CN110956261A - Method and system for determining evaluation index - Google Patents
Method and system for determining evaluation index Download PDFInfo
- Publication number
- CN110956261A CN110956261A CN201911096146.XA CN201911096146A CN110956261A CN 110956261 A CN110956261 A CN 110956261A CN 201911096146 A CN201911096146 A CN 201911096146A CN 110956261 A CN110956261 A CN 110956261A
- Authority
- CN
- China
- Prior art keywords
- evaluation index
- data
- preset
- determining
- corresponding weight
- 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 179
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 17
- 230000006870 function Effects 0.000 claims description 52
- 230000015654 memory Effects 0.000 claims description 27
- 238000009411 base construction Methods 0.000 claims description 3
- 239000010410 layer Substances 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 238000010276 construction Methods 0.000 description 5
- 235000019580 granularity Nutrition 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000011229 interlayer Substances 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a system for determining evaluation indexes, wherein the method comprises the following steps: acquiring the number of samples of an object to be evaluated, preset evaluation index data and a target evaluation variable; constructing a data operation function library for carrying out data processing on preset evaluation index data; constructing a hierarchical model with a preset depth, and determining a hierarchical node where preset evaluation index data is located; acquiring an operation function of each preset evaluation index data and a preset weight of each preset evaluation index data; utilizing the evaluation index data and the corresponding weight in the neural network training level model to obtain the trained evaluation index and the corresponding weight; and determining the evaluation index of the object to be evaluated, the corresponding weight and the value of the target evaluation variable according to the trained evaluation index and the corresponding weight. The method and the system for determining the evaluation index can improve the speed of constructing the hierarchical model and the accuracy of the model, and can realize rapid multiplexing of new application data.
Description
Technical Field
The invention relates to the field of model construction, in particular to a method and a system for determining an evaluation index.
Background
The hierarchical model is a data structure of a 'directed tree' to represent various entities and the connection among the entities, each node in the tree represents a record type, and the tree structure represents the connection among the entity types. In the field of education, researchers and decision makers often use a hierarchical dimension model to construct a multi-layer index dimension structure, and the corresponding weight of each node is obtained, so that values of a root node and each branch node are obtained through layer-by-layer calculation, and evaluation and analysis model construction of students, teachers, schools and other subjects is completed.
However, the existing related tools cannot help a model designer in a non-technical field to construct a model quickly and conveniently. The process of building and computing a hierarchical model often requires a technician to assist a model designer in performing a significant amount of development work. Meanwhile, it is difficult to apply the constructed hierarchical model to develop analysis and adjust the model. None of the existing tools support this need when it is desired to adjust model structure or index weights, or to use the original model for analysis of new data from the user.
Disclosure of Invention
Therefore, the invention provides a method for determining the evaluation index, which overcomes the defects of complex construction of the evaluation model and poor reuse of new data in the prior art.
In a first aspect, an embodiment of the present invention provides a method for determining an evaluation index, including: acquiring the number of samples of an object to be evaluated, preset evaluation index data and a target evaluation variable; constructing a data operation function library for carrying out data processing on the preset evaluation index data; constructing a hierarchical model with a preset depth, and determining a hierarchical node where preset evaluation index data is located; acquiring an operation function of each preset evaluation index data and a preset weight of each preset evaluation index data; training the evaluation index data and the corresponding weight in the hierarchical model by using a neural network to obtain the trained evaluation index and the corresponding weight; and determining the evaluation index of the object to be evaluated, the corresponding weight and the value of the target evaluation variable according to the trained evaluation index and the corresponding weight.
In one embodiment, the data manipulation function library is an extensible manipulation function library.
In an embodiment, the number of hidden layers of the neural network coincides with the number of depths of the hierarchical model.
In an embodiment, the step of training the evaluation index data and the corresponding weight in the hierarchical model by using a neural network to obtain the trained evaluation index and the corresponding weight includes: setting a preset loss function; training evaluation index data and corresponding weights in the hierarchical model according to the loss function; and when the training error is smaller than a preset value, obtaining the trained evaluation index and the corresponding weight.
In an embodiment, determining the evaluation index and the corresponding weight of the object to be evaluated according to the trained evaluation index and the corresponding weight includes: and determining the trained evaluation index and the corresponding weight as the evaluation index and the corresponding weight of the final object to be evaluated.
In a second aspect, an embodiment of the present invention provides an evaluation index determining system, including: the system comprises a to-be-evaluated object data acquisition module, a target evaluation module and a data processing module, wherein the to-be-evaluated object data acquisition module is used for acquiring the number of samples of the to-be-evaluated object, preset evaluation index data and a target evaluation variable; the data operation function base construction module is used for constructing a data operation function base and is used for carrying out data processing on the preset evaluation index data; the hierarchical model building module is used for building a hierarchical model with a preset depth and determining a hierarchical node where preset evaluation index data are located; the preset evaluation index processing parameter acquisition module is used for acquiring an operation function of each preset evaluation index data and a preset weight of each preset evaluation index data; the training module is used for training the evaluation index data and the corresponding weight in the hierarchical model by utilizing a neural network to obtain the trained evaluation index and the corresponding weight; and the evaluation index and evaluation result determining module is used for determining the evaluation index of the object to be evaluated, the corresponding weight and the value of the target evaluation variable according to the trained evaluation index and the corresponding weight.
In a third aspect, an embodiment of the present invention provides a terminal, including: the evaluation index determination method includes at least one processor and a memory communicatively connected to the at least one processor, where the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to cause the at least one processor to perform the evaluation index determination method according to the first aspect of the embodiment of the present invention.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are configured to cause a computer to execute the method for determining an evaluation index according to the first aspect of the embodiment of the present invention.
The technical scheme of the invention has the following advantages:
the method and the system for determining the evaluation index, provided by the invention, are used for obtaining the number of samples of an object to be evaluated, preset evaluation index data and a target evaluation variable; constructing a data operation function library for carrying out data processing on preset evaluation index data; constructing a hierarchical model with a preset depth, and determining a hierarchical node where preset evaluation index data is located; acquiring an operation function of each preset evaluation index data and a preset weight of each preset evaluation index data; training the evaluation index data and the corresponding weight in the hierarchical model by using a neural network to obtain the trained evaluation index and the corresponding weight; and determining the evaluation index of the object to be evaluated, the corresponding weight and the value of the target evaluation variable according to the trained evaluation index and the corresponding weight. The method and the system for determining the evaluation index can improve the speed of constructing the hierarchical model and the accuracy of the model, and can realize rapid multiplexing of new application data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart illustrating an example of a method for determining an evaluation index according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating an example of training evaluation index data and corresponding weights in the hierarchical model by using a neural network according to an embodiment of the present invention;
FIG. 3 is a flow chart of an example of a neural network model provided by an embodiment of the present invention;
fig. 4 is a block diagram of an evaluation index determination system according to an embodiment of the present invention;
fig. 5 is a block diagram of a terminal according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
The embodiment of the invention provides a determination method of an evaluation index, which can be applied to an application scene needing to evaluate a target object. As shown in fig. 1, the method for determining the evaluation index includes:
and step S1, acquiring the number of samples of the object to be evaluated, preset evaluation index data and a target evaluation variable.
In the embodiment of the invention, the subject to be evaluated can be students, teachers, schools and the like, and in practical application, the number of samples, the preset evaluation index data and the target evaluation variable can be reasonably selected according to the specific conditions of the evaluated object. For example, when the object to be evaluated is a student, the selectable sample number is the number of all students in a certain school or all students in a certain online learning course, the preset evaluation index is a statistical index based on the learning process of the learner, such as the online learning login frequency during the learning period of a student unit, the time length of watching a learning video during the learning period of the student unit, the number of forums posted during the learning period of the student unit, the right and wrong practice problems during the learning period of the student unit, the login time interval during the learning period of the student unit, the data source can be csv, excel or a database, and the target evaluation variable is a final evaluation index during the learning period of the student, such as the score of a final examination, whether the study is completed, the course completion rate and the like.
And step S2, constructing a data operation function library for carrying out data processing on the preset evaluation index data.
In the embodiment of the present invention, the operation function may be a mean, a standard deviation, a count, a median, a maximum, a minimum, and the like. In an embodiment, the extensible operation function library of the operation function library, in addition to the basic function, may also customize a processing function according to actual needs, and may be added based on a comparison type field function library of different granularities, and the indexes under different granularities may be the same type of indexes, or may be different types of indexes, such as comparison indexes of basic indexes under granularity 1 and granularity 2, for example: the difference between the average school Chinese mean and the average regional Chinese score, the ratio between the number of questions made by the individual per week and the number of questions made by the sample per week, etc., which are merely illustrative and not limiting.
And step S3, constructing a hierarchical model with a preset depth, and determining a hierarchical node where the preset evaluation index data is located.
In the embodiment of the present invention, the hierarchical model to be initialized, for example, the initial setting depth is 2, and each node has 2 child nodes, which is only by way of example and is not limited thereto. The depth of the depth change model can be set, and the child nodes can be correspondingly increased and decreased by changing the number of the child nodes.
And step S4, acquiring the operation function of each preset evaluation index data and the preset weight of each preset evaluation index data.
In the embodiment of the invention, corresponding operation functions can be set for the preset evaluation index according to actual needs, and the optional operation functions have maximum values, minimum values, mean values, standard deviations, median numbers, variation coefficients, high and low groups, times, logarithms, power functions or other defined operation functions and the like. For example, the individual tests whether the average score is less than the average score within the group, etc., the product of the individual score and the average score within the group, the product of the two indices after decentralization; in addition, the sum of the weights of each preset evaluation index to be initialized and the weights of the child nodes should be 1, and the value of each node is between 0 and 1.
And step S5, training the evaluation index data and the corresponding weight in the hierarchical model by using a neural network to obtain the trained evaluation index and the corresponding weight.
In the embodiment of the invention, the number of the hidden layers of the neural network is consistent with the depth number of the hierarchical model, so that the corresponding indexes and the corresponding weights of all depth nodes can be better trained.
In the embodiment of the invention, the weight of each node in the neural network can be set in a way of expert intervention, and the way of expert intervention comprises the following steps: setting of initial weight, locking of weight (the back propagation is not updated after locking), setting of weight range (the back propagation can only be updated within the set range), selection of initial node function library function, etc., and the above manner of performing expert intervention on the neural network is only an example and is not limited thereto.
And step S6, determining the evaluation index of the object to be evaluated, the corresponding weight and the value of the target evaluation variable according to the trained evaluation index and the corresponding weight.
The method for determining the evaluation index provided by the embodiment of the invention is based on different data sets, can improve the speed of constructing the hierarchical model and the accuracy of the model by training the hierarchical model by utilizing the neural network, and can realize rapid multiplexing of new application data.
In an embodiment, the step of training the evaluation index data and the corresponding weight in the hierarchical model by using a neural network to obtain the trained evaluation index and the corresponding weight, as shown in fig. 2, includes:
step S51, setting a preset loss function;
in practical applications, if the target variable Y is present and is a continuous variable, the least squares method can be used as the loss function:
if the target variable Y is a classification variable, the loss function is a cross entropy loss function:
wherein, stateiThe above description is only illustrative, but not limiting, of the status of the i-th layer index.
Step S52: training evaluation index data and corresponding weights in the hierarchical model according to the loss function;
step S53: and when the training error is smaller than a preset value, obtaining the trained evaluation index and the corresponding weight. And determining the trained evaluation index and the corresponding weight as the evaluation index and the corresponding weight of the final object to be evaluated.
In one embodiment, the definition of the items of data involved needs to be given in advance: xN*mFor input data, N is the number of samples, m is the number of indices of statistics, YN*1For the target variable, (if the missing is constructed by adopting an unsupervised method), Opts is defined as an operable function set, wherein the Opts comprises n operable functions, such as min (), max (), count (), std (), average (), mean () and the like, H is the depth of the hierarchical model, and the default is 2, Wopm*mnWeights are selected for the function with values of-1 or 1, and the dimension mn is the index number m and Opts comprises the product of the number of operable functions. -1 represents the non-adoption of the function and 1 represents the adoption of the function. L is a list of the number of nodes in each layer, the length is equal to the depth of the hierarchical model, the last node is defaulted to be 1, and the other nodes are defaulted to be 2. Default 1 list of [2, 1 ] if depth is 2]Default L for depth 3 is [2, 2, 1%]And W is the inter-layer weight list [ ([ W)mn*L[0]，WL[0]*L[1]，…..WL[i-1]*L[i]，...，WL[H-2]*L[H-1]])]The length is equal to the depth of the hierarchical model, W [0]]Is mn x L0]The shape of the weight of the ith layer is L [ i-1 ]]*L[i]。
In the embodiment of the present invention, the process of training the evaluation index data and the corresponding weight in the hierarchical model by using the neural network model shown in fig. 3 specifically includes:
inputting: data X, number of nodes per layer L, target variable Y (optional), function list Opts.
① initialization variables
Depth H ═ length (l);
the variable number m is length (X [0]) (number of columns of X);
the number of functions n ═ length (opts);
function layer weights Wopm*mnThe initialization is only 1;
list of inter-layer weights W ([ W)mn*L[0]，WL[0]*L[1]，…..WL[i-1]*L[i]，…，WL[H-2]*L]H-1]]) All weights in (1) are initialized to 0.5.
② feature Collection
③ normalized X'
Method using maximum and minimum normalization
Normalizing X' to obtain X ″)N*mn
④ forward propagation
⑤ counter propagating
Constructing a loss function:
if Y is present and is a continuous variable:
if Y is a categorical variable
If Y is absent, the Yi constructed by the principal component analysis method is adopted, and the above operation is carried out.
The embodiment of the invention adopts a back propagation algorithm to carry out the weighting value pairs in the W, and simultaneously adopts the following algorithm pairs Wopm*mnUpdating:
⑥ output
Wop, W, Opts, L are the parameters of the constructed hierarchical model, and the index of the target object to be evaluated and the final evaluation result are determined according to each parameter.
In one embodiment, after the finally trained hierarchical model is obtained, if a user needs to modify some evaluation indexes or weights corresponding to the evaluation indexes according to real-time requirements, real evaluation result data of an object to be evaluated is obtained; and after adaptively modifying the trained evaluation index and the corresponding weight according to the real evaluation result data, determining the evaluation index and the corresponding weight of the object to be evaluated.
Example 2
An embodiment of the present invention provides a system for determining an evaluation index, as shown in fig. 4, where the system includes:
the evaluation target data acquisition module 1 is used for acquiring the number of samples of the evaluation target, preset evaluation index data and target evaluation variables. This module executes the method described in step S1 in embodiment 1, and is not described herein again.
The data operation function base construction module 2 is used for constructing a data operation function base and is used for carrying out data processing on the preset evaluation index data; this module executes the method described in step S2 in embodiment 1, and is not described herein again.
The hierarchical model building module 3 is used for building a hierarchical model with a preset depth and determining a hierarchical node where preset evaluation index data is located; this module executes the method described in step S3 in embodiment 1, and is not described herein again.
The preset evaluation index processing parameter acquisition module 4 is used for acquiring an operation function of each preset evaluation index data and a preset weight of each preset evaluation index data; this module executes the method described in step S4 in embodiment 1, and is not described herein again.
And the training module 5 is used for training the evaluation index data and the corresponding weight in the hierarchical model by using a neural network to obtain the trained evaluation index and the corresponding weight. This module executes the method described in step S5 in embodiment 1, and is not described herein again.
And the evaluation index and evaluation result determining module 6 is used for determining the evaluation index of the object to be evaluated, the corresponding weight and the value of the target evaluation variable according to the trained evaluation index and the corresponding weight. This module executes the method described in step S6 in embodiment 1, and is not described herein again.
In practical development application, a general data structure can be defined to characterize the layer model so as to be saved and reused. The back-end application layer can be constructed by model construction and model data related processing, for example, model construction, weight modification, node setting, depth increase and decrease and the like; the front-end layer can be constructed in a visual operable interface mode, for example, each index obtained after data passes through the model is correspondingly visually displayed, a plurality of operations for constructing the model are realized through clicking or dragging operations, and a final training result is displayed.
According to the system for determining the evaluation index, provided by the embodiment of the invention, the neural network is utilized to train the hierarchical model, so that the speed of constructing the hierarchical model and the accuracy of the model can be improved, and the new application data can be quickly multiplexed.
Example 3
An embodiment of the present invention provides a terminal, as shown in fig. 5, including: at least one processor 401, such as a CPU (Central Processing Unit), at least one communication interface 403, memory 404, and at least one communication bus 402. Wherein a communication bus 402 is used to enable connective communication between these components. The communication interface 403 may include a Display (Display) and a Keyboard (Keyboard), and the optional communication interface 403 may also include a standard wired interface and a standard wireless interface. The Memory 404 may be a RAM (random Access Memory) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The memory 404 may optionally be at least one memory device located remotely from the processor 401. Wherein the processor 401 may execute the determination method of the evaluation index in embodiment 1. A set of program codes is stored in the memory 404, and the processor 401 calls the program codes stored in the memory 404 for executing the determination method of the evaluation index in embodiment 1. The communication bus 402 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 402 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one line is shown in FIG. 5, but this does not represent only one bus or one type of bus.
The memory 404 may include a volatile memory (RAM), such as a random-access memory (RAM); the memory may also include a non-volatile memory (english: non-volatile memory), such as a flash memory (english: flash memory), a hard disk (english: hard disk drive, abbreviation: HDD), or a solid-state drive (english: SSD); the memory 404 may also comprise a combination of memories of the kind described above.
The processor 401 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of a CPU and an NP.
The processor 401 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The aforementioned PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof.
Optionally, the memory 404 is also used to store program instructions. The processor 401 may call a program instruction to implement the determination method of the evaluation index in embodiment 1 as the present application.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer-executable instruction is stored on the computer-readable storage medium, and the computer-executable instruction can execute the determination method of the evaluation index in embodiment 1. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid-State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications of the invention may be made without departing from the spirit or scope of the invention.
Claims (9)
1. A method for determining an evaluation index, comprising:
acquiring the number of samples of an object to be evaluated, preset evaluation index data and a target evaluation variable;
constructing a data operation function library for carrying out data processing on the preset evaluation index data;
constructing a hierarchical model with a preset depth, and determining a hierarchical node where preset evaluation index data is located;
acquiring an operation function of each preset evaluation index data and a preset weight of each preset evaluation index data;
training the evaluation index data and the corresponding weight in the hierarchical model by using a neural network to obtain the trained evaluation index and the corresponding weight;
and determining the evaluation index of the object to be evaluated, the corresponding weight and the value of the target evaluation variable according to the trained evaluation index and the corresponding weight.
2. The method for determining an evaluation index according to claim 1, wherein the data operation function library is an extensible operation function library.
3. The method of determining an evaluation index according to claim 1, wherein the number of hidden layers of the neural network coincides with the number of depths of the hierarchical model.
4. The method for determining an evaluation index according to claim 2, wherein the step of training the evaluation index data and the corresponding weight in the hierarchical model by using the neural network to obtain the trained evaluation index and the corresponding weight comprises:
setting a preset loss function;
training evaluation index data and corresponding weights in the hierarchical model according to the loss function;
and when the training error is smaller than a preset value, obtaining the trained evaluation index and the corresponding weight.
5. The method for determining an evaluation index according to claim 4, wherein determining the evaluation index and the corresponding weight of the object to be evaluated according to the trained evaluation index and the corresponding weight comprises:
and determining the trained evaluation index and the corresponding weight as the evaluation index and the corresponding weight of the final object to be evaluated.
6. The method for determining an evaluation index according to claim 4, wherein determining the evaluation index and the corresponding weight of the object to be evaluated according to the trained evaluation index and the corresponding weight comprises:
acquiring real evaluation result data of an object to be evaluated;
and after the trained evaluation indexes and the corresponding weights are adaptively modified according to the real evaluation result data, determining the evaluation indexes and the corresponding weights of the objects to be evaluated.
7. An evaluation index determination system, comprising:
the system comprises a to-be-evaluated object data acquisition module, a target evaluation module and a data processing module, wherein the to-be-evaluated object data acquisition module is used for acquiring the number of samples of the to-be-evaluated object, preset evaluation index data and a target evaluation variable;
the data operation function base construction module is used for constructing a data operation function base and is used for carrying out data processing on the preset evaluation index data;
the hierarchical model building module is used for building a hierarchical model with a preset depth and determining a hierarchical node where preset evaluation index data are located;
the preset evaluation index processing parameter acquisition module is used for acquiring an operation function of each preset evaluation index data and a preset weight of each preset evaluation index data;
the training module is used for training the evaluation index data and the corresponding weight in the hierarchical model by utilizing a neural network to obtain the trained evaluation index and the corresponding weight;
and the evaluation index and evaluation result determining module is used for determining the evaluation index of the object to be evaluated, the corresponding weight and the value of the target evaluation variable according to the trained evaluation index and the corresponding weight.
8. A terminal, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to cause the at least one processor to perform the method of determining an evaluation index of any of claims 1-6.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions for causing the computer to execute the evaluation index determination method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911096146.XA CN110956261A (en) | 2019-11-11 | 2019-11-11 | Method and system for determining evaluation index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911096146.XA CN110956261A (en) | 2019-11-11 | 2019-11-11 | Method and system for determining evaluation index |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110956261A true CN110956261A (en) | 2020-04-03 |
Family
ID=69977104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911096146.XA Pending CN110956261A (en) | 2019-11-11 | 2019-11-11 | Method and system for determining evaluation index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110956261A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861253A (en) * | 2020-07-29 | 2020-10-30 | 北京车薄荷科技有限公司 | Personnel capacity determining method and system |
| CN112488538A (en) * | 2020-12-04 | 2021-03-12 | 国泰新点软件股份有限公司 | Evaluation index reporting processing method, device and storage medium |
| CN113256465A (en) * | 2021-06-04 | 2021-08-13 | 黄莉 | Remote education training system based on block chain technology |
| CN114676972A (en) * | 2022-03-01 | 2022-06-28 | 北京师范大学 | Teaching quality evaluation index system construction and evaluation method and device and electronic equipment |
-
2019
- 2019-11-11 CN CN201911096146.XA patent/CN110956261A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861253A (en) * | 2020-07-29 | 2020-10-30 | 北京车薄荷科技有限公司 | Personnel capacity determining method and system |
| CN112488538A (en) * | 2020-12-04 | 2021-03-12 | 国泰新点软件股份有限公司 | Evaluation index reporting processing method, device and storage medium |
| CN113256465A (en) * | 2021-06-04 | 2021-08-13 | 黄莉 | Remote education training system based on block chain technology |
| CN114676972A (en) * | 2022-03-01 | 2022-06-28 | 北京师范大学 | Teaching quality evaluation index system construction and evaluation method and device and electronic equipment |
| CN114676972B (en) * | 2022-03-01 | 2024-09-06 | 北京师范大学 | Teaching quality evaluation index system construction and evaluation method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110956261A (en) | Method and system for determining evaluation index | |
| CN109740657B (en) | Training method and device of neural network model for image data classification | |
| CN109242149A (en) | A kind of student performance early warning method and system excavated based on educational data | |
| CN113283488B (en) | Learning behavior-based cognitive diagnosis method and system | |
| CN112561031A (en) | Model searching method and device based on artificial intelligence and electronic equipment | |
| CN116186824B (en) | Building structure arrangement method based on image embedded graph neural network model | |
| CN107368418A (en) | A kind of method, apparatus and medium for traveling through test | |
| CN113779882A (en) | Method, device, equipment and storage medium for predicting residual service life of equipment | |
| CN114492451B (en) | Text matching method, device, electronic equipment and computer readable storage medium | |
| CN111369063B (en) | Test paper model training method, test paper combining method and related device | |
| CN117494813A (en) | Method, device, electronic and medium for mathematical reasoning by using large language model | |
| CN110825903A (en) | Visual question-answering method for improving Hash fusion mechanism | |
| CN114970114A (en) | Virtual simulation model dynamic optimization method and system based on augmented reality | |
| CN113407806B (en) | Network structure searching method, device, equipment and computer readable storage medium | |
| US20210406758A1 (en) | Double-barreled question predictor and correction | |
| CN113642226A (en) | Training method of fair machine learning model based on multi-objective evolutionary algorithm | |
| CN114238106A (en) | Test time prediction method and device, electronic device and storage medium | |
| CN113822441A (en) | Decision model training method and device, terminal equipment and storage medium | |
| Razak et al. | Modelling Hierarchical Fuzzy Systems for Mango Grading via FuzzyR Toolkit | |
| CN113191877A (en) | Data feature acquisition method and system and electronic equipment | |
| CN112528221A (en) | Knowledge and capability binary tracking method based on continuous matrix decomposition | |
| CN111695989A (en) | Modeling method and platform of wind-control credit model | |
| CN111160662A (en) | Risk prediction method, electronic equipment and storage medium | |
| CN114238613B (en) | Method and device for determining mastery degree of knowledge points and electronic equipment | |
| Li | Data-driven adaptive learning systems |
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: 20200403 |
|
| RJ01 | Rejection of invention patent application after publication |