CN113627490B - Operation and maintenance multi-mode decision method and system based on multi-core heterogeneous processor - Google Patents
Operation and maintenance multi-mode decision method and system based on multi-core heterogeneous processor Download PDFInfo
- Publication number
- CN113627490B CN113627490B CN202110798398.8A CN202110798398A CN113627490B CN 113627490 B CN113627490 B CN 113627490B CN 202110798398 A CN202110798398 A CN 202110798398A CN 113627490 B CN113627490 B CN 113627490B
- Authority
- CN
- China
- Prior art keywords
- decision
- content distribution
- data
- distribution matrix
- content
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 107
- 238000012423 maintenance Methods 0.000 title claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 168
- 230000008859 change Effects 0.000 claims abstract description 66
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 187
- 230000000875 corresponding effect Effects 0.000 claims description 60
- 230000005540 biological transmission Effects 0.000 claims description 34
- 230000008569 process Effects 0.000 claims description 32
- 230000001276 controlling effect Effects 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 22
- 230000002596 correlated effect Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 230000006399 behavior Effects 0.000 description 16
- 238000012986 modification Methods 0.000 description 8
- 230000004048 modification Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000000644 propagated effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241000579895 Chlorostilbon Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000010976 emerald Substances 0.000 description 1
- 229910052876 emerald Inorganic materials 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- ZLIBICFPKPWGIZ-UHFFFAOYSA-N pyrimethanil Chemical compound CC1=CC(C)=NC(NC=2C=CC=CC=2)=N1 ZLIBICFPKPWGIZ-UHFFFAOYSA-N 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
According to the operation and maintenance multi-mode decision method and system based on the multi-core heterogeneous processor, the decision content vector is extracted to serve as a historical content vector, and then the target key decision category is subjected to recognition preprocessing according to the historical content vector to obtain the category classification method. When the class division method is used for controlling the decision item errors of the target key decision class, the arrangement mode error change range in the target key decision class can be related to the decision content vectors of the same arrangement mode. The larger content vector can be adjusted in the range, and the smaller content vector can be adjusted in the smaller range of the decision content vector, so that the matching degree of the target key decision category is higher than that of the content of the decision data to be processed. Therefore, decision item errors of each arrangement mode of the target key decision category are respectively adjusted according to the to-be-processed decision data, so that the vector set can be reasonably controlled, and the influence of the to-be-processed decision data on the decision effect of the key decision category is reduced.
Description
Technical Field
The application relates to the technical field of data decision making, in particular to an operation and maintenance multi-mode decision making method and system based on a multi-core heterogeneous processor.
Background
With the continuous progress of information technology, the operation and maintenance multi-mode is processed by a manual decision method in early stage, so that the step of relevant data decision is very slow, and the processing efficiency of relevant data is possibly reduced, thereby bringing bad user experience.
Through the multi-core heterogeneous processor, the efficiency of the related number decision can be effectively improved in the process of continuously increasing the related data volume.
However, there are also some drawbacks in the techniques of correlating data decisions.
Disclosure of Invention
In view of the above, the application provides an operation and maintenance multi-mode decision method and system based on a multi-core heterogeneous processor.
In a first aspect, an operation and maintenance multi-mode decision method based on a multi-core heterogeneous processor is provided, including:
Acquiring decision data to be processed and determining decision content arrangement data of the decision data to be processed; the decision content arrangement data comprise an arrangement mode and a mapping relation of decision content vectors;
Extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the decision content arrangement data;
performing recognition preprocessing on the target key decision category according to the historical content vector to obtain a category classification method; the category classification method comprises a target arrangement mode error change range corresponding to each arrangement mode in the target key decision category;
And controlling decision item errors of the target key decision category according to the category classification method.
Further, controlling decision event errors of the target key decision category according to the category classification method includes:
determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories according to the category dividing method;
determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories, and controlling decision item errors of the target key decision categories according to the target arrangement mode error change range of dividing the current boundary into the target key decision categories; the current boundary divides the target arrangement mode error change range of the target key decision category into an error change interval range;
The error change interval range is an open interval range, the endpoint vector of the error change interval range is a target arrangement mode error change range of the target key decision category divided by the upper boundary, and the current boundary is a target arrangement mode error change range of the target key decision category divided by the current boundary;
according to the decision content arrangement data, extracting corresponding decision content vectors of M target arrangement modes as historical content vectors, wherein the method comprises the following steps:
Normalizing and relating the decision content vector in the decision content arrangement data to a target interval range;
and extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the normalized associated decision content arrangement data.
Further, after controlling the decision item errors of the target key decision category according to the decision content arrangement data, the method further comprises:
identifying global content distribution matrix data when the target key decision categories are classified by using a content distribution matrix identification device; the global content distribution matrix data comprises a content distribution matrix of the target key decision category and decision data to be processed;
judging whether the number of the content distribution matrixes of the global content distribution matrix data is larger than a preset number vector; if yes, executing a first preset step and/or a second preset step; the first preset step is to generate early warning data with an oversized vector set; the second preset step is to reduce decision item errors of the target key decision category.
Further, determining decision content arrangement data of the decision data to be processed includes:
Calculating decision key content of the decision data to be processed;
and executing a feedback vector weighting step of a training model on the decision key content to obtain decision content arrangement data of the decision data to be processed.
Further, the method further comprises the following steps:
acquiring transmission track description data; the transmission track description data are used for describing the interest degree of a content distribution matrix transmitted in a plurality of arrangement modes;
If a vector set control instruction is obtained, determining a vector set control vector corresponding to the target key decision category according to the transmission track description data; the vector set control vector comprises an arrangement mode error change range corresponding to each arrangement mode in the target key decision category, and the arrangement mode error change range is positively correlated with the interest degree of the content distribution matrix of the same arrangement mode;
controlling a decision item error of the target key decision category according to the vector set control vector;
wherein, the acquisition transmission track description data includes:
Dividing boundary line content distribution matrix nodes in sequence, and determining content distribution matrix interestingness data according to operation behavior feedback data; wherein the content distribution matrix interest data includes a number of interest content distribution matrices transmitted to all of the boundary content distribution matrix nodes, the number of interest content distribution matrices being positively correlated with the content distribution matrix interest level;
Taking the number of the content distribution matrixes of the linear relation in the arrangement mode of all the boundary content distribution matrix nodes as the number of the standard content distribution matrixes;
Comparing the number of the standard content distribution matrixes and the number of the interest content distribution matrixes corresponding to the same arrangement mode, and determining the transmission track description data according to the comparison result of the number of the content distribution matrixes;
the determining the content distribution matrix interestingness data according to the operation behavior feedback data comprises the following steps:
If the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is within the expected error range, taking the average vector of the first historical content distribution matrix number and the second historical content distribution matrix number as the interest content distribution matrix number of the target boundary content distribution matrix node; the first historical content distribution matrix quantity is the content distribution matrix quantity corresponding to the operation behavior feedback data obtained in a first process, the second historical content distribution matrix quantity is the content distribution matrix quantity corresponding to the operation behavior feedback data obtained in a second process, the first process is a process of adjusting the content distribution matrix quantity of the boundary content distribution matrix nodes in a small-to-large order, and the second process is a process of adjusting the content distribution matrix quantity of the boundary content distribution matrix nodes in a large-to-small order;
And if the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is not within the expected error range, re-dividing the boundary content distribution matrix nodes, and adjusting the content distribution matrix number of the boundary content distribution matrix nodes so as to determine the new first historical content distribution matrix number and the new second historical content distribution matrix number according to the operation behavior feedback data.
In a second aspect, an operation and maintenance multi-mode decision system based on a multi-core heterogeneous processor is provided, which comprises a data acquisition end and a data processing terminal, wherein the data acquisition end is in communication connection with the data processing terminal, and the data processing terminal is specifically used for:
Acquiring decision data to be processed and determining decision content arrangement data of the decision data to be processed; the decision content arrangement data comprise an arrangement mode and a mapping relation of decision content vectors;
Extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the decision content arrangement data;
performing recognition preprocessing on the target key decision category according to the historical content vector to obtain a category classification method; the category classification method comprises a target arrangement mode error change range corresponding to each arrangement mode in the target key decision category;
And controlling decision item errors of the target key decision category according to the category classification method.
Further, the data processing terminal is specifically configured to:
determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories according to the category dividing method;
determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories, and controlling decision item errors of the target key decision categories according to the target arrangement mode error change range of dividing the current boundary into the target key decision categories; the current boundary divides the target arrangement mode error change range of the target key decision category into an error change interval range;
The error change interval range is an open interval range, the endpoint vector of the error change interval range is a target arrangement mode error change range of the target key decision category divided by the upper boundary, and the current boundary is a target arrangement mode error change range of the target key decision category divided by the current boundary;
the data processing terminal is specifically configured to:
Normalizing and relating the decision content vector in the decision content arrangement data to a target interval range;
and extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the normalized associated decision content arrangement data.
Further, the data processing terminal is specifically configured to:
identifying global content distribution matrix data when the target key decision categories are classified by using a content distribution matrix identification device; the global content distribution matrix data comprises a content distribution matrix of the target key decision category and decision data to be processed;
judging whether the number of the content distribution matrixes of the global content distribution matrix data is larger than a preset number vector; if yes, executing a first preset step and/or a second preset step; the first preset step is to generate early warning data with an oversized vector set; the second preset step is to reduce decision item errors of the target key decision category.
Further, the data processing terminal is specifically configured to:
Calculating decision key content of the decision data to be processed;
and executing a feedback vector weighting step of a training model on the decision key content to obtain decision content arrangement data of the decision data to be processed.
Further, the data processing terminal is specifically configured to:
acquiring transmission track description data; the transmission track description data are used for describing the interest degree of a content distribution matrix transmitted in a plurality of arrangement modes;
If a vector set control instruction is obtained, determining a vector set control vector corresponding to the target key decision category according to the transmission track description data; the vector set control vector comprises an arrangement mode error change range corresponding to each arrangement mode in the target key decision category, and the arrangement mode error change range is positively correlated with the interest degree of the content distribution matrix of the same arrangement mode;
controlling a decision item error of the target key decision category according to the vector set control vector;
the data processing terminal is specifically configured to:
Dividing boundary line content distribution matrix nodes in sequence, and determining content distribution matrix interestingness data according to operation behavior feedback data; wherein the content distribution matrix interest data includes a number of interest content distribution matrices transmitted to all of the boundary content distribution matrix nodes, the number of interest content distribution matrices being positively correlated with the content distribution matrix interest level;
Taking the number of the content distribution matrixes of the linear relation in the arrangement mode of all the boundary content distribution matrix nodes as the number of the standard content distribution matrixes;
Comparing the number of the standard content distribution matrixes and the number of the interest content distribution matrixes corresponding to the same arrangement mode, and determining the transmission track description data according to the comparison result of the number of the content distribution matrixes;
the data processing terminal is specifically configured to:
If the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is within the expected error range, taking the average vector of the first historical content distribution matrix number and the second historical content distribution matrix number as the interest content distribution matrix number of the target boundary content distribution matrix node; the first historical content distribution matrix quantity is the content distribution matrix quantity corresponding to the operation behavior feedback data obtained in a first process, the second historical content distribution matrix quantity is the content distribution matrix quantity corresponding to the operation behavior feedback data obtained in a second process, the first process is a process of adjusting the content distribution matrix quantity of the boundary content distribution matrix nodes in a small-to-large order, and the second process is a process of adjusting the content distribution matrix quantity of the boundary content distribution matrix nodes in a large-to-small order;
And if the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is not within the expected error range, re-dividing the boundary content distribution matrix nodes, and adjusting the content distribution matrix number of the boundary content distribution matrix nodes so as to determine the new first historical content distribution matrix number and the new second historical content distribution matrix number according to the operation behavior feedback data.
According to the operation and maintenance multi-mode decision method and system based on the multi-core heterogeneous processor, decision content arrangement data of the decision data to be processed are determined after the decision data to be processed are obtained, and the decision content arrangement data comprise decision content vectors of each arrangement mode in the decision data to be processed. According to the method, corresponding decision content vectors of M target arrangement modes are extracted as historical content vectors according to the decision content arrangement data, and then the target key decision categories are subjected to recognition pretreatment according to the historical content vectors to obtain the category classification method. Because the category division method comprises a target arrangement mode error change range corresponding to each arrangement mode in the target key decision category, when the category division method is used for controlling the decision item errors of the target key decision category, the arrangement mode error change range corresponding to each arrangement mode in the target key decision category can be related to the decision content vectors of the same arrangement mode. By the control method, the target key decision category can be adjusted to a larger content vector in a larger decision content vector range, and the smaller content vector is adjusted to a smaller decision content vector range, so that the target key decision category has higher matching degree than the content of the decision data to be processed. Therefore, the method and the device respectively adjust the decision item errors of each arrangement mode of the target key decision category according to the to-be-processed decision data, so that the vector set can be reasonably controlled, and the influence of the to-be-processed decision data on the decision effect of the key decision category is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an operation and maintenance multi-mode decision method based on a multi-core heterogeneous processor according to an embodiment of the present application.
Fig. 2 is a block diagram of an operation and maintenance multi-mode decision device based on a multi-core heterogeneous processor according to an embodiment of the present application.
Fig. 3 is a schematic diagram of an operation and maintenance multi-mode decision system based on a multi-core heterogeneous processor according to an embodiment of the present application.
Detailed Description
In order to better understand the above technical solutions, the following detailed description of the technical solutions of the present application is made by using the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and the embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limiting the technical solutions of the present application, and the technical features of the embodiments and the embodiments of the present application may be combined with each other without conflict.
Referring to fig. 1, an operation and maintenance multi-mode decision method based on a multi-core heterogeneous processor is shown, and the method may include the following technical solutions described in steps 100-400.
Step 100, obtaining decision data to be processed and determining decision content arrangement data of the decision data to be processed.
For example, the decision content arrangement data includes a mapping relationship of an arrangement manner and a decision content vector.
And 200, extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the decision content arrangement data.
For example, the historical content vector is used to characterize a historical decision content vector.
And step 300, performing recognition pretreatment on the target key decision category according to the historical content vector to obtain a category classification method.
For example, the category classification method includes a target arrangement error variation range corresponding to each arrangement in the target key decision category.
Step 400, controlling the decision item errors of the target key decision category according to the category classification method.
It can be understood that, when the technical solution described in the above steps 100-400 is executed, decision content arrangement data of the decision data to be processed is determined after the decision data to be processed is obtained, where the decision content arrangement data includes decision content vectors of each arrangement mode in the decision data to be processed. According to the method, corresponding decision content vectors of M target arrangement modes are extracted as historical content vectors according to the decision content arrangement data, and then the target key decision categories are subjected to recognition pretreatment according to the historical content vectors to obtain the category classification method. Because the category division method comprises a target arrangement mode error change range corresponding to each arrangement mode in the target key decision category, when the category division method is used for controlling the decision item errors of the target key decision category, the arrangement mode error change range corresponding to each arrangement mode in the target key decision category can be related to the decision content vectors of the same arrangement mode. By the control method, the target key decision category can be adjusted to a larger content vector in a larger decision content vector range, and the smaller content vector is adjusted to a smaller decision content vector range, so that the target key decision category has higher matching degree than the content of the decision data to be processed. Therefore, the method and the device respectively adjust the decision item errors of each arrangement mode of the target key decision category according to the to-be-processed decision data, so that the vector set can be reasonably controlled, and the influence of the to-be-processed decision data on the decision effect of the key decision category is reduced.
In an alternative embodiment, the inventor finds that when the decision item error of the target critical decision category is controlled according to the category classification method, there is a problem that the change range of the target arrangement error is inaccurate, so that it is difficult to accurately control the decision item error of the target critical decision category, and in order to improve the technical problem, the step of controlling the decision item error of the target critical decision category according to the category classification method described in step 400 may specifically include the following technical schemes described in steps q1 to q 3.
And q1, determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories according to the category dividing method.
And q2, determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories, and controlling decision item errors of the target key decision categories according to the target arrangement mode error change range of dividing the current boundary into the target key decision categories.
Illustratively, the current boundary divides the target arrangement mode error variation range of the target key decision category within an error variation interval range.
And q3, the error change interval range is an open interval range, the endpoint vector of the error change interval range is a target arrangement mode error change range of dividing the target key decision category by the upper boundary, and the current boundary is a target arrangement mode error change range of dividing the target key decision category.
It can be understood that when the technical schemes described in the steps q1 to q3 are executed, the problem of inaccurate variation range of the target arrangement mode error is avoided when the decision item errors of the target key decision category are controlled according to the category dividing method, so that the decision item errors of the target key decision category can be accurately controlled.
In an alternative embodiment, the inventor finds that when the corresponding decision content vectors of the M target arrangements are extracted as the historical content vectors according to the decision content arrangement data, there is a problem that the decision content arrangement data is inaccurate, so that the decision content vectors are difficult to be accurately used as the historical content vectors, and in order to improve the technical problem, the step of extracting the corresponding decision content vectors of the M target arrangements as the historical content vectors according to the decision content arrangement data described in step 200 may specifically include the following technical schemes described in step w1 and step w2.
And step w1, normalizing and relating the decision content vector in the decision content arrangement data to a target interval range.
And step w2, extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the normalized and associated decision content arrangement data.
It can be understood that when the technical schemes described in the above steps w1 and w2 are executed, when the corresponding decision content vectors of the M target arrangements are extracted as the historical content vectors according to the decision content arrangement data, the problem of inaccuracy of the decision content arrangement data is avoided, so that the historical content vectors can be accurately used.
Based on the above-mentioned basis, after the decision item errors of the target key decision category are controlled according to the decision content arrangement data, the following technical schemes described in the steps e 1-e 3 can be further included.
And e1, identifying global content distribution matrix data when the target key decision categories are classified by using a content distribution matrix identification device.
Illustratively, the global content distribution matrix data includes a content distribution matrix of the target key decision category and pending decision data.
Step e2, judging whether the number of the content distribution matrixes of the global content distribution matrix data is larger than a preset number vector; if yes, executing a first preset step and/or a second preset step.
Illustratively, the first preset step generates early warning data with an excessively large vector set.
And e3, the second preset step is to reduce the decision item error of the target key decision category.
It can be appreciated that when the technical schemes described in the steps e1 to e3 are executed, the accuracy of the decision item errors can be effectively improved through the content distribution matrix and the decision data to be processed.
In an alternative embodiment, the inventor finds that when determining the decision content arrangement data of the decision data to be processed, there is a problem that the calculation of the decision key content is unreliable, so that it is difficult to reliably determine the decision content arrangement data of the decision data to be processed, and in order to improve the technical problem, the step of determining the decision content arrangement data of the decision data to be processed described in step 100 may specifically include the following technical solutions described in step r1 and step r 2.
And step r1, calculating the decision key content of the decision data to be processed.
And r2, executing a feedback vector weighting step of a training model on the decision key content to obtain decision content arrangement data of the decision data to be processed.
It can be understood that when the technical schemes described in the above steps r1 and r2 are executed, the problem that the calculation of the decision key content is unreliable is avoided when the decision content arrangement data of the decision data to be processed is determined, so that the decision content arrangement data of the decision data to be processed can be reliably determined.
Based on the above, the technical scheme described in the following steps t1 to t3 can be further included.
And step t1, collecting transmission track description data.
For example, the transmission track description data is used to describe the interest level of the content distribution matrix transmitted in a plurality of arrangements.
And step t2, if a vector set control instruction is obtained, determining a vector set control vector corresponding to the target key decision category according to the transmission track description data.
For example, the vector set control vector includes an arrangement error variation range corresponding to each arrangement in the target key decision category, where the arrangement error variation range is positively correlated with the interest level of the content distribution matrix of the same arrangement.
And t3, controlling the decision item errors of the target key decision category according to the vector set control vector.
It can be appreciated that when the technical scheme described in the above steps t1 to t3 is executed, the instruction is controlled by the vector set, so that the accuracy of the decision item error is improved.
In an alternative embodiment, the inventor finds that when the transmission track description data is collected, there is a problem that the content distribution matrix interestingness data is inaccurate, so that it is difficult to accurately collect the transmission track description data, and in order to improve the technical problem, the step of collecting the transmission track description data described in the step t1 may specifically include the following technical solutions described in the step t 11-the step t 13.
And step t11, dividing boundary line content distribution matrix nodes in turn, and determining content distribution matrix interestingness data according to the operation behavior feedback data.
Illustratively, the content distribution matrix interest data includes a number of interest content distribution matrices transmitted for all of the boundary content distribution matrix nodes, the number of interest content distribution matrices being positively correlated with the content distribution matrix interest level.
And step t12, taking the quantity of the content distribution matrixes of the linear relation of the arrangement mode of all the boundary content distribution matrix nodes as the quantity of the standard content distribution matrixes.
And step t13, comparing the number of the standard content distribution matrixes and the number of the interest content distribution matrixes corresponding to the same arrangement mode, and determining the transmission track description data according to the comparison result of the number of the content distribution matrixes.
It can be understood that when the technical scheme described in the above step t11 to step t13 is executed, the problem of inaccurate interest level data of the content distribution matrix is avoided when the transmission track description data is acquired, so that the transmission track description data can be accurately acquired.
In an alternative embodiment, the inventor finds that when the data is fed back according to the operation behaviors, there is a problem that the predicted error range is inaccurate, so that it is difficult to accurately determine the content distribution matrix interestingness data, and in order to improve the technical problem, the step of determining the content distribution matrix interestingness data according to the operation behaviors described in the step t11 may specifically include the technical solutions described in the following step y1 and step y 2.
And step y1, if the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is within the expected error range, taking the average vector of the first historical content distribution matrix number and the second historical content distribution matrix number as the interest content distribution matrix number of the transmission pair target boundary content distribution matrix node.
The first historical content distribution matrix number is the content distribution matrix number corresponding to the operation behavior feedback data obtained in the first process, the second historical content distribution matrix number is the content distribution matrix number corresponding to the operation behavior feedback data obtained in the second process, the first process is a process of adjusting the content distribution matrix number of the boundary content distribution matrix node in order from small to large, the second process is a process of adjusting the content distribution matrix number of the boundary content distribution matrix node in order from large to small
And y2, if the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is not within the expected error range, re-dividing the boundary content distribution matrix nodes, and adjusting the content distribution matrix number of the boundary content distribution matrix nodes so as to determine the new first historical content distribution matrix number and the new second historical content distribution matrix number according to the operation behavior feedback data.
It can be appreciated that when the technical schemes described in the above steps y1 and y2 are executed, the problem of inaccurate prediction error range is avoided when the data is fed back according to the operation behaviors, so that the interestingness data of the content distribution matrix can be accurately determined.
In a possible embodiment, the inventor finds that, when describing data according to a transmission track, there is a problem that an arrangement mode weight vector is inaccurate, so that it is difficult to accurately determine a vector set control vector corresponding to the target critical decision category, and in order to improve the above technical problem, the step of determining, in step t2, the vector set control vector corresponding to the target critical decision category according to the transmission track description data may specifically include the following technical solutions described in step a1 and step a 2.
And a step a1 of determining an arrangement mode weight vector according to the transmission track description data.
The distribution mode weight vector is a ratio vector of the quantity of the interesting content distribution matrix transmitted in the target distribution mode to the quantity difference of the interesting content distribution matrix, the quantity difference of the interesting content distribution matrix is a difference between the quantity of the first interesting content distribution matrix and the quantity of the second interesting content distribution matrix, the quantity of the first interesting content distribution matrix is the quantity of the interesting content distribution matrix transmitted in the least interesting distribution mode, and the quantity of the second interesting content distribution matrix is the quantity of the interesting content distribution matrix transmitted in the most interesting distribution mode.
And a2, determining the arrangement mode error change range of all the arrangement modes in the target key decision category according to the arrangement mode weight vectors corresponding to all the arrangement modes, and generating a vector set control vector according to the arrangement mode error change range of all the arrangement modes.
Illustratively, the arrangement weight vector is positively correlated with the arrangement error variance.
It can be understood that when the technical schemes described in the steps a1 and a2 are executed, the problem of inaccurate weight vectors in an arrangement mode is avoided when data are described according to a transmission track, so that vector set control vectors corresponding to the target key decision category can be accurately determined.
On the basis of the foregoing, please refer to fig. 2 in combination, there is provided an operation and maintenance multi-mode decision device 200 based on a multi-core heterogeneous processor, which is applied to a data processing terminal, and the device includes:
The arrangement data determining module 210 is configured to obtain decision data to be processed and determine decision content arrangement data of the decision data to be processed; the decision content arrangement data comprise an arrangement mode and a mapping relation of decision content vectors;
The historical content extraction module 220 is configured to extract, according to the decision content arrangement data, corresponding decision content vectors of M target arrangements as historical content vectors;
The category classification recognition module 230 is configured to perform recognition preprocessing on the target key decision category according to the historical content vector to obtain a category classification method; the category classification method comprises a target arrangement mode error change range corresponding to each arrangement mode in the target key decision category;
The item error decision module 240 is configured to control decision item errors of the target key decision category according to the category classification method.
On the basis of the above, referring to fig. 3 in combination, there is shown an operation and maintenance multi-mode decision system 300 based on multi-core heterogeneous processors, including a processor 310 and a memory 320 in communication with each other, where the processor 310 is configured to read and execute a computer program from the memory 320 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 stored which, when run, implements the above method.
In summary, based on the above scheme, decision content arrangement data of the decision data to be processed is determined after the decision data to be processed is acquired, where the decision content arrangement data includes decision content vectors of each arrangement mode in the decision data to be processed. According to the method, corresponding decision content vectors of M target arrangement modes are extracted as historical content vectors according to the decision content arrangement data, and then the target key decision categories are subjected to recognition pretreatment according to the historical content vectors to obtain the category classification method. Because the category division method comprises a target arrangement mode error change range corresponding to each arrangement mode in the target key decision category, when the category division method is used for controlling the decision item errors of the target key decision category, the arrangement mode error change range corresponding to each arrangement mode in the target key decision category can be related to the decision content vectors of the same arrangement mode. By the control method, the target key decision category can be adjusted to a larger content vector in a larger decision content vector range, and the smaller content vector is adjusted to a smaller decision content vector range, so that the target key decision category has higher matching degree than the content of the decision data to be processed. Therefore, the method and the device respectively adjust the decision item errors of each arrangement mode of the target key decision category according to the to-be-processed decision data, so that the vector set can be reasonably controlled, and the influence of the to-be-processed decision data on the decision effect of the key decision category is reduced.
It should be appreciated that the systems and modules thereof 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 then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design 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 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 system of the present application and its modules may be implemented not only with 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., but also with software executed by various types of processors, for example, and with a combination of the above hardware circuitry and software (e.g., firmware).
It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements and adaptations of the application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within the present disclosure, and therefore, such modifications, improvements, and adaptations are intended to be within the spirit and scope of the exemplary embodiments of the present disclosure.
Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.
Furthermore, those skilled in the art will appreciate that the various aspects of the application are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
The computer storage medium may contain a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. 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 through any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or a combination of any of the foregoing.
Computer program code necessary for operation of 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, etc., a conventional programming language such as C language, visualBasic, fortran2003, perl, COBOL2002, PHP, ABAP, dynamic programming languages such as Python, ruby and Groovy, or other programming languages, etc. The program code may execute entirely on the user's computer or 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 form of network, 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 the use of services such as software as a service (SaaS) in a cloud computing environment.
Furthermore, the order in which the elements and sequences are presented, the use of numerical letters, or other designations are used in the application is not intended to limit the sequence of the processes and methods unless specifically recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of example, it is to be understood that such details are merely illustrative 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 included within the spirit and scope of the embodiments of the application. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in order to simplify the description of the present disclosure and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure does not imply that the subject application requires more features than are set forth in the claims. Indeed, less than all of the features of a single embodiment disclosed above.
In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the numbers allow for adaptive variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations in some embodiments for use in determining the breadth of the range, in particular embodiments, the numerical values set forth herein are as precisely as possible.
Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited herein is hereby incorporated by reference in its entirety. Except for the application history file that is inconsistent or conflicting with this disclosure, the file (currently or later attached to this disclosure) that limits the broadest scope of the claims of this disclosure is also excluded. It is noted that the description, definition, and/or use of the term in the appended claims controls the description, definition, and/or use of the term in this application if there is a discrepancy or conflict between the description, definition, and/or use of the term in the appended claims.
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 application. Thus, by way of example, and not limitation, alternative configurations of embodiments of the application may be considered in keeping with the teachings of the application. Accordingly, the embodiments of the present application are not limited to the embodiments explicitly described and depicted herein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (8)
1. The operation and maintenance multi-mode decision method based on the multi-core heterogeneous processor is characterized by comprising the following steps of:
Acquiring decision data to be processed and determining decision content arrangement data of the decision data to be processed; the decision content arrangement data comprise an arrangement mode and a mapping relation of decision content vectors;
Extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the decision content arrangement data;
performing recognition preprocessing on the target key decision category according to the historical content vector to obtain a category classification method; the category classification method comprises a target arrangement mode error change range corresponding to each arrangement mode in the target key decision category;
controlling decision item errors of the target key decision category according to the category dividing method;
wherein controlling decision event errors of the target key decision category according to the category classification method comprises:
determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories according to the category dividing method;
determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories, and controlling decision item errors of the target key decision categories according to the target arrangement mode error change range of dividing the current boundary into the target key decision categories; the current boundary divides the target arrangement mode error change range of the target key decision category into an error change interval range;
The error change interval range is an open interval range, the endpoint vector of the error change interval range is a target arrangement mode error change range of the target key decision category divided by the upper boundary, and the current boundary is a target arrangement mode error change range of the target key decision category divided by the current boundary;
according to the decision content arrangement data, extracting corresponding decision content vectors of M target arrangement modes as historical content vectors, wherein the method comprises the following steps:
Normalizing and relating the decision content vector in the decision content arrangement data to a target interval range;
and extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the normalized associated decision content arrangement data.
2. The method of claim 1, further comprising, after controlling decision event errors for a target critical decision category based on the decision content placement data:
identifying global content distribution matrix data when the target key decision categories are classified by using a content distribution matrix identification device; the global content distribution matrix data comprises a content distribution matrix of the target key decision category and decision data to be processed;
Judging whether the number of the content distribution matrixes of the global content distribution matrix data is larger than a preset number vector; if yes, executing a first preset step and/or a second preset step; the first preset step is to generate early warning data with the largest vector set;
the second preset step is to reduce decision item errors of the target key decision category.
3. The method according to claim 1, wherein determining decision content arrangement data of the decision data to be processed comprises:
Calculating decision key content of the decision data to be processed;
and executing a feedback vector weighting step of a training model on the decision key content to obtain decision content arrangement data of the decision data to be processed.
4. A method according to any one of claims 1 to 3, further comprising:
acquiring transmission track description data; the transmission track description data are used for describing the interest degree of a content distribution matrix transmitted in a plurality of arrangement modes;
If a vector set control instruction is obtained, determining a vector set control vector corresponding to the target key decision category according to the transmission track description data; the vector set control vector comprises an arrangement mode error change range corresponding to each arrangement mode in the target key decision category, and the arrangement mode error change range is positively correlated with the interest degree of the content distribution matrix of the same arrangement mode;
controlling a decision item error of the target key decision category according to the vector set control vector;
wherein, the acquisition transmission track description data includes:
Dividing boundary line content distribution matrix nodes in sequence, and determining content distribution matrix interestingness data according to operation behavior feedback data; wherein the content distribution matrix interest data includes a number of interest content distribution matrices transmitted to all of the boundary content distribution matrix nodes, the number of interest content distribution matrices being positively correlated with the content distribution matrix interest level;
Taking the number of the content distribution matrixes of the linear relation in the arrangement mode of all the boundary content distribution matrix nodes as the number of the standard content distribution matrixes;
Comparing the number of the standard content distribution matrixes and the number of the interest content distribution matrixes corresponding to the same arrangement mode, and determining the transmission track description data according to the comparison result of the number of the content distribution matrixes;
the determining the content distribution matrix interestingness data according to the operation behavior feedback data comprises the following steps:
If the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is within the expected error range, taking the average vector of the first historical content distribution matrix number and the second historical content distribution matrix number as the interesting content distribution matrix number of the transmission pair target boundary content distribution matrix node; the first historical content distribution matrix quantity is the content distribution matrix quantity corresponding to the operation behavior feedback data obtained in a first process, the second historical content distribution matrix quantity is the content distribution matrix quantity corresponding to the operation behavior feedback data obtained in a second process, the first process is a process of adjusting the content distribution matrix quantity of the boundary content distribution matrix nodes in a small-to-large order, and the second process is a process of adjusting the content distribution matrix quantity of the boundary content distribution matrix nodes in a large-to-small order;
And if the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is not within the expected error range, re-dividing the boundary content distribution matrix nodes, and adjusting the content distribution matrix number of the boundary content distribution matrix nodes so as to determine the new first historical content distribution matrix number and the new second historical content distribution matrix number according to the operation behavior feedback data.
5. The operation and maintenance multi-mode decision system based on the multi-core heterogeneous processor is characterized by comprising a data acquisition end and a data processing terminal, wherein the data acquisition end is in communication connection with the data processing terminal, and the data processing terminal is specifically used for:
Acquiring decision data to be processed and determining decision content arrangement data of the decision data to be processed; the decision content arrangement data comprise an arrangement mode and a mapping relation of decision content vectors;
Extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the decision content arrangement data;
performing recognition preprocessing on the target key decision category according to the historical content vector to obtain a category classification method; the category classification method comprises a target arrangement mode error change range corresponding to each arrangement mode in the target key decision category;
controlling decision item errors of the target key decision category according to the category dividing method;
the data processing terminal is specifically configured to:
determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories according to the category dividing method;
determining a target arrangement mode error change range of dividing the current boundary into the target key decision categories, and controlling decision item errors of the target key decision categories according to the target arrangement mode error change range of dividing the current boundary into the target key decision categories; the current boundary divides the target arrangement mode error change range of the target key decision category into an error change interval range;
The error change interval range is an open interval range, the endpoint vector of the error change interval range is a target arrangement mode error change range of the target key decision category divided by the upper boundary, and the current boundary is a target arrangement mode error change range of the target key decision category divided by the current boundary;
the data processing terminal is specifically configured to:
Normalizing and relating the decision content vector in the decision content arrangement data to a target interval range;
and extracting corresponding decision content vectors of M target arrangement modes as historical content vectors according to the normalized associated decision content arrangement data.
6. The system of claim 5, wherein the data processing terminal is specifically configured to:
identifying global content distribution matrix data when the target key decision categories are classified by using a content distribution matrix identification device; the global content distribution matrix data comprises a content distribution matrix of the target key decision category and decision data to be processed;
Judging whether the number of the content distribution matrixes of the global content distribution matrix data is larger than a preset number vector; if yes, executing a first preset step and/or a second preset step; the first preset step is to generate early warning data with the largest vector set; the second preset step is to reduce decision item errors of the target key decision category.
7. The system of claim 5, wherein the data processing terminal is specifically configured to:
Calculating decision key content of the decision data to be processed;
and executing a feedback vector weighting step of a training model on the decision key content to obtain decision content arrangement data of the decision data to be processed.
8. The system according to any of the claims 5 to 7, wherein the data processing terminal is specifically configured to:
acquiring transmission track description data; the transmission track description data are used for describing the interest degree of a content distribution matrix transmitted in a plurality of arrangement modes;
If a vector set control instruction is obtained, determining a vector set control vector corresponding to the target key decision category according to the transmission track description data; the vector set control vector comprises an arrangement mode error change range corresponding to each arrangement mode in the target key decision category, and the arrangement mode error change range is positively correlated with the interest degree of the content distribution matrix of the same arrangement mode;
controlling a decision item error of the target key decision category according to the vector set control vector;
the data processing terminal is specifically configured to:
Dividing boundary line content distribution matrix nodes in sequence, and determining content distribution matrix interestingness data according to operation behavior feedback data; wherein the content distribution matrix interest data includes a number of interest content distribution matrices transmitted to all of the boundary content distribution matrix nodes, the number of interest content distribution matrices being positively correlated with the content distribution matrix interest level;
Taking the number of the content distribution matrixes of the linear relation in the arrangement mode of all the boundary content distribution matrix nodes as the number of the standard content distribution matrixes;
Comparing the number of the standard content distribution matrixes and the number of the interest content distribution matrixes corresponding to the same arrangement mode, and determining the transmission track description data according to the comparison result of the number of the content distribution matrixes;
the data processing terminal is specifically configured to:
If the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is within the expected error range, taking the average vector of the first historical content distribution matrix number and the second historical content distribution matrix number as the interesting content distribution matrix number of the transmission pair target boundary content distribution matrix node; the first historical content distribution matrix quantity is the content distribution matrix quantity corresponding to the operation behavior feedback data obtained in a first process, the second historical content distribution matrix quantity is the content distribution matrix quantity corresponding to the operation behavior feedback data obtained in a second process, the first process is a process of adjusting the content distribution matrix quantity of the boundary content distribution matrix nodes in a small-to-large order, and the second process is a process of adjusting the content distribution matrix quantity of the boundary content distribution matrix nodes in a large-to-small order;
And if the difference between the first historical content distribution matrix number and the second historical content distribution matrix number is not within the expected error range, re-dividing the boundary content distribution matrix nodes, and adjusting the content distribution matrix number of the boundary content distribution matrix nodes so as to determine the new first historical content distribution matrix number and the new second historical content distribution matrix number according to the operation behavior feedback data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110798398.8A CN113627490B (en) | 2021-07-15 | 2021-07-15 | Operation and maintenance multi-mode decision method and system based on multi-core heterogeneous processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110798398.8A CN113627490B (en) | 2021-07-15 | 2021-07-15 | Operation and maintenance multi-mode decision method and system based on multi-core heterogeneous processor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113627490A CN113627490A (en) | 2021-11-09 |
| CN113627490B true CN113627490B (en) | 2024-05-28 |
Family
ID=78379815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110798398.8A Active CN113627490B (en) | 2021-07-15 | 2021-07-15 | Operation and maintenance multi-mode decision method and system based on multi-core heterogeneous processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627490B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780842A (en) * | 2017-01-11 | 2017-05-31 | 张军 | A kind of intelligent travelling crane early warning system prototype based on multinuclear heterogeneous processor |
| CN107329878A (en) * | 2017-07-03 | 2017-11-07 | 上海德衡数据科技有限公司 | A kind of multi-modal decision system prototype of O＆M based on multinuclear heterogeneous processor |
| CN107347064A (en) * | 2017-06-29 | 2017-11-14 | 厦门日华科技股份有限公司 | Cloud computing platform Tendency Prediction method based on neural network algorithm |
| CN108038186A (en) * | 2017-12-11 | 2018-05-15 | 上海齐网网络科技有限公司 | A kind of Internet of Things operating system framework based on multiple agent |
| CN108932135A (en) * | 2018-06-29 | 2018-12-04 | 中国科学技术大学苏州研究院 | The acceleration platform designing method of sorting algorithm based on FPGA |
| CN110001660A (en) * | 2018-12-17 | 2019-07-12 | 蔚来汽车有限公司 | A kind of distributed multi-core heterogeneous system |
| CN110221951A (en) * | 2019-06-05 | 2019-09-10 | 张军 | A kind of multi-modal decision system of O&M based on multi-data processing device |
| CN110706256A (en) * | 2019-09-27 | 2020-01-17 | 杭州博雅鸿图视频技术有限公司 | Detection tracking algorithm optimization method based on multi-core heterogeneous platform |
| CN111880545A (en) * | 2020-02-17 | 2020-11-03 | 李华兰 | Automatic driving device, system, automatic driving decision processing method and device |
| WO2021012524A1 (en) * | 2019-07-24 | 2021-01-28 | 平安科技（深圳）有限公司 | Item supervision method and device, computer equipment and storage medium |
| CN112288027A (en) * | 2020-11-05 | 2021-01-29 | 河北工业大学 | Heterogeneous multi-modal image genetics data feature analysis method |
| CN112419729A (en) * | 2020-11-23 | 2021-02-26 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining decision strategy according to predicted traffic flow |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391450A (en) * | 2017-06-30 | 2017-11-24 | 上海德衡数据科技有限公司 | A kind of multi-modal decision system prototype of O＆M based on GPB algorithms |
| US11924435B2 (en) * | 2020-05-15 | 2024-03-05 | Intel Corporation | High quality advanced neighbor management encoder architecture |
-
2021
- 2021-07-15 CN CN202110798398.8A patent/CN113627490B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780842A (en) * | 2017-01-11 | 2017-05-31 | 张军 | A kind of intelligent travelling crane early warning system prototype based on multinuclear heterogeneous processor |
| CN107347064A (en) * | 2017-06-29 | 2017-11-14 | 厦门日华科技股份有限公司 | Cloud computing platform Tendency Prediction method based on neural network algorithm |
| CN107329878A (en) * | 2017-07-03 | 2017-11-07 | 上海德衡数据科技有限公司 | A kind of multi-modal decision system prototype of O＆M based on multinuclear heterogeneous processor |
| CN108038186A (en) * | 2017-12-11 | 2018-05-15 | 上海齐网网络科技有限公司 | A kind of Internet of Things operating system framework based on multiple agent |
| CN108932135A (en) * | 2018-06-29 | 2018-12-04 | 中国科学技术大学苏州研究院 | The acceleration platform designing method of sorting algorithm based on FPGA |
| CN110001660A (en) * | 2018-12-17 | 2019-07-12 | 蔚来汽车有限公司 | A kind of distributed multi-core heterogeneous system |
| CN110221951A (en) * | 2019-06-05 | 2019-09-10 | 张军 | A kind of multi-modal decision system of O&M based on multi-data processing device |
| WO2021012524A1 (en) * | 2019-07-24 | 2021-01-28 | 平安科技（深圳）有限公司 | Item supervision method and device, computer equipment and storage medium |
| CN110706256A (en) * | 2019-09-27 | 2020-01-17 | 杭州博雅鸿图视频技术有限公司 | Detection tracking algorithm optimization method based on multi-core heterogeneous platform |
| CN111880545A (en) * | 2020-02-17 | 2020-11-03 | 李华兰 | Automatic driving device, system, automatic driving decision processing method and device |
| CN112288027A (en) * | 2020-11-05 | 2021-01-29 | 河北工业大学 | Heterogeneous multi-modal image genetics data feature analysis method |
| CN112419729A (en) * | 2020-11-23 | 2021-02-26 | 北京嘀嘀无限科技发展有限公司 | Method and system for determining decision strategy according to predicted traffic flow |
Non-Patent Citations (3)
| Title |
|---|
| Evaluating mapreduce for multi-core and multiprocessor systems;Bin Ren等;《PPOPP》;20170131;全文 * |
| 基于信息寻觅智能体的网络用户浏览模式研究;张世武, 吴月华, 杨杰, 刘际明;计算机研究与发展;20041116(第11期);全文 * |
| 面向边缘计算的目标追踪应用部署策略研究;张展;张宪琦;左德承;付国栋;;软件学报;20200114(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113627490A (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113378554B (en) | Intelligent interaction method and system for medical information | |
| CN112684396B (en) | Data preprocessing method and system for electric energy meter operation error monitoring model | |
| CN115641176B (en) | Data analysis method and AI system | |
| CN115481197B (en) | Distributed data processing method, system and cloud platform | |
| CN114580495A (en) | Business service information analysis method based on artificial intelligence and server | |
| CN113627490B (en) | Operation and maintenance multi-mode decision method and system based on multi-core heterogeneous processor | |
| CN113626538B (en) | Medical information intelligent classification method and system based on big data | |
| CN113626594B (en) | Operation and maintenance knowledge base establishing method and system based on multiple intelligent agents | |
| CN116204681A (en) | Short video release information detection method, system and cloud platform | |
| CN113630336B (en) | Data distribution method and system based on optical interconnection | |
| CN115512344A (en) | Three-dimensional live-action image recognition processing method and system and cloud platform | |
| CN115457340A (en) | Image recognition processing method and system based on artificial intelligence | |
| CN113609931B (en) | Face recognition method and system based on neural network | |
| CN115079882B (en) | Human-computer interaction processing method and system based on virtual reality | |
| CN113610117B (en) | Underwater sensing data processing method and system based on depth data | |
| CN115409510B (en) | Online transaction security system and method | |
| CN115563153B (en) | Task batch processing method, system and server based on artificial intelligence | |
| CN113643818B (en) | Method and system for integrating medical data based on regional data | |
| CN115756576B (en) | Translation method of software development kit and software development system | |
| CN113590952B (en) | Data center construction method and system | |
| CN114611478B (en) | Information processing method and system based on artificial intelligence and cloud platform | |
| CN114661980B (en) | Webpage data pushing method and system and cloud platform | |
| CN113610123B (en) | Multi-source heterogeneous data fusion method and system based on Internet of things | |
| CN113613252B (en) | 5G-based network security analysis method and system | |
| CN113609362B (en) | Data management method and system based on 5G |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |