CN113239229A - Intelligent screening data processing method and system and cloud platform - Google Patents
Intelligent screening data processing method and system and cloud platform Download PDFInfo
- Publication number
- CN113239229A CN113239229A CN202110674381.1A CN202110674381A CN113239229A CN 113239229 A CN113239229 A CN 113239229A CN 202110674381 A CN202110674381 A CN 202110674381A CN 113239229 A CN113239229 A CN 113239229A
- Authority
- CN
- China
- Prior art keywords
- voiceprint
- label
- data
- tag
- screened
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
According to the intelligent screening data processing method, the intelligent screening data processing system and the cloud platform, the first interactive data label can be obtained at random according to the to-be-operated indicating data, the screening accuracy is greatly improved, and according to the first interactive data label and the second interactive data label of at least one target operation indicating data, whether the to-be-screened operation indicating data is matched with one target operation indicating data or not can be determined more accurately, and the identification result of the to-be-screened operation indicating data is determined according to the preset identification result of the target operation indicating data. By carrying out multi-dimensional analysis on the indication data to be operated, each piece of relevant data can be accurately screened, the efficiency of screening the relevant data is effectively improved, and the cost is saved.
Description
Technical Field
The application relates to the technical field of data screening, in particular to an intelligent screening data processing method and system and a cloud platform.
Background
With the rapid development of intelligent technology, new terms such as cloud computing, big data and artificial intelligence enter the visual field of people, and the artificial intelligence is gradually and widely regarded as a technical revolution after people enter the information era. However, in the process of the related intelligent screening technology, huge workload is brought to the cloud platform due to the continuous increase of the amount of the related data, so that the cloud platform is disordered.
Disclosure of Invention
In view of this, the present application provides an intelligent screening data processing method, system and cloud platform.
In a first aspect, a method for processing intelligent screening data is provided, the method comprising:
acquiring a screening data set of operation instruction data to be screened;
selecting a first interactive data tag of the operation indication data to be screened from the screening data set, wherein the first interactive data tag comprises a first voiceprint tag and a first operation tag;
determining whether the operation indication data to be screened is matched with one target operation indication data or not according to the first interaction data label and a second interaction data label of at least one target operation indication data, wherein the second interaction data label comprises at least one of a second fingerprint label and a second operation label;
and when the operation instruction data to be screened is determined to be matched with one target operation instruction data, determining the identification result of the operation instruction data to be screened according to the preset identification result of the target operation instruction data.
Further, the selecting the first interactive data tag of the operation indication data to be filtered from the filtering data set of the operation indication data to be filtered includes:
randomly extracting at least one relevant feature vector voiceprint feature from the screening data set;
and for each pass characteristic vector voiceprint characteristic, extracting the characteristic of the pass characteristic vector voiceprint characteristic, and determining the first voiceprint label according to the extracted result.
Further, the determining the first voiceprint label according to the extracted result comprises:
building a reference label matrix according to the extracted cosine parameter set;
analyzing the average weight distribution of the reference label matrix;
and converting the reference label matrix into a standard label matrix according to the average weight distribution, and taking the standard label matrix as the first voiceprint label.
Further, the constructing of the reference label matrix according to the extracted cosine parameter set includes:
and selecting cosine parameters representing minimum voiceprint data from the cosine parameter set, and combining the cosine parameters into the reference label matrix.
Further, the selecting the first interactive data tag of the operation indication data to be filtered from the filtering data set of the operation indication data to be filtered includes:
selecting operation data from the screening data set; dividing the operational data into at least one operational step;
and for each operation step, performing standardized filtering on the operation step to obtain the first operation label.
Further, the method further comprises:
building a voiceprint training model according to the second voiceprint label of the at least one target operation indication data;
building an operation training model according to the second operation label of the at least one target operation indication data;
when the second interactive data tag includes a second voiceprint tag and a second operation tag, determining whether the operation indication data to be screened matches with one target operation indication data according to the first interactive data tag and the second interactive data tag of at least one target operation indication data includes: determining the voiceprint label matching degree between the first voiceprint label and the second voiceprint label according to the voiceprint training model;
determining the matching degree of the operation labels between the first operation label and the second operation label according to the operation training model;
and determining whether the operation instruction data to be screened is matched with a target operation instruction data or not according to the matching degree of the voiceprint tags and the matching degree of the operation tags.
Further, the determining the voiceprint label matching degree between the first voiceprint label and the second voiceprint label according to the voiceprint training model comprises:
parsing the first voiceprint label into at least one first voiceprint label sub-matrix;
for each first voiceprint label submatrix, searching a related feature vector content attribute set corresponding to the first voiceprint label submatrix in the voiceprint training model;
when the close characteristic vector content attribute set is not empty, sequentially analyzing a voiceprint label error between the first voiceprint label and each close characteristic vector content attribute in the close characteristic vector content attribute set;
and when the voiceprint label error is determined to be smaller than a first preset error range, determining the voiceprint label error as the voiceprint label matching degree.
Further, the constructing a voiceprint training model according to the second voiceprint label of the at least one target operation indication data includes:
parsing the second acoustic tag into at least one second acoustic tag sub-matrix;
reconstructing the second voiceprint tags according to the second voiceprint tag submatrix aiming at each second voiceprint tag submatrix to obtain third voiceprint tags;
setting up the voiceprint training model by taking the second voiceprint label submatrix as a characteristic vector and the third voiceprint label as a standard comparison value;
when the relevant feature vector content attribute set is not empty, the searching the relevant feature vector content attribute set corresponding to the first voiceprint label matrix in the voiceprint training model includes: taking the first voiceprint label submatrix as a characteristic vector, and determining a standard comparison value corresponding to the characteristic vector in the voiceprint training model;
determining at least one third voiceprint tag included in the standard comparison value as the set of correlation feature vector content attributes;
wherein said sequentially analyzing the voiceprint label error between the first voiceprint label and each relevant feature vector content attribute in the relevant feature vector content attribute set comprises:
reconstructing the first voiceprint label according to the first voiceprint label submatrix to obtain a fourth voiceprint label;
and sequentially analyzing the voiceprint label error between the fourth voiceprint label and each third voiceprint label.
In a second aspect, an intelligent screening data processing system is provided, comprising a processor and a memory, which are in communication with each other, the processor being configured to read a computer program from the memory and execute the computer program to implement the method described above.
In a third aspect, a cloud platform, comprising:
a memory for storing a computer program;
a processor coupled to the memory for executing the computer program stored by the memory to implement the above-described method.
According to the intelligent screening data processing method, the intelligent screening data processing system and the cloud platform, the first interactive data label can be obtained at random according to the to-be-screened operation indicating data, the screening accuracy is greatly improved, and according to the first interactive data label and the second interactive data label of at least one target operation indicating data, whether the to-be-screened operation indicating data is matched with one target operation indicating data or not can be determined more accurately, and the identification result of the to-be-screened operation indicating data is determined according to the preset identification result of the target operation indicating data. By carrying out multi-dimensional analysis on the indication data to be operated, each piece of relevant data can be accurately screened, the efficiency of screening the relevant data is effectively improved, and the cost is saved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart of an intelligent screening data processing method according to an embodiment of the present application.
Fig. 2 is a block diagram of an intelligent screening data processing apparatus according to an embodiment of the present application.
Fig. 3 is an architecture diagram of an intelligent screening data processing system according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions, the technical solutions of the present application are described in detail below with reference to the drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.
Referring to fig. 1, a method for processing intelligent screening data, which may be applied to a system for recognizing risk account intrusion prevention, is shown, and the method may include the following technical solutions described in steps 100 to 400.
Step 100, a screening data set of operation instruction data to be screened is obtained.
Illustratively, the screening data set represents that the operation indicating data to be screened forms a related data set.
Illustratively, the first interactive data tag includes a first voiceprint tag and a first action tag.
Illustratively, the second interactive data tag includes at least one of a second voiceprint tag and a second operation tag.
Step 400, when it is determined that the operation instruction data to be screened matches one target operation instruction data, determining an identification result of the operation instruction data to be screened according to a preset identification result of the target operation instruction data.
Illustratively, the identification result represents the screening of the set of screening data for relevant data meeting the requirements of the screening criteria.
It can be understood that, when the technical solutions described in the above steps 100 to 400 are executed, the first interactive data tag can be randomly obtained according to the instruction data to be filtered, so that the accuracy of the filtering is greatly improved, and according to the first interactive data tag and the second interactive data tag of at least one target operation instruction data, whether the instruction data to be filtered matches one target operation instruction data can be more accurately determined, and the identification result of the instruction data to be filtered is determined according to the preset identification result of the target operation instruction data. By carrying out multi-dimensional analysis on the indication data to be operated, each piece of relevant data can be accurately screened, the efficiency of screening the relevant data is effectively improved, and the cost is saved.
In an alternative embodiment, the inventors found that, when the first interactive data tag of the operation indication data to be filtered is selected from the filtered data set of the operation indication data to be filtered, there is a technical problem that the extracted voiceprint feature of each related feature vector is inaccurate, so that it is difficult to accurately select the first interactive data tag of the operation indication data to be filtered from the filtered data set of the operation indication data to be filtered, and in order to improve the technical problem, the step of selecting the first interactive data tag of the operation indication data to be filtered from the filtered data set of the operation indication data to be filtered described in step 200 may specifically include the technical solutions described in the following step q1 and step q 2.
And q1, randomly extracting at least one related feature vector voiceprint feature from the screening data set.
And q2, for each pass characteristic vector voiceprint characteristic, performing characteristic extraction on the pass characteristic vector voiceprint characteristic, and determining the first voiceprint label according to the extracted result.
It can be understood that, when the technical solutions described in the above steps q1 and q2 are performed, when the first interactive data tag of the operation indication data to be filtered is selected from the filtered data set of the operation indication data to be filtered, the technical problem that the extracted voiceprint feature of each related feature vector is inaccurate is avoided, so that the first interactive data tag of the operation indication data to be filtered can be accurately selected from the filtered data set of the operation indication data to be filtered.
In an alternative embodiment, the inventor finds that, according to the extracted result, there is a technical problem that a reference tag matrix is mistakenly constructed, so that it is difficult to accurately determine the first voiceprint tag, and in order to improve the technical problem, the step of determining the first voiceprint tag according to the extracted result described in step q2 may specifically include the technical solutions described in the following step q2a 1-step q2a 3.
And step q2a1, constructing a reference label matrix according to the extracted cosine parameter set.
Step q2a2, analyzing the average weight distribution of the reference label matrix.
And q2a3, converting the reference label matrix into a standard label matrix according to the average weight distribution, and taking the standard label matrix as the first voiceprint label.
It can be understood that when the technical scheme described in the step q2a 1-step q2a3 is executed, the technical problem of building a reference label matrix error is avoided according to the extracted result, so that the first voiceprint label can be accurately determined.
In an alternative embodiment, the inventor finds that, when constructing the reference tag matrix according to the extracted cosine parameter set, there is a problem that the cosine parameter of the minimum voiceprint data is not accurate, so that it is difficult to accurately construct the reference tag matrix according to the extracted cosine parameter set, and in order to improve the above technical problem, the step of constructing the reference tag matrix according to the extracted cosine parameter set described in step q2a1 has a technical solution that may include the following step q 11.
And q11, selecting cosine parameters representing the minimum voiceprint data from the cosine parameter set, and combining the cosine parameters into the reference label matrix.
It can be understood that, when the technical solution described in step q11 is executed, and a reference label matrix is built according to the extracted cosine parameter set, the problem that the cosine parameter of the minimum voiceprint data is not accurate is avoided, so that the extracted cosine parameter set can be used for building the reference label matrix accurately.
In an alternative embodiment, the inventors have found that, when the first interactive data tag of the operation indication data to be filtered is selected from the filtered data set of the operation indication data to be filtered, there is a technical problem that the selected operation data is inaccurate, so that it is difficult to accurately select the first interactive data tag of the operation indication data to be filtered from the filtered data set of the operation indication data to be filtered, and in order to improve the technical problem, the step of selecting the first interactive data tag of the operation indication data to be filtered from the filtered data set of the operation indication data to be filtered, which is described in step 200, may specifically include the technical solutions described in the following step w 1-step w 3.
And step w1, selecting operation data from the screening data set.
Step w2, dividing the operation data into at least one operation step.
And a step w3, performing standardized filtering on each operation step to obtain the first operation label.
It can be understood that when the technical solutions described in steps w 1-w 3 are executed, when the first interactive data tag of the operation indication data to be filtered is selected from the filtered data set of the operation indication data to be filtered, the technical problem of inaccurate operation data selection is avoided, so that the first interactive data tag of the operation indication data to be filtered can be accurately selected from the filtered data set of the operation indication data to be filtered.
Based on the above basis, the technical scheme described in the following steps e 1-e 5 is also included.
And e1, building a voiceprint training model according to the second voiceprint label of the at least one target operation indication data.
And e2, building an operation training model according to the second operation label of the at least one target operation indication data.
Step e3, when the second interactive data tag includes a second fingerprint tag and a second operation tag, the determining whether the operation indication data to be filtered matches with a target operation indication data according to the first interactive data tag and the second interactive data tag of at least one target operation indication data includes: and determining the matching degree of the voiceprint labels between the first voiceprint label and the second voiceprint label according to the voiceprint training model.
Step e4, determining the operation label matching degree between the first operation label and the second operation label according to the operation training model.
Step e5, determining whether the operation instruction data to be screened is matched with a target operation instruction data according to the matching degree of the voiceprint label and the matching degree of the operation label.
It is understood that when the technical solutions described in the above steps e 1-e 5 are executed, whether the operation instruction data to be screened matches with a target operation instruction data can be determined more accurately through the voiceprint training model and the operation training model.
In an alternative embodiment, the inventor finds that, according to the voiceprint training model, there is a problem that the first voiceprint label is incorrectly parsed, so that it is difficult to accurately determine the matching degree of the voiceprint labels between the first voiceprint label and the second voiceprint label, and in order to improve the above technical problem, the step of determining the matching degree of the voiceprint labels between the first voiceprint label and the second voiceprint label according to the voiceprint training model described in step e3 may specifically include the technical solutions described in the following steps e3a 1-e 3a 4.
Step e3a1, parsing said first voiceprint label into at least one first voiceprint label sub-matrix.
And e3a2, searching the related feature vector content attribute set corresponding to each first voiceprint label submatrix in the voiceprint training model.
And e3a3, when the relevant feature vector content attribute set is not empty, sequentially analyzing the voiceprint label error between the first voiceprint label and each relevant feature vector content attribute in the relevant feature vector content attribute set.
Step e3a4, when the voiceprint label error is determined to be smaller than a first preset error range, determining the voiceprint label error as the voiceprint label matching degree
It can be understood that, when the technical solutions described in steps e3a 1-e 3a4 are implemented, the problem of the parsing error of the first voiceprint label is avoided according to the voiceprint training model, so that the matching degree of the voiceprint labels between the first voiceprint label and the second voiceprint label can be accurately determined.
In an alternative embodiment, the inventor finds that, according to the second voiceprint tag of the at least one target operation indication data, there is a problem that the second voiceprint tag is reconstructed incorrectly, so that it is difficult to accurately build the voiceprint training model, and in order to improve the above technical problem, the step of building the voiceprint training model according to the second voiceprint tag of the at least one target operation indication data, which is described in step e1, may specifically include the technical solutions described in the following step e1a 1-step e1a 5.
Step e1a1, parsing the second acoustic label into at least one second acoustic label sub-matrix.
And e1a2, reconstructing the second voiceprint tags according to the second voiceprint tag submatrix aiming at each second voiceprint tag submatrix to obtain third voiceprint tags.
And e1a3, constructing the voiceprint training model by taking the second voiceprint label submatrix as a characteristic vector and the third voiceprint label as a standard comparison value.
Step e1a4, when the relevant feature vector content attribute set is not empty, the searching the relevant feature vector content attribute set corresponding to the first voiceprint label matrix in the voiceprint training model includes: and determining a standard comparison value corresponding to the characteristic vector in the voiceprint training model by taking the first voiceprint label submatrix as the characteristic vector.
Step e1a5, determining at least one third voiceprint label comprised in the standard comparison value as the set of correlation feature vector content attributes.
It can be understood that, when the technical solutions described in the above steps e1a 1-e 1a5 are performed, according to the second voiceprint tag of the at least one target operation indication data, the problem of reconstruction errors of the second voiceprint tag is avoided, so that the voiceprint training model can be accurately constructed.
In an alternative embodiment, the inventors found that when the voiceprint label error between the first voiceprint label and each relevant feature vector content attribute in the relevant feature vector content attribute set is analyzed sequentially, there is a problem that the first voiceprint label submatrix is inaccurate, so that it is difficult to accurately analyze the voiceprint label error between the first voiceprint label and each relevant feature vector content attribute in the relevant feature vector content attribute set, and in order to improve the above technical problem, the step of analyzing the voiceprint label error between the first voiceprint label and each relevant feature vector content attribute in the relevant feature vector content attribute set sequentially described in step e3a3 may specifically include the technical solutions described in the following step r1 and step r 2.
And r1, reconstructing the first voiceprint label according to the first voiceprint label submatrix to obtain a fourth voiceprint label.
And r2, sequentially analyzing the voiceprint label error between the fourth voiceprint label and each third voiceprint label.
It can be understood that when the technical solutions described in the above steps r1 and r2 are performed, when the voiceprint label errors between the first voiceprint label and each of the relevant feature vector content attributes in the relevant feature vector content attribute set are sequentially analyzed, the problem of inaccuracy of the first voiceprint label submatrix is avoided, so that the voiceprint label errors between the first voiceprint label and each of the relevant feature vector content attributes in the relevant feature vector content attribute set can be accurately analyzed.
In a possible embodiment, the inventor finds that, when the operation tag matching degree is characterized by an operation tag error, the reference standard comparison value is not accurate according to the voiceprint tag matching degree and the operation tag matching degree, so that it is difficult to accurately determine whether the operation indication data to be filtered matches with a target operation indication data, and in order to improve the above technical problem, the step of determining whether the operation indication data to be filtered matches with a target operation indication data according to the voiceprint tag matching degree and the operation tag matching degree described in step e5 when the operation tag matching degree is characterized by an operation tag error may specifically include the technical solutions described in the following steps e5a 1-e 5a 3.
Step e5a1, determining a reference standard comparison value of the voiceprint tag error and the operation tag error.
And e5a2, determining the target operation instruction data represented by the content attribute of the related feature vector corresponding to the reference standard comparison value.
And e5a3, determining whether the operation instruction data to be screened is matched with the target operation instruction data according to the reference standard comparison value and a second preset error range.
It can be understood that, when the technical solutions described in the above steps e5a 1-e 5a3 are performed, when the operation tag matching degree is characterized by an operation tag error, the problem of inaccurate comparison value of the reference standard is avoided according to the voiceprint tag matching degree and the operation tag matching degree, so that whether the operation indication data to be screened matches with a target operation indication data can be accurately determined.
Based on the above basis, the following technical solution described in step t1 may also be included.
And t1, when it is determined that the operation instruction data to be screened is matched with a target operation instruction data, analyzing the total matching degree between the operation instruction data to be screened and the target operation instruction data, and determining whether to send the operation instruction data to be screened and the target operation instruction data to a cloud platform for one-by-one audit according to the total matching degree and a third preset error range.
It can be understood that, when the technical solution described in the above step t1 is executed, by improving the total matching degree between the operation instruction data to be screened and the target operation instruction data, it can be accurately determined whether to send the operation instruction data to be screened and the target operation instruction data to the cloud platform for one-by-one auditing.
On the basis, please refer to fig. 2 in combination, an intelligent screening data processing apparatus 200 is provided, which is applied to a cloud platform, and the apparatus includes:
a data obtaining module 210, configured to obtain a screening data set of operation instruction data to be screened;
a tag screening module 220, configured to select a first interactive data tag of the operation indication data to be screened from the screened data set, where the first interactive data tag includes a first voiceprint tag and a first operation tag;
a tag determining module 230, configured to determine whether the operation indication data to be filtered matches one target operation indication data according to the first interaction data tag and a second interaction data tag of at least one target operation indication data, where the second interaction data tag includes at least one of a second fingerprint tag and a second operation tag;
and a result identification module 240, configured to determine, when it is determined that the operation instruction data to be screened matches one target operation instruction data, an identification result of the operation instruction data to be screened according to a preset identification result of the target operation instruction data.
On the basis of the above, please refer to fig. 3, which shows an intelligent screening data processing system 300, which includes a processor 310 and a memory 320, which are communicated with each other, wherein the processor 310 is configured to read a computer program from the memory 320 and execute the computer program to implement the above method.
On the basis of the above, there is also provided a computer-readable storage medium on which a computer program is stored, which when executed implements the above-described method.
In summary, based on the above scheme, the first interactive data tag can be randomly obtained according to the instruction data to be operated, so that the screening accuracy is greatly improved, and according to the first interactive data tag and the second interactive data tag of at least one target operation instruction data, whether the instruction data to be screened is matched with one target operation instruction data can be more accurately determined, and the identification result of the instruction data to be screened is determined according to the preset identification result of the target operation instruction data. By carrying out multi-dimensional analysis on the indication data to be operated, each piece of relevant data can be accurately screened, the efficiency of screening the relevant data is effectively improved, and the cost is saved.
It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).
It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.
Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the present application may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. An intelligent screening data processing method, characterized in that the method comprises:
acquiring a screening data set of operation instruction data to be screened;
selecting a first interactive data tag of the operation indication data to be screened from the screening data set, wherein the first interactive data tag comprises a first voiceprint tag and a first operation tag;
determining whether the operation indication data to be screened is matched with one target operation indication data or not according to the first interaction data label and a second interaction data label of at least one target operation indication data, wherein the second interaction data label comprises at least one of a second fingerprint label and a second operation label;
and when the operation instruction data to be screened is determined to be matched with one target operation instruction data, determining the identification result of the operation instruction data to be screened according to the preset identification result of the target operation instruction data.
2. The method according to claim 1, wherein the selecting the first interactive data tag of the operation indication data to be filtered from the filtered data set of the operation indication data to be filtered comprises:
randomly extracting at least one relevant feature vector voiceprint feature from the screening data set;
and for each pass characteristic vector voiceprint characteristic, extracting the characteristic of the pass characteristic vector voiceprint characteristic, and determining the first voiceprint label according to the extracted result.
3. The method of claim 2, wherein determining the first voiceprint tag from the extracted result comprises:
building a reference label matrix according to the extracted cosine parameter set;
analyzing the average weight distribution of the reference label matrix;
and converting the reference label matrix into a standard label matrix according to the average weight distribution, and taking the standard label matrix as the first voiceprint label.
4. The method of claim 3, wherein the building a reference label matrix from the extracted set of cosine parameters comprises:
and selecting cosine parameters representing minimum voiceprint data from the cosine parameter set, and combining the cosine parameters into the reference label matrix.
5. The method according to claim 1, wherein the selecting the first interactive data tag of the operation indication data to be filtered from the filtered data set of the operation indication data to be filtered comprises:
selecting operation data from the screening data set;
dividing the operational data into at least one operational step;
and for each operation step, performing standardized filtering on the operation step to obtain the first operation label.
6. The method of claim 1, further comprising:
building a voiceprint training model according to the second voiceprint label of the at least one target operation indication data;
building an operation training model according to the second operation label of the at least one target operation indication data;
when the second interactive data tag includes a second voiceprint tag and a second operation tag, determining whether the operation indication data to be screened matches with one target operation indication data according to the first interactive data tag and the second interactive data tag of at least one target operation indication data includes: determining the voiceprint label matching degree between the first voiceprint label and the second voiceprint label according to the voiceprint training model;
determining the matching degree of the operation labels between the first operation label and the second operation label according to the operation training model;
and determining whether the operation instruction data to be screened is matched with a target operation instruction data or not according to the matching degree of the voiceprint tags and the matching degree of the operation tags.
7. The method of claim 6, wherein determining a voiceprint tag match between the first voiceprint tag and the second voiceprint tag according to the voiceprint training model comprises:
parsing the first voiceprint label into at least one first voiceprint label sub-matrix;
for each first voiceprint label submatrix, searching a related feature vector content attribute set corresponding to the first voiceprint label submatrix in the voiceprint training model;
when the close characteristic vector content attribute set is not empty, sequentially analyzing a voiceprint label error between the first voiceprint label and each close characteristic vector content attribute in the close characteristic vector content attribute set;
and when the voiceprint label error is determined to be smaller than a first preset error range, determining the voiceprint label error as the voiceprint label matching degree.
8. The method of claim 7, wherein constructing a voiceprint training model from the second voiceprint label of the at least one target operation indication data comprises:
parsing the second acoustic tag into at least one second acoustic tag sub-matrix;
reconstructing the second voiceprint tags according to the second voiceprint tag submatrix aiming at each second voiceprint tag submatrix to obtain third voiceprint tags;
setting up the voiceprint training model by taking the second voiceprint label submatrix as a characteristic vector and the third voiceprint label as a standard comparison value;
when the relevant feature vector content attribute set is not empty, the searching the relevant feature vector content attribute set corresponding to the first voiceprint label matrix in the voiceprint training model includes: taking the first voiceprint label submatrix as a characteristic vector, and determining a standard comparison value corresponding to the characteristic vector in the voiceprint training model;
determining at least one third voiceprint tag included in the standard comparison value as the set of correlation feature vector content attributes;
wherein said sequentially analyzing the voiceprint label error between the first voiceprint label and each relevant feature vector content attribute in the relevant feature vector content attribute set comprises:
reconstructing the first voiceprint label according to the first voiceprint label submatrix to obtain a fourth voiceprint label;
and sequentially analyzing the voiceprint label error between the fourth voiceprint label and each third voiceprint label.
9. An intelligent screening data processing system comprising a processor and a memory in communication with each other, the processor being configured to read a computer program from the memory and execute the computer program to perform the method of any one of claims 1 to 8.
10. A cloud platform, comprising:
a memory for storing a computer program;
a processor coupled to the memory for executing the computer program stored by the memory to implement the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110674381.1A CN113239229A (en) | 2021-06-17 | 2021-06-17 | Intelligent screening data processing method and system and cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110674381.1A CN113239229A (en) | 2021-06-17 | 2021-06-17 | Intelligent screening data processing method and system and cloud platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113239229A true CN113239229A (en) | 2021-08-10 |
Family
ID=77140269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110674381.1A Withdrawn CN113239229A (en) | 2021-06-17 | 2021-06-17 | Intelligent screening data processing method and system and cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113239229A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113746701A (en) * | 2021-09-03 | 2021-12-03 | 四川英得赛克科技有限公司 | Data acquisition method, system, storage medium and electronic equipment |
| CN114693353A (en) * | 2022-03-31 | 2022-07-01 | 方付春 | Electronic commerce data processing method, electronic commerce system and cloud platform |
| CN115357925A (en) * | 2022-09-23 | 2022-11-18 | 王维礼 | Encryption processing method and system and cloud platform |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101064043A (en) * | 2006-04-29 | 2007-10-31 | 上海优浪信息科技有限公司 | Sound-groove gate inhibition system and uses thereof |
| US20080288551A1 (en) * | 2005-11-30 | 2008-11-20 | Koninklijke Philips Electronics, N.V. | Method and System for Updating User Profiles |
| US20090132508A1 (en) * | 2006-05-02 | 2009-05-21 | Koninklijke Philips Electronics N.V. | System and method for associating a category label of one user with a category label defined by another user |
| CN109036436A (en) * | 2018-09-18 | 2018-12-18 | 广州势必可赢网络科技有限公司 | A kind of voice print database method for building up, method for recognizing sound-groove, apparatus and system |
| CN109145204A (en) * | 2018-07-27 | 2019-01-04 | 苏州思必驰信息科技有限公司 | The generation of portrait label and application method and system |
| CN110489659A (en) * | 2019-07-18 | 2019-11-22 | 平安科技（深圳）有限公司 | Data matching method and device |
| CN110867188A (en) * | 2018-08-13 | 2020-03-06 | 珠海格力电器股份有限公司 | Method and device for providing content service, storage medium and electronic device |
| CN111506764A (en) * | 2020-04-16 | 2020-08-07 | 腾讯科技（深圳）有限公司 | Audio data screening method, computer device and storage medium |
| CN112328994A (en) * | 2020-11-17 | 2021-02-05 | 携程计算机技术（上海）有限公司 | Voiceprint data processing method and device, electronic equipment and storage medium |
| CN112380377A (en) * | 2021-01-14 | 2021-02-19 | 腾讯科技（深圳）有限公司 | Audio recommendation method and device, electronic equipment and computer storage medium |
-
2021
- 2021-06-17 CN CN202110674381.1A patent/CN113239229A/en not_active Withdrawn
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080288551A1 (en) * | 2005-11-30 | 2008-11-20 | Koninklijke Philips Electronics, N.V. | Method and System for Updating User Profiles |
| CN101064043A (en) * | 2006-04-29 | 2007-10-31 | 上海优浪信息科技有限公司 | Sound-groove gate inhibition system and uses thereof |
| US20090132508A1 (en) * | 2006-05-02 | 2009-05-21 | Koninklijke Philips Electronics N.V. | System and method for associating a category label of one user with a category label defined by another user |
| CN109145204A (en) * | 2018-07-27 | 2019-01-04 | 苏州思必驰信息科技有限公司 | The generation of portrait label and application method and system |
| CN110867188A (en) * | 2018-08-13 | 2020-03-06 | 珠海格力电器股份有限公司 | Method and device for providing content service, storage medium and electronic device |
| CN109036436A (en) * | 2018-09-18 | 2018-12-18 | 广州势必可赢网络科技有限公司 | A kind of voice print database method for building up, method for recognizing sound-groove, apparatus and system |
| CN110489659A (en) * | 2019-07-18 | 2019-11-22 | 平安科技（深圳）有限公司 | Data matching method and device |
| CN111506764A (en) * | 2020-04-16 | 2020-08-07 | 腾讯科技（深圳）有限公司 | Audio data screening method, computer device and storage medium |
| CN112328994A (en) * | 2020-11-17 | 2021-02-05 | 携程计算机技术（上海）有限公司 | Voiceprint data processing method and device, electronic equipment and storage medium |
| CN112380377A (en) * | 2021-01-14 | 2021-02-19 | 腾讯科技（深圳）有限公司 | Audio recommendation method and device, electronic equipment and computer storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113746701A (en) * | 2021-09-03 | 2021-12-03 | 四川英得赛克科技有限公司 | Data acquisition method, system, storage medium and electronic equipment |
| CN114693353A (en) * | 2022-03-31 | 2022-07-01 | 方付春 | Electronic commerce data processing method, electronic commerce system and cloud platform |
| CN115357925A (en) * | 2022-09-23 | 2022-11-18 | 王维礼 | Encryption processing method and system and cloud platform |
| CN115357925B (en) * | 2022-09-23 | 2024-01-12 | 陕西合友网络科技有限公司 | Encryption processing method, encryption processing system and cloud platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113239229A (en) | Intelligent screening data processing method and system and cloud platform | |
| CN112232771B (en) | Big data analysis method and big data cloud platform applied to smart government-enterprise cloud service | |
| CN113378554A (en) | Medical information intelligent interaction method and system | |
| CN114661994B (en) | User interest data processing method and system based on artificial intelligence and cloud platform | |
| CN113450075A (en) | Work order processing method and device based on natural language technology | |
| CN115732050A (en) | Intelligent medical big data information acquisition method and system | |
| CN116737975A (en) | Public health data query method and system applied to image analysis | |
| CN114329116B (en) | Artificial intelligence-based intelligent park resource matching degree analysis method and system | |
| CN115641176B (en) | Data analysis method and AI system | |
| CN111581299A (en) | Inter-library data conversion system and method of multi-source data warehouse based on big data | |
| CN113610373A (en) | Information decision processing method and system based on intelligent manufacturing | |
| CN114779923A (en) | VR simulation scene positioning method and system based on ultrasonic waves | |
| CN113626538A (en) | Medical information intelligent classification method and system based on big data | |
| CN114661980B (en) | Webpage data pushing method and system and cloud platform | |
| CN114201973B (en) | Resource pool object data mining method and system based on artificial intelligence | |
| CN115409510B (en) | Online transaction security system and method | |
| CN114358420B (en) | Business workflow intelligent optimization method and system based on industrial ecology | |
| CN115756576B (en) | Translation method of software development kit and software development system | |
| CN116720123B (en) | Account identification method, account identification device, terminal equipment and medium | |
| CN113609931A (en) | Face recognition method and system based on neural network | |
| CN115687875A (en) | Smart campus management method and system and SaaS cloud platform | |
| CN116185963A (en) | Processing system and method for power data file | |
| CN113239332A (en) | Intelligent account filling and login processing method and system and cloud platform | |
| CN114817417A (en) | Intelligent interaction method and system based on meta universe | |
| CN114663071A (en) | Method and system for processing science and technology project data on line |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210810 |