CN117194944A - Pattern recognition integrated service system based on artificial intelligence - Google Patents
Pattern recognition integrated service system based on artificial intelligence Download PDFInfo
- Publication number
- CN117194944A CN117194944A CN202310551089.XA CN202310551089A CN117194944A CN 117194944 A CN117194944 A CN 117194944A CN 202310551089 A CN202310551089 A CN 202310551089A CN 117194944 A CN117194944 A CN 117194944A
- Authority
- CN
- China
- Prior art keywords
- data
- target data
- data sample
- target
- sample data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003909 pattern recognition Methods 0.000 title claims abstract description 26
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000000605 extraction Methods 0.000 claims abstract description 31
- 230000005540 biological transmission Effects 0.000 claims abstract description 21
- 239000000284 extract Substances 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 66
- 238000004364 calculation method Methods 0.000 claims description 26
- 238000013507 mapping Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 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
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of pattern recognition integrated service, and discloses a pattern recognition integrated service system based on artificial intelligence, which comprises the following components: the device comprises a data sample acquisition module, a data transmission module, a main control module, a data encryption module, a data characteristic extraction module, a data identification module, a data classification module and a display module. According to the invention, the data encryption module processes the first shared value and the second shared value by adopting a random overturning method on the basis of random arrangement, so that the randomness is improved, and meanwhile, the leakage of an intermediate result is prevented; meanwhile, the data characteristic extraction module can rapidly extract characteristic target data sample data from a large number of target data sample data without performing a large number of logic judgments, so that the efficiency of extracting the characteristic target data sample data can be effectively improved, and the time for extracting the characteristic target data sample data is saved.
Description
Technical Field
The invention belongs to the technical field of pattern recognition integrated services, and particularly relates to a pattern recognition integrated service system based on artificial intelligence.
Background
The problem of pattern recognition is to divide the samples into certain categories according to the characteristics of the samples by using a calculation method. Pattern recognition is to study the automatic processing and interpretation of patterns by computer mathematical technique, and the environment and object are collectively called as "pattern". With the development of computer technology, it is possible for human beings to study a complex information processing process, and an important form of the process is the recognition of the environment and objects by living bodies. Pattern recognition takes image processing, computer vision, voice language information processing, brain network group, brain-like intelligence and the like as main research directions to research the mechanism of human pattern recognition and an effective calculation method; however, the existing pattern recognition integrated service system recognition process based on artificial intelligence easily causes the problem of data privacy disclosure, thereby affecting the security of data; meanwhile, the existing method for extracting target data sample data cannot rapidly extract target data sample data.
Through the above analysis, the problems and defects existing in the prior art are as follows:
(1) The existing pattern recognition integrated service system recognition process based on artificial intelligence easily causes the problem of data privacy disclosure, thereby influencing the safety of data.
(2) The existing method for extracting the target data sample data cannot extract the target data sample data rapidly.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a pattern recognition integrated service system based on artificial intelligence.
The invention is realized in such a way that a pattern recognition integrated service system based on artificial intelligence comprises:
the device comprises a data sample acquisition module, a data transmission module, a main control module, a data encryption module, a data characteristic extraction module, a data identification module, a data classification module and a display module;
the data sample acquisition module is connected with the data transmission module and is used for acquiring a target data sample; the data sample acquisition module acquisition method comprises the following steps: searching a target data keyword through a searching program, and counting target data to construct a target data set; storing the retrieval target data into a target data set;
the data transmission module is connected with the data sample acquisition module and the main control module and is used for transmitting the target data sample to the main control module through a wireless network; the data transmission module transmission method comprises the following steps: detecting a wireless network signal through a wireless signal detection program, inputting a wireless network account number, connecting a wireless network, and sending collected target data to a main control module through the wireless network for processing;
the main control module is connected with the data transmission module, the data encryption module, the data characteristic extraction module, the data identification module, the data classification module and the display module and used for controlling the normal work of each module;
the data encryption module is connected with the main control module and used for encrypting the target data sample; the data encryption module encryption method comprises the following steps: encrypting target characteristic target data sample data to obtain an initial intermediate result; inputting the initial intermediate result to a basic operator layer, and obtaining target encryption target data sample data output by the basic operator layer;
the data characteristic extraction module is connected with the main control module and is used for extracting data characteristics of the target data sample; the data characteristic extraction module is used for extracting the following steps: determining a key target data sample data attribute; establishing a template vector according to the value range of the target data sample data element of the key target data sample data attribute and the value range of the key target data sample data element of the characteristic target data sample data; extracting characteristic target data sample data by applying the established template vector to target data sample data elements corresponding to key target data sample data attributes in the plurality of sets of target data sample data;
the data identification module is connected with the main control module and used for identifying the data characteristics of the target data sample;
the data classification module is connected with the main control module and is used for classifying the target data sample data according to the identification result;
the display module is connected with the main control module and used for displaying the collected target data sample data and the identification result.
Further, the encryption method of the data encryption module comprises the following steps:
(1) Encrypting target characteristic target data sample data to obtain an initial intermediate result; inputting the initial intermediate result to a basic operator layer, and obtaining target encryption target data sample data output by the basic operator layer;
the basic operator layer comprises a linear calculation layer, a target data sample data type conversion layer and a nonlinear element-by-element calculation layer.
Further, the inputting the initial intermediate result to a basic operator layer, and obtaining target encryption target data sample data output by the basic operator layer includes:
under the condition that the target data sample data type of the initial intermediate result is inconsistent with the target data sample data type, inputting the initial intermediate result to the target data sample data type conversion layer, and acquiring first target data sample data of the target data sample data type output by the target data sample data type conversion layer;
inputting the first target data sample data into the linear calculation layer to obtain first encrypted target data sample data output by the linear calculation layer;
and inputting the first encrypted target data sample data into the nonlinear element-by-element calculation layer, and obtaining the target encrypted target data sample data output by the nonlinear element-by-element calculation layer.
Further, the inputting the first target data sample data to the linear computing layer, obtaining first encrypted target data sample data output by the linear computing layer, includes:
splitting the first target data sample data to obtain at least two subsequences;
the first encrypted target data sample data is determined based on the at least two sub-sequences.
Further, the determining the first encrypted target data sample data based on the at least two sub-sequences includes:
obtaining a target multiplication triplet;
the first encrypted target data sample data is determined based on the target multiplication triplet and the at least two sub-sequences.
Further, the inputting the first encrypted target data sample data to the nonlinear element-by-element calculation layer, and obtaining the target encrypted target data sample data output by the nonlinear element-by-element calculation layer includes:
acquiring a first sharing value and a second sharing value corresponding to the first encryption target data sample data;
respectively processing the first sharing value and the second sharing value by adopting target random arrangement to obtain a third sharing value and a fourth sharing value;
determining an element-by-element function result based on the third shared value and the fourth shared value;
splitting the element-by-element function result to obtain a fifth sharing value and a sixth sharing value;
respectively carrying out inverse arrangement on the fifth sharing value and the sixth sharing value to determine the target encryption target data sample data;
the processing the first sharing value and the second sharing value by adopting the target random arrangement respectively to obtain a third sharing value and a fourth sharing value includes:
obtaining a target random overturn vector;
and respectively processing the first sharing value and the second sharing value based on the target random arrangement and the target random turning vector to acquire the third sharing value and the fourth sharing value.
Further, the base operator layer includes:
at least one base operator of addition, subtraction, multiplication, transformation shape, and broadcast shape.
Further, the data feature extraction module extracts the following steps:
1) Acquiring a plurality of groups of target data sample data, and cleaning the plurality of groups of target data sample data; wherein each set of target data sample data comprises target data sample data elements corresponding to a predetermined number of target data sample data attributes, respectively; determining key target data sample data attributes for extracting characteristic target data sample data in the preset target data sample data attributes;
2) Establishing a template vector according to a target data sample data element value range of the key target data sample data attribute and a value range of a key target data sample data element of the characteristic target data sample data, wherein the key target data sample data element refers to a target data sample data element corresponding to the key target data sample data attribute in the characteristic target data sample data;
3) And extracting characteristic target data sample data by applying the established template vector to target data sample data elements corresponding to the key target data sample data attributes in the plurality of groups of target data sample data.
Further, the establishing the template vector according to the target data sample data element value range of the key target data sample data attribute and the value range of the key target data sample data element of the characteristic target data sample data comprises:
analyzing the value range of the target data sample data element of the key target data sample data attribute and the value range of the key target data sample data element of the characteristic target data sample data;
establishing a value vector according to the value field of the data elements of the target data sample;
and establishing a template vector according to the value vector and the value range.
Further, the elements in the template vector are in one-to-one correspondence with the elements in the value vector, and the key target data sample data elements refer to target data sample data elements corresponding to key target data sample data attributes in the characteristic target data sample data, including:
forming target data sample data elements corresponding to key target data sample data attributes in the multiple groups of target data sample data into target data sample data vectors, and establishing a one-to-one mapping function of the value fields and the value vectors of the target data sample data elements;
mapping each target data sample data element in the target data sample data vector into an element in a corresponding value vector by using the one-to-one mapping function, and forming a mapping vector by the mapped element;
establishing an extraction vector by using the mapping vector and the corresponding relation between the elements of the value vector and the elements of the template vector;
and extracting characteristic target data sample data from the plurality of groups of target data sample data by using the extraction vector.
In combination with the above technical solution and the technical problems to be solved, please analyze the following aspects to provide the following advantages and positive effects:
first, aiming at the technical problems in the prior art and the difficulty in solving the problems, the technical problems solved by the technical proposal of the invention are analyzed in detail and deeply by tightly combining the technical proposal to be protected, the results and data in the research and development process, and the like, and some technical effects brought after the problems are solved have creative technical effects. The specific description is as follows:
according to the invention, the first sharing value and the second sharing value are processed by adopting a random overturning method based on random arrangement through the data encryption module, so that the randomness is improved, the distribution of each element in the random arrangement is avoided, the data privacy of the target data sample is further protected, and the middle result is prevented from being revealed; meanwhile, the data characteristic extraction module can rapidly extract characteristic target data sample data from a large number of target data sample data without performing a large number of logic judgments, so that the efficiency of extracting the characteristic target data sample data can be effectively improved, and the time for extracting the characteristic target data sample data is saved.
Secondly, the technical scheme is regarded as a whole or from the perspective of products, and the technical scheme to be protected has the following technical effects and advantages:
according to the invention, the first sharing value and the second sharing value are processed by adopting a random overturning method based on random arrangement through the data encryption module, so that the randomness is improved, the distribution of each element in the random arrangement is avoided, the data privacy of the target data sample is further protected, and the middle result is prevented from being revealed; meanwhile, the data characteristic extraction module can rapidly extract characteristic target data sample data from a large number of target data sample data without performing a large number of logic judgments, so that the efficiency of extracting the characteristic target data sample data can be effectively improved, and the time for extracting the characteristic target data sample data is saved.
Drawings
FIG. 1 is a block diagram of an artificial intelligence based pattern recognition integrated service system according to an embodiment of the present invention.
Fig. 2 is a flowchart of an encryption method of a data encryption module according to an embodiment of the present invention.
Fig. 3 is a flowchart of a data feature extraction module extraction method according to an embodiment of the present invention.
In fig. 1: 1. a data sample acquisition module; 2. a data transmission module; 3. a main control module; 4. a data encryption module; 5. a data feature extraction module; 6. a data identification module; 7. a data classification module; 8. and a display module.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
1. The embodiments are explained. In order to fully understand how the invention may be embodied by those skilled in the art, this section is an illustrative embodiment in which the claims are presented for purposes of illustration.
As shown in fig. 1, an artificial intelligence based pattern recognition integrated service system according to an embodiment of the present invention includes: the system comprises a data sample acquisition module 1, a data transmission module 2, a main control module 3, a data encryption module 4, a data characteristic extraction module 5, a data identification module 6, a data classification module 7 and a display module 8.
The data sample acquisition module 1 is connected with the data transmission module 2 and is used for acquiring target data samples; the data sample acquisition module acquisition method comprises the following steps: searching a target data keyword through a searching program, and counting target data to construct a target data set; storing the retrieval target data into a target data set;
the data transmission module 2 is connected with the data sample acquisition module 1 and the main control module 3 and is used for transmitting the target data sample to the main control module through a wireless network; the data transmission module transmission method comprises the following steps: detecting a wireless network signal through a wireless signal detection program, inputting a wireless network account number, connecting a wireless network, and sending collected target data to a main control module through the wireless network for processing 3;
the main control module 3 is connected with the data transmission module 2, the data encryption module 4, the data characteristic extraction module 5, the data identification module 6, the data classification module 7 and the display module 8 and used for controlling the normal work of each module;
the data encryption module 4 is connected with the main control module 3 and used for encrypting the target data sample; the data encryption module encryption method comprises the following steps: encrypting target characteristic target data sample data to obtain an initial intermediate result; inputting the initial intermediate result to a basic operator layer, and obtaining target encryption target data sample data output by the basic operator layer;
the data characteristic extraction module 5 is connected with the main control module 3 and is used for extracting data characteristics of the target data sample; the data characteristic extraction module is used for extracting the following steps: determining a key target data sample data attribute; establishing a template vector according to the value range of the target data sample data element of the key target data sample data attribute and the value range of the key target data sample data element of the characteristic target data sample data; extracting characteristic target data sample data by applying the established template vector to target data sample data elements corresponding to key target data sample data attributes in the plurality of sets of target data sample data;
the data identification module 6 is connected with the main control module 3 and is used for identifying the data characteristics of the target data sample;
the data classification module 7 is connected with the main control module 3 and is used for classifying the target data sample data according to the identification result;
the display module 8 is connected with the main control module 3 and used for displaying the collected target data sample data and the identification result.
As shown in fig. 2, the encryption method of the data encryption module provided by the invention is as follows:
s101, carrying out encryption processing on target characteristic target data sample data to obtain an initial intermediate result; inputting the initial intermediate result to a basic operator layer, and obtaining target encryption target data sample data output by the basic operator layer;
the basic operator layer comprises a linear calculation layer, a target data sample data type conversion layer and a nonlinear element-by-element calculation layer.
The method for inputting the initial intermediate result into the basic operator layer to obtain the target encryption target data sample data output by the basic operator layer comprises the following steps:
under the condition that the target data sample data type of the initial intermediate result is inconsistent with the target data sample data type, inputting the initial intermediate result to the target data sample data type conversion layer, and acquiring first target data sample data of the target data sample data type output by the target data sample data type conversion layer;
inputting the first target data sample data into the linear calculation layer to obtain first encrypted target data sample data output by the linear calculation layer;
and inputting the first encrypted target data sample data into the nonlinear element-by-element calculation layer, and obtaining the target encrypted target data sample data output by the nonlinear element-by-element calculation layer.
The method for inputting the first target data sample data into the linear computing layer to obtain the first encrypted target data sample data output by the linear computing layer comprises the following steps:
splitting the first target data sample data to obtain at least two subsequences;
the first encrypted target data sample data is determined based on the at least two sub-sequences.
The method for determining the first encrypted target data sample data based on the at least two subsequences provided by the invention comprises the following steps:
obtaining a target multiplication triplet;
the first encrypted target data sample data is determined based on the target multiplication triplet and the at least two sub-sequences.
The method for inputting the first encrypted target data sample data into the nonlinear element-by-element calculation layer to obtain the target encrypted target data sample data output by the nonlinear element-by-element calculation layer comprises the following steps:
acquiring a first sharing value and a second sharing value corresponding to the first encryption target data sample data;
respectively processing the first sharing value and the second sharing value by adopting target random arrangement to obtain a third sharing value and a fourth sharing value;
determining an element-by-element function result based on the third shared value and the fourth shared value;
splitting the element-by-element function result to obtain a fifth sharing value and a sixth sharing value;
respectively carrying out inverse arrangement on the fifth sharing value and the sixth sharing value to determine the target encryption target data sample data;
the processing the first sharing value and the second sharing value by adopting the target random arrangement respectively to obtain a third sharing value and a fourth sharing value includes:
obtaining a target random overturn vector;
and respectively processing the first sharing value and the second sharing value based on the target random arrangement and the target random turning vector to acquire the third sharing value and the fourth sharing value.
The basic operator layer provided by the invention comprises:
at least one base operator of addition, subtraction, multiplication, transformation shape, and broadcast shape.
As shown in fig. 3, the extraction method of the data feature extraction module provided by the invention is as follows:
s201, acquiring a plurality of groups of target data sample data, and cleaning the plurality of groups of target data sample data; wherein each set of target data sample data comprises target data sample data elements corresponding to a predetermined number of target data sample data attributes, respectively; determining key target data sample data attributes for extracting characteristic target data sample data in the preset target data sample data attributes;
s202, a template vector is established according to a target data sample data element value range of the key target data sample data attribute and a value range of a key target data sample data element of the characteristic target data sample data, wherein the key target data sample data element refers to a target data sample data element corresponding to the key target data sample data attribute in the characteristic target data sample data;
s203, extracting characteristic target data sample data by applying the established template vector to target data sample data elements corresponding to the key target data sample data attributes in the plurality of groups of target data sample data.
The invention provides a method for establishing a template vector according to a target data sample data element value range of a key target data sample data attribute and a value range of a key target data sample data element of characteristic target data sample data, which comprises the following steps:
analyzing the value range of the target data sample data element of the key target data sample data attribute and the value range of the key target data sample data element of the characteristic target data sample data;
establishing a value vector according to the value field of the data elements of the target data sample;
and establishing a template vector according to the value vector and the value range.
The elements in the template vector provided by the invention are in one-to-one correspondence with the elements in the value vector, and the key target data sample data elements refer to target data sample data elements corresponding to key target data sample data attributes in the characteristic target data sample data, and the key target data sample data elements comprise:
forming target data sample data elements corresponding to key target data sample data attributes in the multiple groups of target data sample data into target data sample data vectors, and establishing a one-to-one mapping function of the value fields and the value vectors of the target data sample data elements;
mapping each target data sample data element in the target data sample data vector into an element in a corresponding value vector by using the one-to-one mapping function, and forming a mapping vector by the mapped element;
establishing an extraction vector by using the mapping vector and the corresponding relation between the elements of the value vector and the elements of the template vector;
and extracting characteristic target data sample data from the plurality of groups of target data sample data by using the extraction vector.
2. Application example. In order to prove the inventive and technical value of the technical solution of the present invention, this section is an application example on specific products or related technologies of the claim technical solution.
When the invention works, firstly, a target data sample is collected through a data sample collecting module 1; transmitting the target data sample to the main control module 3 by using a wireless network through the data transmission module 2; secondly, the main control module 3 encrypts the target data sample through the data encryption module 4; extracting data characteristics of the target data sample by a data characteristic extraction module 5; identifying the data characteristics of the target data sample through a data identification module 6; then, classifying the target data sample data according to the recognition result by the data classification module 7; finally, the collected target data sample data and the identification result are displayed through the display module 8.
It should be noted that the embodiments of the present invention can be realized in hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those of ordinary skill in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, 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 device of the present invention and its modules may be implemented by hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., as well as software executed by various types of processors, or by a combination of the above hardware circuitry and software, such as firmware.
3. Evidence of the effect of the examples. The embodiment of the invention has a great advantage in the research and development or use process, and has the following description in combination with data, charts and the like of the test process.
According to the invention, the first sharing value and the second sharing value are processed by adopting a random overturning method based on random arrangement through the data encryption module, so that the randomness is improved, the distribution of each element in the random arrangement is avoided, the data privacy of the target data sample is further protected, and the middle result is prevented from being revealed; meanwhile, the data characteristic extraction module can rapidly extract characteristic target data sample data from a large number of target data sample data without performing a large number of logic judgments, so that the efficiency of extracting the characteristic target data sample data can be effectively improved, and the time for extracting the characteristic target data sample data is saved.
The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the invention is not limited thereto, but any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention will be apparent to those skilled in the art within the scope of the present invention.
Claims (10)
1. An artificial intelligence based pattern recognition integrated service system, comprising:
the device comprises a data sample acquisition module, a data transmission module, a main control module, a data encryption module, a data characteristic extraction module, a data identification module, a data classification module and a display module;
the data sample acquisition module is connected with the data transmission module and is used for acquiring a target data sample; the data sample acquisition module acquisition method comprises the following steps: searching a target data keyword through a searching program, and counting target data to construct a target data set; storing the retrieval target data into a target data set;
the data transmission module is connected with the data sample acquisition module and the main control module and is used for transmitting the target data sample to the main control module through a wireless network; the data transmission module transmission method comprises the following steps: detecting a wireless network signal through a wireless signal detection program, inputting a wireless network account number, connecting a wireless network, and sending collected target data to a main control module through the wireless network for processing;
the main control module is connected with the data transmission module, the data encryption module, the data characteristic extraction module, the data identification module, the data classification module and the display module and used for controlling the normal work of each module;
the data encryption module is connected with the main control module and used for encrypting the target data sample; the data encryption module encryption method comprises the following steps: encrypting target characteristic target data sample data to obtain an initial intermediate result; inputting the initial intermediate result to a basic operator layer, and obtaining target encryption target data sample data output by the basic operator layer;
the data characteristic extraction module is connected with the main control module and is used for extracting data characteristics of the target data sample; the data characteristic extraction module is used for extracting the following steps: determining a key target data sample data attribute; establishing a template vector according to the value range of the target data sample data element of the key target data sample data attribute and the value range of the key target data sample data element of the characteristic target data sample data; extracting characteristic target data sample data by applying the established template vector to target data sample data elements corresponding to key target data sample data attributes in the plurality of sets of target data sample data;
the data identification module is connected with the main control module and used for identifying the data characteristics of the target data sample;
the data classification module is connected with the main control module and is used for classifying the target data sample data according to the identification result;
the display module is connected with the main control module and used for displaying the collected target data sample data and the identification result.
2. The artificial intelligence based pattern recognition integrated service system of claim 1, wherein the data encryption module encryption method is as follows:
(1) Encrypting target characteristic target data sample data to obtain an initial intermediate result; inputting the initial intermediate result to a basic operator layer, and obtaining target encryption target data sample data output by the basic operator layer;
the basic operator layer comprises a linear calculation layer, a target data sample data type conversion layer and a nonlinear element-by-element calculation layer.
3. The artificial intelligence based pattern recognition integrated service system of claim 2, wherein the inputting the initial intermediate result to a base operator layer, obtaining target encrypted target data sample data output by the base operator layer, comprises:
under the condition that the target data sample data type of the initial intermediate result is inconsistent with the target data sample data type, inputting the initial intermediate result to the target data sample data type conversion layer, and acquiring first target data sample data of the target data sample data type output by the target data sample data type conversion layer;
inputting the first target data sample data into the linear calculation layer to obtain first encrypted target data sample data output by the linear calculation layer;
and inputting the first encrypted target data sample data into the nonlinear element-by-element calculation layer, and obtaining the target encrypted target data sample data output by the nonlinear element-by-element calculation layer.
4. The artificial intelligence based pattern recognition integrated service system of claim 2, wherein the inputting the first target data sample data to the linear computing layer, obtaining the first encrypted target data sample data output by the linear computing layer, comprises:
splitting the first target data sample data to obtain at least two subsequences;
the first encrypted target data sample data is determined based on the at least two sub-sequences.
5. The artificial intelligence based pattern recognition integrated service system of claim 2, wherein the determining the first encrypted target data sample data based on the at least two sub-sequences comprises:
obtaining a target multiplication triplet;
the first encrypted target data sample data is determined based on the target multiplication triplet and the at least two sub-sequences.
6. The artificial intelligence based pattern recognition integrated service system of claim 2, wherein the inputting the first encrypted target data sample data into the nonlinear element-by-element calculation layer, obtaining the target encrypted target data sample data output by the nonlinear element-by-element calculation layer, comprises:
acquiring a first sharing value and a second sharing value corresponding to the first encryption target data sample data;
respectively processing the first sharing value and the second sharing value by adopting target random arrangement to obtain a third sharing value and a fourth sharing value;
determining an element-by-element function result based on the third shared value and the fourth shared value;
splitting the element-by-element function result to obtain a fifth sharing value and a sixth sharing value;
respectively carrying out inverse arrangement on the fifth sharing value and the sixth sharing value to determine the target encryption target data sample data;
the processing the first sharing value and the second sharing value by adopting the target random arrangement respectively to obtain a third sharing value and a fourth sharing value includes:
obtaining a target random overturn vector;
and respectively processing the first sharing value and the second sharing value based on the target random arrangement and the target random turning vector to acquire the third sharing value and the fourth sharing value.
7. The artificial intelligence based pattern recognition integrated service system of claim 2, wherein the base operator layer comprises:
at least one base operator of addition, subtraction, multiplication, transformation shape, and broadcast shape.
8. The pattern recognition integrated service system based on artificial intelligence according to claim 1, wherein the data feature extraction module extracts the following:
1) Acquiring a plurality of groups of target data sample data, and cleaning the plurality of groups of target data sample data; wherein each set of target data sample data comprises target data sample data elements corresponding to a predetermined number of target data sample data attributes, respectively; determining key target data sample data attributes for extracting characteristic target data sample data in the preset target data sample data attributes;
2) Establishing a template vector according to a target data sample data element value range of the key target data sample data attribute and a value range of a key target data sample data element of the characteristic target data sample data, wherein the key target data sample data element refers to a target data sample data element corresponding to the key target data sample data attribute in the characteristic target data sample data;
3) And extracting characteristic target data sample data by applying the established template vector to target data sample data elements corresponding to the key target data sample data attributes in the plurality of groups of target data sample data.
9. The artificial intelligence based pattern recognition integrated service system of claim 8, wherein the establishing a template vector from the target data sample data element value range of the key target data sample data attribute and the value range of the key target data sample data element of the feature target data sample data comprises:
analyzing the value range of the target data sample data element of the key target data sample data attribute and the value range of the key target data sample data element of the characteristic target data sample data;
establishing a value vector according to the value field of the data elements of the target data sample;
and establishing a template vector according to the value vector and the value range.
10. The artificial intelligence based pattern recognition integrated service system of claim 8, wherein the elements in the template vector are in one-to-one correspondence with the elements in the value vector, and wherein the key target data sample data elements refer to target data sample data elements in the feature target data sample data corresponding to key target data sample data attributes, comprising:
forming target data sample data elements corresponding to key target data sample data attributes in the multiple groups of target data sample data into target data sample data vectors, and establishing a one-to-one mapping function of the value fields and the value vectors of the target data sample data elements;
mapping each target data sample data element in the target data sample data vector into an element in a corresponding value vector by using the one-to-one mapping function, and forming a mapping vector by the mapped element;
establishing an extraction vector by using the mapping vector and the corresponding relation between the elements of the value vector and the elements of the template vector;
and extracting characteristic target data sample data from the plurality of groups of target data sample data by using the extraction vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310551089.XA CN117194944A (en) | 2023-05-16 | 2023-05-16 | Pattern recognition integrated service system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310551089.XA CN117194944A (en) | 2023-05-16 | 2023-05-16 | Pattern recognition integrated service system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117194944A true CN117194944A (en) | 2023-12-08 |
Family
ID=89002327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310551089.XA Pending CN117194944A (en) | 2023-05-16 | 2023-05-16 | Pattern recognition integrated service system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117194944A (en) |
-
2023
- 2023-05-16 CN CN202310551089.XA patent/CN117194944A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wei et al. | I know what you see: Power side-channel attack on convolutional neural network accelerators | |
| CN108509915B (en) | Method and device for generating face recognition model | |
| CN112766189B (en) | Deep forgery detection method and device, storage medium and electronic equipment | |
| CN108121945A (en) | A kind of multi-target detection tracking, electronic equipment and storage medium | |
| CN108280348B (en) | Android malicious software identification method based on RGB image mapping | |
| US20210200971A1 (en) | Image processing method and apparatus | |
| CN111738199B (en) | Image information verification method, device, computing device and medium | |
| US20190147613A1 (en) | Estimation of human orientation in images using depth information | |
| CN114330565A (en) | Face recognition method and device | |
| CN117036843A (en) | Target detection model training method, target detection method and device | |
| CN109064464B (en) | Method and device for detecting burrs of battery pole piece | |
| CN117953581A (en) | Method and device for identifying actions, electronic equipment and readable storage medium | |
| Talasila et al. | [Retracted] Deep Learning‐Based Leaf Region Segmentation Using High‐Resolution Super HAD CCD and ISOCELL GW1 Sensors | |
| CN115470873B (en) | Radar radiation source identification method and system | |
| CN117194944A (en) | Pattern recognition integrated service system based on artificial intelligence | |
| Adiono et al. | HOG-AdaBoost implementation for human detection employing FPGA ALTERA DE2-115 | |
| CN115225308B (en) | Attack partner identification method for large-scale group attack flow and related equipment | |
| CN116452802A (en) | Vehicle loss detection method, device, equipment and storage medium | |
| CN113542527B (en) | Face image transmission method and device, electronic equipment and storage medium | |
| CN114638359A (en) | Method and device for removing neural network backdoor and image recognition | |
| US11515995B2 (en) | Efficient computation of univariate statistical moments for side channel vulnerability evaluation | |
| CN114090650A (en) | Sample data identification method and device, electronic equipment and storage medium | |
| CN109583590B (en) | Data processing method and data processing device | |
| CN112348060A (en) | Classification vector generation method and device, computer equipment and storage medium | |
| Qi et al. | Fast and efficient face detector based on large kernel attention for CPU device |
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 |