtain a standard static matrix;
expanding the matrix row number and the matrix column number of the dynamic matrix to a standard row number and a standard column number by using preset matrix parameters to obtain a standard dynamic matrix;
and calculating the matrix product of the standard static matrix and the standard dynamic matrix by using a preset matrix product formula.
Specifically, the process of extending the number of rows and columns of the static matrix to the number of rows and columns of the standard matrix by using the preset matrix parameters and the process of extending the key vectors to the standard length by using the preset vector parameters are similar, and details are not repeated herein.
Further, since the fusion calculation cannot be performed due to different matrix sizes, the sizes of the static matrix and the dynamic matrix need to be uniformly planned, which facilitates the subsequent fusion calculation.
In detail, the calculating the matrix product of the standard static matrix and the standard dynamic matrix by using a preset matrix product formula includes:
calculating a matrix product of the standard static matrix and the standard dynamic matrix by using the following matrix product formula:
wherein ,
is a product matrix, is based on>
For the purpose of the standard static matrix, the matrix is,
for the standard dynamic matrix, ->
For a matrix parameter in the product matrix, < > H>
For a matrix parameter in the standard static matrix, <' > H>
Are matrix parameters within the standard dynamic matrix.
Specifically, the matrix fusion process is visually expressed through a formula through a matrix product formula, so that the calculation is convenient to understand, the formula using process is simple, the method is simple and is not easy to cause errors, and the fusion tag can be accurately obtained.
Fig. 4 is a functional block diagram of an apparatus for automatically generating and evolving tags according to an embodiment of the present invention, and the apparatus is adapted to dynamically change data.
The automatic label generation evolution device 100 adapting to the dynamic change of data can be installed in electronic equipment. According to the implemented functions, the automatic tag generation and evolution apparatus 100 adapted to the dynamic change of data may include a module 101 for obtaining static data, a module 102 for obtaining dynamic data, a module for generating dynamic tags, and a module 104 for performing tag fusion. 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 that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the obtain static data module 101: acquiring preset static data, calculating the data intensity of the static data, determining the static data with the intensity greater than the preset intensity as key data, and integrating the key data into a static label;
the obtain dynamic data module 102: acquiring a preset dynamic webpage, acquiring real-time data of the dynamic webpage by using a preset webpage data grabbing tool, determining an API (application program interface) interface between the dynamic webpage and a preset cloud server by using a preset classification decision tree, and returning the real-time data to the cloud server through the API interface to obtain a real-time data document;
the generate dynamic label module 103: extracting ternary information in the real-time data document by using a preset event extraction model, and integrating the ternary information into a dynamic tag;
the tag fusion module 104: and splicing the static label and the dynamic label into a fusion label by using a vector splicing technology, and determining the fusion label as an automatic generation label.
In detail, in the embodiment of the present invention, when the modules in the apparatus 100 for automatically generating and evolving a tag under dynamic change of adaptive data are used, the same technical means as the method for automatically generating and evolving a tag under dynamic change of adaptive data described in fig. 1 to fig. 3 are used, and the same technical effects can be produced, which is not described herein again.
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 block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a string of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, which is used for verifying the validity (anti-counterfeiting) of the information and generating a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, artificial Intelligence (AI) is a theory, method, technique and application system 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 system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not 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 label automatic generation evolution method adapting to dynamic data change is characterized by comprising the following steps:
acquiring preset static data, calculating the data intensity of the static data, determining the static data with the intensity greater than the preset intensity as key data, and integrating the key data into a static label;
acquiring a preset dynamic webpage, acquiring real-time data of the dynamic webpage by using a preset webpage data grabbing tool, determining an API (application programming interface) interface between the dynamic webpage and a preset cloud server by using a preset classification decision tree, and returning the real-time data to the cloud server through the API interface to obtain a real-time data document;
extracting ternary information in the real-time data document by using a preset event extraction model, and integrating the ternary information into a dynamic tag;
and splicing the static label and the dynamic label into a fusion label by using a vector splicing technology, and determining the fusion label as an automatic generation label.
2. The method for automatic label generation evolution under the dynamic data change adaptation of claim 1, wherein the calculating the data strength of the static data comprises:
calculating the data intensity of the static data by using the following intensity calculation formula:
wherein, the
Is the first->
Each static data->
Is greater than or equal to>
For the total number of all static data>
Is as follows
Data frequency count of static data, and->
Is the first->
Total number of occurrences of the static data.
3. The method for automatically generating and evolving the label under the dynamic change of the adaptive data according to claim 1, wherein the integrating the key data into the static label comprises:
carrying out vector coding on the key data one by one to obtain key vectors;
acquiring the maximum length in the key vector as a standard length;
extending the key vectors to a standard length by using preset vector parameters to obtain standard vectors;
and merging the column dimensions of the standard vectors to obtain a merged result, and determining the merged result as a static label.
4. The method for automatically generating and evolving tags according to claim 1, wherein the determining the API interface between the dynamic web page and the preset cloud server by using the preset classification decision tree includes:
acquiring a webpage interface of the dynamic webpage;
determining the API of the webpage interface and a preset cloud server by using the following classification decision tree functions:
wherein ,
decision tree function for said classificationIn the output value of (d), in combination with a signal strength of a signal>
For parameters of said classification decision tree function>
An input value of the classification decision tree function;
taking the webpage interface as a classification decision tree function input value, and calculating and outputting an API (application programming interface) interface of the cloud server corresponding to the webpage interface through the classification decision tree function;
when the input value is less than the parameters of the classification decision tree function, the output label is
I.e. the API interface of the cloud server corresponding to the web page interface &>
；
When the input value is greater than the parameters of the classification decision tree function, the output label is
I.e. the API interface of the cloud server corresponding to the web interface->
；
When the input value is equal to the parameter of the classification decision tree function, the output label is
I.e. the API interface of the cloud server corresponding to the web interface->
。
5. The method for automatically generating and evolving tag under the dynamic change of the data according to claim 1, wherein the returning the real-time data to the cloud server through the API interface includes:
creating a real-time database exclusive to the real-time data in the cloud server;
butting a webpage interface of the dynamic webpage with the API interface to form a data transmission channel;
and uploading the real-time data to a real-time database, namely a cloud server, by using the data transmission channel.
6. The method for automatically generating and evolving tags according to claim 1, wherein the extracting the ternary information in the real-time data document by using a preset event extraction model comprises:
paragraph clause segmentation is carried out on the real-time data document to obtain document clauses;
mapping the document clauses into dimensions according with the ternary labels one by utilizing a preset mapping function in an event extraction model;
and outputting the ternary label corresponding to the document clause on a model output layer, and determining that the ternary label is ternary information.
7. The method for automatically generating and evolving the label under the condition of adapting to the dynamic change of the data according to any one of claims 1 to 6, wherein the splicing the static label and the dynamic label into the fusion label by using the vector splicing technology comprises:
converting the static label into a static matrix;
converting the dynamic label into a dynamic matrix;
and calculating a product matrix of the static matrix and the dynamic matrix, and determining the product matrix as a fusion tag.
8. The method according to claim 7, wherein the calculating a product matrix of the static matrix and the dynamic matrix comprises:
respectively acquiring the matrix row number and the matrix column number of the static matrix and the dynamic matrix;
taking the maximum value in the matrix row number and the matrix column number as a standard row number and a standard column number;
expanding the number of matrix rows and the number of matrix columns of the static matrix to the number of standard rows and standard columns by using preset matrix parameters to obtain a standard static matrix;
expanding the matrix row number and the matrix column number of the dynamic matrix to a standard row number and a standard column number by using preset matrix parameters to obtain a standard dynamic matrix;
and calculating the matrix product of the standard static matrix and the standard dynamic matrix by using a preset matrix product formula.
9. The method as claimed in claim 8, wherein the calculating the matrix product of the standard static matrix and the standard dynamic matrix by using a preset matrix product formula comprises:
calculating a matrix product of the standard static matrix and the standard dynamic matrix by using the following matrix product formula:
wherein ,
is a product matrix, in conjunction with a selection of a number of predetermined criteria>
For said standard static matrix>
For the standard dynamic matrix, ->
For the matrix parameters within the product matrix,/>
for a matrix parameter in the standard static matrix, <' > H>
Are matrix parameters within the standard dynamic matrix.
10. An apparatus for automatically generating and evolving labels under dynamic change of data, the apparatus comprising:
a static data acquisition module: acquiring preset static data, calculating the data intensity of the static data, determining the static data with the intensity greater than the preset intensity as key data, and integrating the key data into a static label;
a dynamic data acquisition module: acquiring a preset dynamic webpage, acquiring real-time data of the dynamic webpage by using a preset webpage data grabbing tool, determining an API (application programming interface) interface between the dynamic webpage and a preset cloud server by using a preset classification decision tree, and returning the real-time data to the cloud server through the API interface to obtain a real-time data document;
and a dynamic label generation module: extracting ternary information in the real-time data document by using a preset event extraction model, and integrating the ternary information into a dynamic label;
and a label fusion module is carried out: and splicing the static label and the dynamic label into a fusion label by using a vector splicing technology, and determining the fusion label as an automatic generation label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310038824.7A CN115859911B (en) | 2023-01-13 | 2023-01-13 | Automatic label generation evolution method and device adapting to dynamic change of data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310038824.7A CN115859911B (en) | 2023-01-13 | 2023-01-13 | Automatic label generation evolution method and device adapting to dynamic change of data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115859911A true CN115859911A (en) | 2023-03-28 |
| CN115859911B CN115859911B (en) | 2023-05-16 |
Family
ID=85657286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310038824.7A Active CN115859911B (en) | 2023-01-13 | 2023-01-13 | Automatic label generation evolution method and device adapting to dynamic change of data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115859911B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110020149A (en) * | 2017-11-30 | 2019-07-16 | Tcl集团股份有限公司 | Labeling processing method, device, terminal device and the medium of user information |
| CN114707474A (en) * | 2022-04-25 | 2022-07-05 | 平安普惠企业管理有限公司 | Report generation method and device, electronic equipment and computer readable storage medium |
| CN115048599A (en) * | 2022-06-20 | 2022-09-13 | 未鲲(上海)科技服务有限公司 | Enterprise product interface configuration method, device, equipment and medium |
-
2023
- 2023-01-13 CN CN202310038824.7A patent/CN115859911B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110020149A (en) * | 2017-11-30 | 2019-07-16 | Tcl集团股份有限公司 | Labeling processing method, device, terminal device and the medium of user information |
| CN114707474A (en) * | 2022-04-25 | 2022-07-05 | 平安普惠企业管理有限公司 | Report generation method and device, electronic equipment and computer readable storage medium |
| CN115048599A (en) * | 2022-06-20 | 2022-09-13 | 未鲲(上海)科技服务有限公司 | Enterprise product interface configuration method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115859911B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145828B (en) | Method and apparatus for generating video category detection model | |
| US20220222925A1 (en) | Artificial intelligence-based image processing method and apparatus, device, and storage medium | |
| CN107346336A (en) | Information processing method and device based on artificial intelligence | |
| CN114398557B (en) | Information recommendation method and device based on double images, electronic equipment and storage medium | |
| US20230297598A1 (en) | Latent Intent Clustering in High Latent Spaces | |
| CN115809833B (en) | Intelligent supervision method and device for foundation project based on portrait technology | |
| CN112069498A (en) | SQL injection detection model construction method and detection method | |
| CN116402630A (en) | Financial risk prediction method and system based on characterization learning | |
| CN116881430A (en) | Industrial chain identification method and device, electronic equipment and readable storage medium | |
| CN112582073B (en) | Medical information acquisition method, device, electronic equipment and medium | |
| CN113312924A (en) | Risk rule classification method and device based on NLP high-precision analysis label | |
| CN113282433A (en) | Cluster anomaly detection method and device and related equipment | |
| CN115859121B (en) | Text processing model training method and device | |
| CN112202919A (en) | Picture ciphertext storage and retrieval method and system under cloud storage environment | |
| CN115859911B (en) | Automatic label generation evolution method and device adapting to dynamic change of data | |
| CN113706207B (en) | Order success rate analysis method, device, equipment and medium based on semantic analysis | |
| CN106598983A (en) | Information display method and device | |
| CN111061779A (en) | Data processing method and device based on big data platform | |
| CN112561538B (en) | Risk model creation method, apparatus, computer device and readable storage medium | |
| CN112328977B (en) | Application software authenticity detection method, device, equipment and medium | |
| CN114741697A (en) | Malicious code classification method and device, electronic equipment and medium | |
| CN114332599A (en) | Image recognition method, image recognition device, computer equipment, storage medium and product | |
| CN113378723A (en) | Automatic safety identification system for hidden danger of power transmission and transformation line based on depth residual error network | |
| CN114510592A (en) | Image classification method and device, electronic equipment and storage medium | |
| CN111917861A (en) | Knowledge storage method and system based on block chain and knowledge graph and application thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |