CN107330619A - Determine method, device and the computer-readable recording medium of comprehensive evaluation value - Google Patents
Determine method, device and the computer-readable recording medium of comprehensive evaluation value Download PDFInfo
- Publication number
- CN107330619A CN107330619A CN201710522530.6A CN201710522530A CN107330619A CN 107330619 A CN107330619 A CN 107330619A CN 201710522530 A CN201710522530 A CN 201710522530A CN 107330619 A CN107330619 A CN 107330619A
- Authority
- CN
- China
- Prior art keywords
- mrow
- evaluation
- msub
- evaluation index
- time
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 509
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000005496 tempering Methods 0.000 claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 230000002068 genetic effect Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 16
- 239000006185 dispersion Substances 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 12
- 230000010354 integration Effects 0.000 claims description 8
- 238000013519 translation Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims 2
- 238000010606 normalization Methods 0.000 abstract 1
- 238000004891 communication Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002262 irrigation Effects 0.000 description 2
- 238000003973 irrigation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241001347978 Major minor Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013178 mathematical model 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
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 210000004940 nucleus Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000002948 stochastic simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Genetics & Genomics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Physiology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of method, device and computer-readable recording medium for determining comprehensive evaluation value, belong to system comprehensive evaluation technical field.This method includes：Evaluation index value of the n evaluation index of each evaluation object in m evaluation object p time point is obtained, m, n and the p are the natural number more than 1；Evaluation index value to acquisition carries out immeasurable tempering processing, obtains normalizing evaluation index value；Based on the normalization evaluation index value, time dimension weighting weight and space dimension weighting weight, the comprehensive evaluation value of each evaluation object in the m evaluation object is determined by weighted comprehensive computing, time dimension weighting weight is to determine to obtain based on the p time point, and space dimension weighting weight is to determine to obtain using genetic algorithm by dynamic clustering model.The present invention solves the three-dimensional Comprehensive Evaluation Problem of space-time, that is, realizes the comprehensive evaluation value that evaluation object is determined under space-time three-dimensional.
Description
Technical Field
The present invention relates to the field of comprehensive evaluation technology of systems, and in particular, to a method and an apparatus for determining a comprehensive evaluation value, and a computer-readable storage medium.
Background
At present, the comprehensive evaluation technology is widely applied to the fields of drought risk assessment and the like. The comprehensive evaluation technique is a process of integrating a plurality of evaluation index values into one comprehensive evaluation value by a certain mathematical model in order to achieve a certain evaluation purpose.
In the related art, the comprehensive evaluation problems of the current research are roughly divided into two categories: one is to comprehensively evaluate the past, present and future states and development trends of each evaluation index of a certain evaluation object, and is characterized in that comprehensive evaluation is carried out on a single evaluation object based on time-dimensional data. The other type is that the evaluation targets are identified and classified on the basis of comprehensively comparing each evaluation index of a plurality of evaluation targets at a certain time point, and the method is characterized in that comprehensive evaluation is carried out on the plurality of evaluation targets based on space dimensional data.
However, in real life, in addition to the above-mentioned comprehensive evaluation problem, a spatiotemporal stereo comprehensive evaluation problem is also included, in which the state and the trend of each evaluation index of a plurality of evaluation targets at a plurality of time points are comprehensively evaluated, and in this case, how to determine the comprehensive evaluation value of each evaluation target becomes a focus of research.
Disclosure of Invention
In order to solve the problems of the prior art, embodiments of the present invention provide a method, an apparatus, and a computer-readable storage medium for determining a comprehensive evaluation value. The technical scheme is as follows:
in a first aspect, a method for determining a comprehensive evaluation value is provided, the method including:
acquiring the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points, wherein m, n and p are all natural numbers larger than 1;
carrying out non-quantity tempering treatment on the obtained evaluation index value to obtain a normalized evaluation index value;
and determining a comprehensive evaluation value of each evaluation object in the m evaluation objects through weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, wherein the time-dimensional weighted weight is determined based on the p time points, and the space-dimensional weighted weight is determined by a dynamic clustering model and a genetic algorithm.
Optionally, the determining a comprehensive evaluation value of each of the m evaluation objects by a weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight includes:
determining a comprehensive evaluation value of each of the m evaluation objects by the following formula (1) based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight:
wherein u isiA total rating value for the ith rating object among the m rating objects, wkWeighting the time dimension corresponding to the k time point in the p time points, wherein ajWeighting the space dimension corresponding to the jth evaluation index in the n evaluation indexes, wherein y isij(tk) The j evaluation index of the i evaluation object at the k time point tkThe normalized evaluation index value of (1).
Optionally, before determining the comprehensive evaluation value of each of the m evaluation objects by a weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight, the method further includes:
determining a clustering center of an evaluation object by a specified iteration method;
classifying the m evaluation objects based on the determined clustering centers to obtain a plurality of clustering sets, and determining clustering degrees in the clusters according to the clustering sets;
determining inter-class dispersion among the m evaluation objects;
and determining the space dimension weighting weight by adopting a genetic algorithm through the dynamic clustering model based on the intra-class clustering degree and the inter-class dispersion degree.
Optionally, before determining the comprehensive evaluation value of each of the m evaluation objects by a weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight, the method further includes:
determining the time-dimensional weighting based on the p time points by the following equation (2):
wherein, the wkAnd weighting the time dimension corresponding to the kth time point in the p time points.
Optionally, the performing of the non-quantitative tempering treatment on the obtained evaluation index value to obtain a normalized evaluation index value includes:
when the evaluation index of the evaluation object is larger and more excellent, carrying out the non-amount tempering treatment on the obtained evaluation index value through the following formula (3) to obtain a normalized evaluation index value:
when the evaluation index of the evaluation object is smaller and more excellent, carrying out the non-amount tempering treatment on the obtained evaluation index value through the following formula (4) to obtain a normalized evaluation index value:
wherein, said yij(tk) The j-th evaluation index of the i-th evaluation object in the m evaluation objects is at tkNormalized evaluation index value at a point in time, said xij(tk) The j-th evaluation index of the i-th evaluation object is at tkAn evaluation index value at a time point, theThe j-th evaluation index of the m evaluation objects is the minimum evaluation index value in the evaluation index values of p time pointsThe evaluation index value is the largest evaluation index value of the j-th evaluation index of the m evaluation objects in the evaluation index values of p time points, c is a preset translation parameter, d is a preset scaling parameter, and c and d are natural numbers.
In a second aspect, there is provided an apparatus for determining a comprehensive evaluation value, the apparatus including:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points, and m, n and p are all natural numbers larger than 1;
the processing module is used for carrying out non-quantity toughening treatment on the obtained evaluation index value to obtain a normalized evaluation index value;
a first determining module, configured to determine, based on the normalized evaluation index value, the time-dimensional weighting weight, and the space-dimensional weighting weight, a comprehensive evaluation value of each of the m evaluation objects through a weighted comprehensive operation, where the time-dimensional weighting weight is determined based on the p time points, and the space-dimensional weighting weight is determined by a dynamic clustering model using a genetic algorithm.
Optionally, the first determining module is configured to:
determining a comprehensive evaluation value of each of the m evaluation objects by the following formula (1) based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight:
wherein u isiA total rating value for the ith rating object among the m rating objects, wkWeighting the time dimension corresponding to the k time point in the p time points, wherein ajFor the n evaluation fingersThe space dimension corresponding to the jth evaluation index in the index is weighted, and y isij(tk) The j evaluation index of the i evaluation object at the k time point tkThe normalized evaluation index value of (1).
Optionally, the apparatus further comprises:
the second determination module is used for determining the clustering center of the evaluation object by a specified iteration method;
a third determining module, configured to classify the m evaluation objects based on the determined clustering centers to obtain multiple clustering sets, and determine an intra-clustering degree according to the multiple clustering sets;
a fourth determining module, configured to determine inter-class dispersion among the m evaluation objects;
and the fifth determining module is used for determining the space dimension weighting weight by adopting a genetic algorithm through the dynamic clustering model based on the intra-class clustering degree and the inter-class dispersion degree.
Optionally, the apparatus further comprises:
a sixth determining module, configured to determine the time-dimensional weighting weight according to the following formula (2) based on the p time points:
wherein, the wkAnd weighting the time dimension corresponding to the kth time point in the p time points.
In a third aspect, a computer-readable storage medium is provided, in which at least one instruction is stored, and the instruction is loaded and executed by a processor to implement the method for determining a comprehensive evaluation value according to the first aspect.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
and acquiring the evaluation index values of the n evaluation indexes of each of the m evaluation objects at p time points, and carrying out non-quantity tempering treatment on the acquired evaluation index values to obtain normalized evaluation index values in order to prevent data distortion. Then, based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, a comprehensive evaluation value of each of the m evaluation objects is determined through weighted comprehensive operation, so that the space-time three-dimensional comprehensive evaluation problem is solved, namely, the comprehensive evaluation value of the evaluation object is determined in the space-time three-dimensional dimension.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart illustrating a method of determining a comprehensive evaluation value according to an exemplary embodiment.
Fig. 2 is a flowchart illustrating a method of determining a comprehensive evaluation value according to another exemplary embodiment.
Fig. 3 is a flowchart illustrating a method of determining a comprehensive evaluation value according to another exemplary embodiment.
Fig. 4A is a schematic structural diagram illustrating an apparatus for determining a comprehensive evaluation value according to an exemplary embodiment.
Fig. 4B is a schematic structural diagram illustrating another apparatus for determining a comprehensive evaluation value according to an exemplary embodiment.
Fig. 4C is a schematic structural diagram illustrating another apparatus for determining a comprehensive evaluation value according to an exemplary embodiment.
Fig. 5 is a block diagram illustrating an apparatus 500 for determining a comprehensive evaluation value according to an exemplary embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Before describing the embodiments of the present invention in detail, the terms and environments related to the embodiments of the present invention will be briefly described.
First, the terms related to the embodiments of the present invention are briefly described:
intra-class degree of aggregation:in order to indicate the degree of concentration between evaluation objects belonging to the same class, it is generally desirable that the samples within the class be concentrated as much as possible.
Degree of dispersion between classes:in order to indicate the degree of dispersion between evaluation objects, it is generally desirable that samples between classes be dispersed as much as possible.
Genetic algorithm:the method is an intelligent optimization algorithm for simulating a biological major-minor elimination rule and a population internal chromosome information exchange mechanism, has good performance verified in theory and practice, and can be used for solving a complex nonlinear optimization problem.
Next, a brief description is given of an implementation environment related to the embodiments of the present invention. The method for determining the comprehensive evaluation value according to the embodiment of the present invention may be executed by a terminal, which may be a terminal such as a computer or a tablet computer, and is not limited in this respect.
Next, a method of determining a comprehensive evaluation value according to an embodiment of the present invention will be described in detail by the embodiments shown in fig. 1, 2, and 3, respectively.
Fig. 1 is a flowchart illustrating a method for determining a comprehensive evaluation value according to an exemplary embodiment, which may include the following steps:
step 101: and acquiring the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points, wherein m, n and p are all natural numbers larger than 1.
Step 102: carrying out non-quantity tempering treatment on the obtained evaluation index value to obtain a normalized evaluation index value;
step 103: and determining a comprehensive evaluation value of each evaluation object in the m evaluation objects through weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, wherein the time-dimensional weighted weight is determined based on the p time points, and the space-dimensional weighted weight is determined by a dynamic clustering model and a genetic algorithm.
In the embodiment of the invention, the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points are acquired, and in order to prevent data distortion, the acquired evaluation index values are subjected to non-quantity tempering treatment to obtain normalized evaluation index values. Then, based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, a comprehensive evaluation value of each of the m evaluation objects is determined through weighted comprehensive operation, so that the problem of comprehensive evaluation of space-time stereo is solved, namely, the comprehensive evaluation value of the evaluation object is determined in the space-time stereo dimension.
Alternatively, determining a comprehensive evaluation value of each of the m evaluation objects by a weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight includes:
based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight, a comprehensive evaluation value of each of the m evaluation objects is determined by the following formula (1):
wherein u isiIs the integrated evaluation value of the ith evaluation object in the m evaluation objects, wkWeighting the time dimension corresponding to the kth time point in the p time points, the ajWeighting the space dimension corresponding to the jth evaluation index of the n evaluation indexes, yij(tk) The j-th evaluation index of the i-th evaluation object at the k-th time point tkThe normalized evaluation index value of (1).
Optionally, before determining the comprehensive evaluation value of each of the m evaluation objects by a weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight, the method further includes:
determining a clustering center of an evaluation object by a specified iteration method;
classifying the m evaluation objects based on the determined clustering centers to obtain a plurality of clustering sets, and determining clustering degrees in the clusters according to the clustering sets;
determining inter-class dispersion among the m evaluation objects;
and determining the space dimension weighting weight by adopting a genetic algorithm through the dynamic clustering model based on the intra-class clustering degree and the inter-class dispersion degree.
Optionally, before determining the comprehensive evaluation value of each of the m evaluation objects by a weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight, the method further includes:
based on the p time points, the time-dimensional weighting weight is determined by the following equation (2):
wherein, the wkAnd weighting the time dimension corresponding to the kth time point in the p time points.
Optionally, performing an infinite tempering treatment on the obtained evaluation index value to obtain a normalized evaluation index value, including:
when the evaluation index of the evaluation object is larger and more excellent, carrying out the non-amount tempering treatment on the obtained evaluation index value through the following formula (3) to obtain a normalized evaluation index value:
when the evaluation index of the evaluation object is smaller and more excellent, carrying out the non-amount tempering treatment on the obtained evaluation index value through the following formula (4) to obtain a normalized evaluation index value:
wherein y isij(tk) The j-th evaluation index of the i-th evaluation object in the m evaluation objects is at tkNormalized evaluation index value of time point, xij(tk) The j-th evaluation index of the i-th evaluation object is at tkAn evaluation index value at a time point of the measurement of theThe j-th evaluation index of the m evaluation objects is the minimum evaluation index value in the evaluation index values of p time pointsThe j-th evaluation index of the m evaluation objects is the maximum evaluation index value in the evaluation index values of p time points, and c is a preset evaluation index valueAnd d is a preset scaling parameter, and c and d are natural numbers.
All the above optional technical solutions can be combined arbitrarily to form an optional embodiment of the present invention, which is not described in detail herein.
Fig. 2 is a flowchart illustrating a method for determining a comprehensive evaluation value according to another exemplary embodiment, which is exemplified by applying the method for determining a comprehensive evaluation value to a terminal, and the method for determining a comprehensive evaluation value may include the following steps:
step 201: and acquiring the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points, wherein m, n and p are natural numbers larger than 1.
In actual life, various complex system comprehensive evaluation problems exist in different industries, and the evaluation problems cannot be evaluated by adopting a single evaluation index, and generally an evaluation index system is established by n evaluation indexes to carry out comprehensive evaluation. In the embodiment of the present invention, it is assumed that an index system established for a certain type of evaluation problem is composed of n evaluation indexes, m evaluation objects to be subjected to cluster analysis are provided, each evaluation index has evaluation index values at p time points, and an evaluation index matrix X ═ X (X) with spatiotemporal stereo properties can be obtainedij(tk))m×n×pWherein x in the evaluation index matrixij(tk) The j-th evaluation index of the i-th evaluation object is at tkAn evaluation index value at a time point.
In an actual implementation, the evaluation index values of the n evaluation indexes of each of the m evaluation objects at p time points may be stored in the terminal by a user in advance, so that the terminal may locally obtain the evaluation index values of the n evaluation indexes of each of the m evaluation objects at p time points.
Of course, in another possible implementation manner, the evaluation index values of the n evaluation indexes of each of the m evaluation objects at p time points may also be stored in other devices, and the other devices have a connection relationship with the terminal. In this case, the terminal may acquire the evaluation index values of the n evaluation indexes of each of the m evaluation objects at p points in time from other devices having a connection relationship with itself.
Step 202: and carrying out non-quantity tempering treatment on the obtained evaluation index value to obtain a normalized evaluation index value.
For an evaluation index matrix with space-time three-dimensional properties, in order to prevent the problem of data distortion caused by consistent non-dimensional tempering treatment, the embodiment of the invention uniformly performs dimensionless quantization treatment on the data of evaluation index values in the evaluation index matrix at different time points.
In the specific implementation, according to different effects of the evaluation index on the evaluation object, the specific implementation manner of performing the non-quantitative tempering treatment on the obtained evaluation index value is also different, and specifically may include the following two cases:
in the first case: when the evaluation index of the evaluation object is larger and more excellent, carrying out the non-amount tempering treatment on the obtained evaluation index value through the following formula (3) to obtain a normalized evaluation index value:
wherein y isij(tk) The j-th evaluation index of the i-th evaluation object in the m evaluation objects is at tkNormalized evaluation index value of time point, xij(tk) The j-th evaluation index of the i-th evaluation object is at tkAn evaluation index value at a time point of the measurement of theThe j-th evaluation index of the m evaluation objects is the minimum evaluation index value in the evaluation index values of p time pointsThe j-th evaluation index of the m evaluation objects is the maximum evaluation index value in the evaluation index values of p time points, c is a preset translation parameter, d is a preset scaling parameter, and c and d are natural numbers.
In the second case: when the evaluation index of the evaluation object is smaller and more excellent, carrying out the non-amount tempering treatment on the obtained evaluation index value through the following formula (4) to obtain a normalized evaluation index value:
after the acquired evaluation index value is subjected to the non-quantitative tempering treatment, a normalized evaluation index matrix Y with space-time three-dimensional properties is obtained (Y)ij(tk))m×n×pWherein y in the normalized evaluation index matrix with space-time stereo propertyij(tk) To normalize the evaluation index value.
In practical implementation, c and d may be set by a user according to actual requirements, for example, if the model involved in the calculation process is too small, the model involved may be amplified by setting the value of amplification d.
In addition, for the sake of easy understanding, the symbols referred to in the above formulas are simply described, where "/" represents division, "+" represents addition, "-" represents subtraction, and "+" represents multiplication.
Step 203: a time-dimensional weighting weight is determined based on the p time points.
In the embodiment of the invention, the comprehensive evaluation problem of the space-time stereo is solved, namely the timeliness of each evaluation index needs to be considered, so that the time-dimension weighting weight needs to be determined.
In a specific implementation, the terminal determines the time-dimensional weighting weight based on the p time points by the following formula (2):
wherein, the wkAnd weighting the time dimension corresponding to the kth time point in the p time points.
In addition, for the sake of easy understanding, the notation related to the above formula is briefly described here, where "exp" represents an exponential function with a natural number e as the base.
It should be noted that, here, a case that each evaluation index value in the spatio-temporal stereo comprehensive evaluation problem has a time preference is taken as an example for explanation, that is, when each evaluation index value in the spatio-temporal stereo comprehensive evaluation problem has a time preference, the terminal determines the time-dimensional weighting weight through the above formula (2) based on the p time points. In another embodiment, if each evaluation index value in the spatio-temporal stereo comprehensive evaluation problem has no time preference, the time-dimensional weighting weight may be determined by using objective weighting methods such as information entropy, pull-up level, and the like, which is not limited in the embodiment of the present invention.
It should be further noted that, in the actual implementation process, the step 203 is implemented just before the step 204, but there is actually no execution order between the step 203 and the above-mentioned steps 201 and 202.
Step 204: and determining the comprehensive evaluation value of each evaluation object in the m evaluation objects through weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, wherein the space-dimensional weighted weight is determined by a dynamic clustering model and a genetic algorithm.
In a specific implementation, based on the normalized evaluation index value, the time-dimensional weighted weight, and the spatial-dimensional weighted weight, a comprehensive evaluation value of each of the m evaluation objects is determined by the following formula (1):
wherein u isiIs the integrated evaluation value of the ith evaluation object in the m evaluation objects, wkWeighting the time dimension corresponding to the kth time point in the p time points, the ajWeighting the space dimension corresponding to the jth evaluation index of the n evaluation indexes, yij(tk) The j-th evaluation index of the i-th evaluation object at the k-th time point tkThe normalized evaluation index value of (1).
In addition, for the convenience of understanding, the partial symbols related to the above formula are briefly described, wherein the above "." represents multiplication.
In the embodiment of the invention, two times of weighted integration of space and time dimensions are required to be carried out on the time-space stereo data, in the process of comprehensive evaluation, because trend analysis and cluster analysis are also required to be carried out on the comprehensive evaluation result of the past year, in order to prevent that the space weighted integration may cause pollution to each index data after the time-dimension weighted integration, the space weighted integration is firstly carried out on the evaluation index value of each evaluation object, and then the time-dimension weighted integration is carried out, as shown in the formula (1). In this way, a total evaluation value sequence of U ═ U (U) can be obtained1,u2,u3,...,um)。
Further, before determining the integrated evaluation value of each of the m evaluation objects by a weighted integration operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight, it is necessary to determine the space-dimensional weighted weight. The embodiment of the invention mainly determines the space dimension weighting weight by adopting a genetic algorithm through a dynamic clustering model, and the specific implementation of the embodiment of the invention can comprise the following implementation steps (1) to (4):
(1) determining a clustering center of an evaluation object by a specified iteration method;
in a specific implementation, the specific implementation of determining the clustering center of the evaluation object by using the specified iteration method may include the following implementation steps of:
firstly, determining a clustering number M according to the actual condition or the actual requirement of comprehensive evaluation, wherein the value range of M is (M is more than or equal to 2 and less than or equal to M).
② randomly selecting M points as initial poly core, and marking as
Typically, the M points may be randomly generated by a random pattern algorithm.
③ according to L0The above-mentioned comprehensive evaluation value sequence is set to "U" ((U))1,u2,u3,...,um) Points in (1) are classified into M classes, which are denoted asWherein,represents a set of h-th class rating objects, wherein,to a comprehensive evaluation value uiAbsolute distance from the initial h-class center of the poly core.
It should be noted that, during the initial iteration, n spatial-dimensional weighting weights a ═ can be randomly generated by a stochastic simulation algorithm (a ═ is1,a2,...,an) And determining a set of comprehensive evaluation values based on the n randomly generated space-dimensional weighted weights, so as to utilize each comprehensive evaluation value u in the determined set of comprehensive evaluation valuesiThe absolute distance to the initial h-class center of the poly core is determined.
④ consists of theta0Starting, calculating a new coreWherein,is composed ofClass u of classiAverage value of the respective comprehensive evaluation values.
⑤ reclassifying the m evaluative objects according to step ③ and determining new nuclei according to step ④ untilWill be currently determinedAnd determining a cluster center as an evaluation object, wherein the cluster center is a preset small enough allowable error value.
(2) Classifying the m evaluation objects based on the determined clustering centers to obtain a plurality of clustering sets, and determining clustering degrees in the clusters according to the clustering sets;
after the cluster center of the evaluation objects is determined, the m evaluation objects are classified according to the cluster center based on the first step. In a specific implementation, the terminal may determine the intra-class aggregation degree according to the plurality of cluster sets by the following formula (5):
wherein l (u)i-uj) Indicating the absolute distance between the objects under evaluation i and i.
(3) Determining inter-class dispersion among the m evaluation objects;
in a specific implementation, the inter-class dispersion among the m evaluation objects can be determined by the following formula (6):
(4) and determining the space dimension weighting weight by adopting a genetic algorithm through the dynamic clustering model based on the intra-class clustering degree and the inter-class dispersion degree.
The aim of dynamic clustering model building is to select the optimal spatial dimension projection direction, i.e. to select the optimal spatial dimension weighting weight a ═1,a2,...,an) The intra-class samples are concentrated as much as possible, and the inter-class samples are scattered as much as possible, so the projection index for establishing the dynamic clustering model can be expressed as shown in formula (7):
QQ(a)＝SS(a)-DD(a) (7)
and then, carrying out optimization solution on the dynamic clustering model. In a specific implementation, the optimal projection direction is estimated by the following equation (8), namely:
where s.t | | a | | | | 1 represents a constraint condition, that is, in the embodiment of the present invention, the constraint condition that makes the qq (a) the largest is that the modulus of the spatial dimension weighting weight is 1.
After the spatial dimension weighting weight is determined through the above process, the spatial dimension weighting weight is substituted into the above formula (1), and thus the comprehensive evaluation value of each evaluation object in the m evaluation objects can be determined.
In addition, after the spatial dimension weighting weight is substituted into the step (1), clustering division and trend analysis can be performed on the m evaluation objects. That is, the embodiment of the present invention further realizes the functions of trend analysis and cluster division.
In the embodiment of the invention, the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points are acquired, and in order to prevent data distortion, the acquired evaluation index values are subjected to non-quantity tempering treatment to obtain normalized evaluation index values. Then, based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, a comprehensive evaluation value of each of the m evaluation objects is determined through weighted comprehensive operation, so that the space-time three-dimensional comprehensive evaluation problem is solved, namely, the comprehensive evaluation value of the evaluation object is determined in the space-time three-dimensional dimension.
For easy understanding, the practical application of the embodiment of the present invention will be briefly described below by taking the evaluation of drought risks in 3, 4 counties in a certain area of a certain province as an example. Referring to fig. 3, fig. 3 is a flowchart illustrating a method of determining a comprehensive evaluation value according to another exemplary embodiment. The method for determining the comprehensive evaluation value may be executed by a terminal, and may include the following implementation steps:
step 301: evaluation index values of 10 evaluation indexes of each of the 7 evaluation objects at 4 time points are acquired.
Wherein the 7 evaluation objects are 3 cities and 4 counties of a certain region of a certain province, for example, the 3 cities and 4 counties are P1、P2、P3、P4、P5、P6And P7. The 10 evaluation indexes can be respectively drought strength C1Duration of drought C2Population density C3First industrial ratio C4Daily water consumption for everyone C5Cold tolerance of crops C6Water demand C of ten thousand yuan GDP (Gross domestic product)7Effective irrigation rate C8Electromechanical well number C9Homo GDPC10. The data are evaluation index values at 4 time points from 2004 to 2007.
Wherein, the above-mentioned C1And C2The drought disaster-causing factor can be obtained by performing characteristic analysis on drought factor observation data such as rainfall, evaporation capacity, soil moisture content and the like of an evaluation area in the past year, and the data of each part of the drought disaster-causing factor are the same as the data expected in the past year due to the drought risk obtained by the characteristic analysis. C above3、C4、C5、C8And C10The data can be obtained from a statistical yearbook of a certain province. C above7Data from Water resources bulletin, above C9Data from a countryside annual survey of a certain province, above C6Usually expressed in terms of stage moisture sensitivity index, which is calculated using statistical yearbook and agricultural sector data.
Step 302: and carrying out non-quantity tempering treatment on the obtained evaluation index value to obtain a normalized evaluation index value.
In the embodiment of the present invention, each obtained evaluation index in the comprehensive evaluation index system for drought risk is subjected to non-quantitative tempering treatment according to formula (3) in the embodiment of fig. 2, so that all evaluation indexes are converted into a larger and more optimal type, and the obtained normalized evaluation index value is shown in table 1.
TABLE 1
Step 303: a time-dimensional weighting weight is determined based on the 4 time points.
In the embodiment of the present invention, 4 years of evaluation index values are included, so that k is 1, 2, 3, and 4, and the specific implementation process thereof may refer to step 203 in the above embodiment of fig. 2, which is not repeated herein.
Step 304: and determining the comprehensive evaluation value of each evaluation object in the 7 evaluation objects through weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, wherein the space-dimensional weighted weight is determined by a dynamic clustering model and a genetic algorithm.
Let the spatial dimension weight be a ═ a1,a2,...,an) The spatial dimension weighting can be obtained by performing optimization solution through several implementation steps (1) to (4) in the embodiment of fig. 2.
That is, first, a clustering center of an evaluation object is determined by a designated iteration method, and in the embodiment of the present invention, cities and counties in a certain area of a certain city are divided into three categories according to a drought risk comprehensive requirement: dangerous, dangerous and non-dangerous, i.e. M is 3, and 3 points are randomly selected as initial clustering, and the clustering center is determined by the iterative process of the third and fourth embodiments in fig. 2. For example, the cluster center is: (5.775,9.296,15.070),
then, the m evaluation objects are classified based on the determined clustering centers to obtain a plurality of clustering sets, and the intra-class clustering degree is determined according to the plurality of clustering sets. For example, the cluster set corresponding to cluster center 5.775 includes P1And P7The cluster set corresponding to the cluster center 9.296 includes P2And P3The cluster set corresponding to the cluster center 15.070 includes P4、P5And P6。
Finally, the spatial dimension weighting is determined according to the above steps (3) to (4), and the obtained spatial dimension weighting is, for example, a ═ 0.453,0.316,0.198,0.036,0.209,0.117,0.019,0.446,0.617,0.130 }.
After the spatial dimension weighting weight is determined, the determined spatial dimension weighting weight is substituted into the formula (1), and thus the comprehensive evaluation indexes of each city and county can be determined as shown in table 2.
TABLE 2
| Year of year | P1 | P2 | P3 | P4 | P5 | P6 | P7 |
| 2004 | 0.803 | 2.208 | 1.820 | 1.238 | 1.112 | 1.240 | 0.554 |
| 2005 | 1.115 | 2.187 | 1.806 | 1.258 | 1.115 | 1.297 | 0.612 |
| 2006 | 0.688 | 2.240 | 1.585 | 1.235 | 1.193 | 1.280 | 0.612 |
| 2007 | 0.870 | 2.153 | 1.852 | 1.216 | 1.236 | 1.305 | 0.555 |
| Comprehensive evaluation value | 6.570 | 16.701 | 13.429 | 9.394 | 8.983 | 9.800 | 4.442 |
| Clustering results | Danger of | Without danger | Without danger | Is relatively dangerous | Is relatively dangerous | Is relatively dangerous | Danger of |
From the results of this comprehensive evaluation, it can be seen that P7The area is in the most serious state of drought comprehensive risk, and P is the second place1Region, and P2The region is relatively low in comprehensive evaluation risk of drought. In addition, as can be seen from the above-mentioned clustering, the cluster set includes P1And P7The drought risk of the region is serious, and the cluster set comprises P4、P5And P6The drought risk of the region is next to P1And P7And (4) regions. P comprised by the set of clusters2And P3The drought risk degree of the area is relatively small.
In addition, as can be seen from table 2, the change trend of drought risks in 3 cities and 4 counties in a certain region of a certain province is not obvious in recent years, and only P is5The comprehensive evaluation value of the region has a remarkable increasing trend, which shows that the drought risk of the region has a decreasing trend. By making P pairs5As can be seen from the analysis of the evaluation index values of the regions, P has recently been observed5In the area, under the condition that other indexes are not changed much, evaluation indexes such as the first industry proportion, the cold tolerance of crops, the effective irrigation rate, the number of electromechanical wells, the man-average GDP and the like are developed towards the favorable direction.
In the embodiment of the invention, the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points are acquired, and in order to prevent data distortion, the acquired evaluation index values are subjected to non-quantity tempering treatment to obtain normalized evaluation index values. Then, based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, a comprehensive evaluation value of each of the m evaluation objects is determined through weighted comprehensive operation, so that the space-time three-dimensional comprehensive evaluation problem is solved, namely, the comprehensive evaluation value of the evaluation object is determined in the space-time three-dimensional dimension.
Fig. 4A is a schematic structural diagram illustrating an apparatus for determining a comprehensive evaluation value, which may be implemented by software, hardware, or a combination of both, according to an exemplary embodiment. The means for determining the comprehensive evaluation value may include:
an obtaining module 401, configured to obtain evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points, where m, n, and p are all natural numbers greater than 1;
a processing module 402, configured to perform non-quantitative tempering processing on the obtained evaluation index value to obtain a normalized evaluation index value;
a first determining module 403, configured to determine, based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight, a comprehensive evaluation value of each of the m evaluation objects through a weighted comprehensive operation, where the time-dimensional weighted weight is determined based on the p time points, and the space-dimensional weighted weight is determined by using a genetic algorithm through a dynamic clustering model.
Optionally, the first determining module 403 is configured to:
determining a comprehensive evaluation value of each of the m evaluation objects by the following formula (1) based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight:
wherein u isiA total rating value for the ith rating object among the m rating objects, wkWeighting the time dimension corresponding to the k time point in the p time points, wherein ajWeighting the space dimension corresponding to the jth evaluation index in the n evaluation indexes, wherein y isij(tk) The j evaluation index of the i evaluation object at the k time point tkThe normalized evaluation index value of (1).
Optionally, referring to fig. 4B, the apparatus further includes:
a second determining module 404, configured to determine a clustering center of the evaluation object by using a specified iteration method;
a third determining module 405, configured to classify the m evaluation objects based on the determined clustering centers to obtain multiple clustering sets, and determine a clustering degree according to the multiple clustering sets;
a fourth determining module 406, configured to determine inter-class dispersion among the m evaluation objects;
a fifth determining module 407, configured to determine the spatial dimension weighted weight by using a genetic algorithm through the dynamic clustering model based on the intra-class aggregation degree and the inter-class dispersion degree.
Optionally, referring to fig. 4C, the apparatus further includes:
a sixth determining module 408, configured to determine the time-dimensional weighting weight according to the following formula (2) based on the p time points:
wherein, the wkAnd weighting the time dimension corresponding to the kth time point in the p time points.
In the embodiment of the invention, the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points are acquired, and in order to prevent data distortion, the acquired evaluation index values are subjected to non-quantity tempering treatment to obtain normalized evaluation index values. Then, based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, a comprehensive evaluation value of each of the m evaluation objects is determined through weighted comprehensive operation, so that the space-time three-dimensional comprehensive evaluation problem is solved, namely, the comprehensive evaluation value of the evaluation object is determined in the space-time three-dimensional dimension.
It should be noted that: the device for determining a comprehensive evaluation value provided in the above embodiment is only illustrated by the division of the above functional modules when implementing the method for determining a comprehensive evaluation value, and in practical applications, the above function allocation may be performed by different functional modules according to needs, that is, the internal structure of the apparatus may be divided into different functional modules to perform all or part of the above described functions. In addition, the apparatus for determining a comprehensive evaluation value and the method for determining a comprehensive evaluation value provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Fig. 5 is a block diagram illustrating an apparatus 500 for determining a comprehensive evaluation value according to an exemplary embodiment. For example, the apparatus 500 may be a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
Referring to fig. 5, the apparatus 500 may include one or more of the following components: processing component 502, memory 504, power component 506, multimedia component 508, audio component 510, input/output (I/O) interface 512, sensor component 514, and communication component 516.
The processing component 502 generally controls overall operation of the device 500, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 502 may include one or more processors 520 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 502 can include one or more modules that facilitate interaction between the processing component 502 and other components. For example, the processing component 502 can include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.
The memory 504 is configured to store various types of data to support operations at the apparatus 500. Examples of such data include instructions for any application or method operating on device 500, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 504 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The power supply component 506 provides power to the various components of the device 500. The power components 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power supplies for the apparatus 500.
The multimedia component 508 includes a screen that provides an output interface between the device 500 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 500 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 510 is configured to output and/or input audio signals. For example, audio component 510 includes a Microphone (MIC) configured to receive external audio signals when apparatus 500 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 504 or transmitted via the communication component 516. In some embodiments, audio component 510 further includes a speaker for outputting audio signals.
The I/O interface 512 provides an interface between the processing component 502 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the device 500. For example, the sensor assembly 514 may detect an open/closed state of the apparatus 500, the relative positioning of the components, such as a display and keypad of the apparatus 500, the sensor assembly 514 may also detect a change in the position of the apparatus 500 or a component of the apparatus 500, the presence or absence of user contact with the apparatus 500, orientation or acceleration/deceleration of the apparatus 500, and a change in the temperature of the apparatus 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 514 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 516 is configured to facilitate communication between the apparatus 500 and other devices in a wired or wireless manner. The apparatus 500 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 516 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 516 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 500 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the method of determining a comprehensive evaluation value as shown in fig. 1, 2 or 3 described above.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 504 comprising instructions, executable by the processor 520 of the apparatus 500 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
A non-transitory computer-readable storage medium, wherein instructions, when executed by a processor of a mobile terminal, enable the mobile terminal to perform the method of determining a comprehensive evaluation value as shown in fig. 1, 2 or 3 above.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method of determining a composite evaluation value, the method comprising:
acquiring the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points, wherein m, n and p are all natural numbers larger than 1;
carrying out non-quantity tempering treatment on the obtained evaluation index value to obtain a normalized evaluation index value;
and determining a comprehensive evaluation value of each evaluation object in the m evaluation objects through weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight and the space-dimensional weighted weight, wherein the time-dimensional weighted weight is determined based on the p time points, and the space-dimensional weighted weight is determined by a dynamic clustering model and a genetic algorithm.
2. The method according to claim 1, wherein the determining a comprehensive evaluation value of each of the m evaluation objects by a weighted comprehensive operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight includes:
determining a comprehensive evaluation value of each of the m evaluation objects by the following formula (1) based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight:
<mrow> <msub> <mi>u</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>p</mi> </munderover> <mrow> <mo>(</mo> <msub> <mi>w</mi> <mi>k</mi> </msub> <mo>&CenterDot;</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>a</mi> <mi>j</mi> </msub> <msub> <mi>y</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> <mo>)</mo> </mrow> <mo>,</mo> <mrow> <mo>(</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>...</mn> <mo>,</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> </mrow>
wherein u isiA total rating value for the ith rating object among the m rating objects, wkWeighting the time dimension corresponding to the k time point in the p time points, wherein ajWeighting the space dimension corresponding to the jth evaluation index in the n evaluation indexes, wherein y isij(tk) The j evaluation index of the i evaluation object at the k time point tkThe normalized evaluation index value of (1).
3. The method according to claim 1 or 2, wherein before determining the integrated evaluation value of each of the m evaluation objects by a weighted integration operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight, further comprising:
determining a clustering center of an evaluation object by a specified iteration method;
classifying the m evaluation objects based on the determined clustering centers to obtain a plurality of clustering sets, and determining clustering degrees in the clusters according to the clustering sets;
determining inter-class dispersion among the m evaluation objects;
and determining the space dimension weighting weight by adopting a genetic algorithm through the dynamic clustering model based on the intra-class clustering degree and the inter-class dispersion degree.
4. The method according to claim 1 or 2, wherein before determining the integrated evaluation value of each of the m evaluation objects by a weighted integration operation based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight, further comprising:
determining the time-dimensional weighting based on the p time points by the following equation (2):
<mrow> <msub> <mi>w</mi> <mi>k</mi> </msub> <mo>=</mo> <mi>exp</mi> <mrow> <mo>(</mo> <mi>k</mi> <mo>/</mo> <mo>(</mo> <mrow> <mn>2</mn> <mi>p</mi> </mrow> <mo>)</mo> <mo>)</mo> </mrow> <mo>/</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>p</mi> </munderover> <mi>exp</mi> <mrow> <mo>(</mo> <mi>k</mi> <mo>/</mo> <mo>(</mo> <mrow> <mn>2</mn> <mi>p</mi> </mrow> <mo>)</mo> <mo>)</mo> </mrow> <mo>,</mo> <mrow> <mo>(</mo> <mi>k</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mo>...</mo> <mo>,</mo> <mi>p</mi> <mo>)</mo> </mrow> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>2</mn> <mo>)</mo> </mrow> </mrow>
wherein, the wkAnd weighting the time dimension corresponding to the kth time point in the p time points.
5. The method of claim 1, wherein the step of performing the non-quantitative tempering treatment on the obtained evaluation index value to obtain a normalized evaluation index value comprises:
when the evaluation index of the evaluation object is larger and more excellent, carrying out the non-amount tempering treatment on the obtained evaluation index value through the following formula (3) to obtain a normalized evaluation index value:
<mrow> <msub> <mi>y</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mi>c</mi> <mo>+</mo> <mo>&lsqb;</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mo>-</mo> <munder> <mi>min</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>k</mi> </mrow> </munder> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> <mo>)</mo> </mrow> <mo>&rsqb;</mo> <mo>/</mo> <mo>&lsqb;</mo> <munder> <mi>max</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>k</mi> </mrow> </munder> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> <mo>)</mo> </mrow> <mo>-</mo> <munder> <mi>min</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>k</mi> </mrow> </munder> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> <mo>)</mo> </mrow> <mo>&rsqb;</mo> <mo>*</mo> <mi>d</mi> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>3</mn> <mo>)</mo> </mrow> </mrow>
when the evaluation index of the evaluation object is smaller and more excellent, carrying out the non-amount tempering treatment on the obtained evaluation index value through the following formula (4) to obtain a normalized evaluation index value:
<mrow> <msub> <mi>y</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mi>c</mi> <mo>+</mo> <mo>&lsqb;</mo> <munder> <mi>max</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>k</mi> </mrow> </munder> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> </mrow> <mo>&rsqb;</mo> <mo>/</mo> <mo>&lsqb;</mo> <munder> <mi>max</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>k</mi> </mrow> </munder> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> <mo>)</mo> </mrow> <mo>-</mo> <munder> <mi>min</mi> <mrow> <mi>i</mi> <mo>,</mo> <mi>k</mi> </mrow> </munder> <mrow> <mo>(</mo> <msub> <mi>x</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> <mo>)</mo> </mrow> <mo>&rsqb;</mo> <mo>*</mo> <mi>d</mi> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>4</mn> <mo>)</mo> </mrow> </mrow>
wherein, said yij(tk) The j-th evaluation index of the i-th evaluation object in the m evaluation objects is at tkNormalized evaluation index value at a point in time, said xij(tk) The j-th evaluation index of the i-th evaluation object is at tkAn evaluation index value at a time point, theThe j-th evaluation index of the m evaluation objects is the minimum evaluation index value in the evaluation index values of p time pointsThe evaluation index value is the largest evaluation index value of the j-th evaluation index of the m evaluation objects in the evaluation index values of p time points, c is a preset translation parameter, d is a preset scaling parameter, and c and d are natural numbers.
6. An apparatus for determining a comprehensive evaluation value, the apparatus comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring the evaluation index values of n evaluation indexes of each evaluation object in m evaluation objects at p time points, and m, n and p are all natural numbers larger than 1;
the processing module is used for carrying out non-quantity toughening treatment on the obtained evaluation index value to obtain a normalized evaluation index value;
a first determining module, configured to determine, based on the normalized evaluation index value, the time-dimensional weighting weight, and the space-dimensional weighting weight, a comprehensive evaluation value of each of the m evaluation objects through a weighted comprehensive operation, where the time-dimensional weighting weight is determined based on the p time points, and the space-dimensional weighting weight is determined by a dynamic clustering model using a genetic algorithm.
7. The apparatus of claim 6, wherein the first determination module is to:
determining a comprehensive evaluation value of each of the m evaluation objects by the following formula (1) based on the normalized evaluation index value, the time-dimensional weighted weight, and the space-dimensional weighted weight:
<mrow> <msub> <mi>u</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>p</mi> </munderover> <mrow> <mo>(</mo> <msub> <mi>w</mi> <mi>k</mi> </msub> <mo>&CenterDot;</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>a</mi> <mi>j</mi> </msub> <msub> <mi>y</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>(</mo> <msub> <mi>t</mi> <mi>k</mi> </msub> <mo>)</mo> <mo>)</mo> </mrow> <mo>,</mo> <mrow> <mo>(</mo> <mi>i</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mn>...</mn> <mo>,</mo> <mi>m</mi> <mo>)</mo> </mrow> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>)</mo> </mrow> </mrow>
wherein u isiA total rating value for the ith rating object among the m rating objects, wkWeighting the time dimension corresponding to the k time point in the p time points, wherein ajWeighting the space dimension corresponding to the jth evaluation index in the n evaluation indexes, wherein y isij(tk) The j evaluation index of the i evaluation object at the k time point tkThe normalized evaluation index value of (1).
8. The apparatus of claim 6 or 7, wherein the apparatus further comprises:
the second determination module is used for determining the clustering center of the evaluation object by a specified iteration method;
a third determining module, configured to classify the m evaluation objects based on the determined clustering centers to obtain multiple clustering sets, and determine an intra-clustering degree according to the multiple clustering sets;
a fourth determining module, configured to determine inter-class dispersion among the m evaluation objects;
and the fifth determining module is used for determining the space dimension weighting weight by adopting a genetic algorithm through the dynamic clustering model based on the intra-class clustering degree and the inter-class dispersion degree.
9. The apparatus of claim 6 or 7, wherein the apparatus further comprises:
a sixth determining module, configured to determine the time-dimensional weighting weight according to the following formula (2) based on the p time points:
<mrow> <msub> <mi>w</mi> <mi>k</mi> </msub> <mo>=</mo> <mi>exp</mi> <mrow> <mo>(</mo> <mi>k</mi> <mo>/</mo> <mo>(</mo> <mrow> <mn>2</mn> <mi>p</mi> </mrow> <mo>)</mo> <mo>)</mo> </mrow> <mo>/</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>k</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>p</mi> </munderover> <mi>exp</mi> <mrow> <mo>(</mo> <mi>k</mi> <mo>/</mo> <mo>(</mo> <mrow> <mn>2</mn> <mi>p</mi> </mrow> <mo>)</mo> <mo>)</mo> </mrow> <mo>,</mo> <mrow> <mo>(</mo> <mi>k</mi> <mo>=</mo> <mn>1</mn> <mo>,</mo> <mn>2</mn> <mo>,</mo> <mo>...</mo> <mo>,</mo> <mi>p</mi> <mo>)</mo> </mrow> <mo>-</mo> <mo>-</mo> <mo>-</mo> <mrow> <mo>(</mo> <mn>2</mn> <mo>)</mo> </mrow> </mrow>
wherein, the wkAnd weighting the time dimension corresponding to the kth time point in the p time points.
10. A computer-readable storage medium having stored therein at least one instruction, which is loaded and executed by a processor, to implement the method for determining a composite evaluation value according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710522530.6A CN107330619A (en) | 2017-06-30 | 2017-06-30 | Determine method, device and the computer-readable recording medium of comprehensive evaluation value |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710522530.6A CN107330619A (en) | 2017-06-30 | 2017-06-30 | Determine method, device and the computer-readable recording medium of comprehensive evaluation value |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107330619A true CN107330619A (en) | 2017-11-07 |
Family
ID=60198584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710522530.6A Pending CN107330619A (en) | 2017-06-30 | 2017-06-30 | Determine method, device and the computer-readable recording medium of comprehensive evaluation value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107330619A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992401A (en) * | 2017-11-29 | 2018-05-04 | 平安科技（深圳）有限公司 | Performance test evaluation method, device, terminal device and storage medium |
| CN108665148A (en) * | 2018-04-18 | 2018-10-16 | 腾讯科技（深圳）有限公司 | A kind of e-sourcing quality evaluating method, device and storage medium |
| CN111310052A (en) * | 2020-02-29 | 2020-06-19 | 平安国际智慧城市科技股份有限公司 | User portrait construction method and device and computer readable storage medium |
| CN111724007A (en) * | 2019-03-18 | 2020-09-29 | 马上消费金融股份有限公司 | Risk evaluation method, evaluation device, intelligent system and storage device |
| CN112388627A (en) * | 2019-08-19 | 2021-02-23 | 维布络有限公司 | Method and system for executing tasks in dynamic heterogeneous robot environment |
| CN112632799A (en) * | 2021-01-06 | 2021-04-09 | 国核电力规划设计研究院有限公司 | Method and device for valuing design wind speed of power transmission line |
| CN113408840A (en) * | 2020-03-17 | 2021-09-17 | 横河电机株式会社 | Evaluation system, evaluation method, and computer-readable non-transitory storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101694744A (en) * | 2009-10-28 | 2010-04-14 | 北京交通大学 | Method and system for evaluating road emergency evacuation capacity and method and system for grading road emergency evacuation capacity |
| CN104992245A (en) * | 2015-07-09 | 2015-10-21 | 南京信息工程大学 | Generalized-entropy-theory-based dynamic intelligent comprehensive analysis method for water environment risk management |
| CN105933138A (en) * | 2016-03-29 | 2016-09-07 | 光通天下网络科技有限公司 | Time-space dimension combined cloud service reliability situation assessment and prediction method |
| CN106383889A (en) * | 2016-09-22 | 2017-02-08 | 国信优易数据有限公司 | Dimension reduction clustering data analysis method |
-
2017
- 2017-06-30 CN CN201710522530.6A patent/CN107330619A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101694744A (en) * | 2009-10-28 | 2010-04-14 | 北京交通大学 | Method and system for evaluating road emergency evacuation capacity and method and system for grading road emergency evacuation capacity |
| CN104992245A (en) * | 2015-07-09 | 2015-10-21 | 南京信息工程大学 | Generalized-entropy-theory-based dynamic intelligent comprehensive analysis method for water environment risk management |
| CN105933138A (en) * | 2016-03-29 | 2016-09-07 | 光通天下网络科技有限公司 | Time-space dimension combined cloud service reliability situation assessment and prediction method |
| CN106383889A (en) * | 2016-09-22 | 2017-02-08 | 国信优易数据有限公司 | Dimension reduction clustering data analysis method |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992401A (en) * | 2017-11-29 | 2018-05-04 | 平安科技（深圳）有限公司 | Performance test evaluation method, device, terminal device and storage medium |
| CN107992401B (en) * | 2017-11-29 | 2020-08-14 | 平安科技（深圳）有限公司 | Performance test evaluation method and device, terminal equipment and storage medium |
| CN108665148A (en) * | 2018-04-18 | 2018-10-16 | 腾讯科技（深圳）有限公司 | A kind of e-sourcing quality evaluating method, device and storage medium |
| CN108665148B (en) * | 2018-04-18 | 2022-02-22 | 腾讯科技（深圳）有限公司 | Electronic resource quality evaluation method and device and storage medium |
| CN111724007A (en) * | 2019-03-18 | 2020-09-29 | 马上消费金融股份有限公司 | Risk evaluation method, evaluation device, intelligent system and storage device |
| CN111724007B (en) * | 2019-03-18 | 2022-12-06 | 马上消费金融股份有限公司 | Risk evaluation method, evaluation device, intelligent system and storage device |
| CN112388627A (en) * | 2019-08-19 | 2021-02-23 | 维布络有限公司 | Method and system for executing tasks in dynamic heterogeneous robot environment |
| CN111310052A (en) * | 2020-02-29 | 2020-06-19 | 平安国际智慧城市科技股份有限公司 | User portrait construction method and device and computer readable storage medium |
| CN111310052B (en) * | 2020-02-29 | 2024-10-29 | 平安国际智慧城市科技股份有限公司 | User portrait construction method, device and computer readable storage medium |
| CN113408840A (en) * | 2020-03-17 | 2021-09-17 | 横河电机株式会社 | Evaluation system, evaluation method, and computer-readable non-transitory storage medium |
| CN112632799A (en) * | 2021-01-06 | 2021-04-09 | 国核电力规划设计研究院有限公司 | Method and device for valuing design wind speed of power transmission line |
| CN112632799B (en) * | 2021-01-06 | 2024-01-26 | 国核电力规划设计研究院有限公司 | Method and device for evaluating design wind speed of power transmission line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107330619A (en) | Determine method, device and the computer-readable recording medium of comprehensive evaluation value | |
| CN109635920B (en) | Neural network optimization method and device, electronic device and storage medium | |
| CN110245757B (en) | Image sample processing method and device, electronic equipment and storage medium | |
| CN107766891B (en) | User gender identification method and device, storage medium and electronic equipment | |
| TWI738144B (en) | Information processing method and device, electronic equipment and storage medium | |
| CN114724643A (en) | Method for screening polypeptide compound and related device | |
| CN113781518B (en) | Neural network structure searching method and device, electronic equipment and storage medium | |
| CN107807730A (en) | Using method for cleaning, device, storage medium and electronic equipment | |
| CN112768064B (en) | Disease prediction device and equipment, symptom information processing method, device and equipment | |
| CN107480773B (en) | Method and device for training convolutional neural network model and storage medium | |
| CN107807940B (en) | Information recommendation method and device | |
| CN109284307B (en) | Traffic data clustering method and device and electronic equipment | |
| CN116127353A (en) | Classification method, classification model training method, equipment and medium | |
| US20220374775A1 (en) | Method for multi-task scheduling, device and storage medium | |
| CN116341252A (en) | Method, device and storage medium for simulating glass color sampling | |
| CN113139490B (en) | Image feature matching method and device, computer equipment and storage medium | |
| CN109657153A (en) | It is a kind of for determining the method and apparatus of the association financial information of user | |
| CN110659726B (en) | Image processing method and device, electronic equipment and storage medium | |
| WO2019114481A1 (en) | Cluster type recognition method, apparatus, electronic apparatus, and storage medium | |
| CN112307353B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN112799895B (en) | Hardware evaluation method, device, electronic equipment, storage medium and program product | |
| CN115131059B (en) | Method and device for publishing multimedia resources, computer equipment and storage medium | |
| CN112070235B (en) | Abnormal positioning method and device for deep learning framework and storage medium | |
| CN111198760B (en) | Data processing method and device | |
| CN116781658A (en) | Method, device, equipment and medium for detecting mail issuing outside |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171107 |
|
| RJ01 | Rejection of invention patent application after publication |