CN114358569A - Enterprise core competitiveness evaluation method based on multi-level model fusion and storage medium - Google Patents
Enterprise core competitiveness evaluation method based on multi-level model fusion and storage medium Download PDFInfo
- Publication number
- CN114358569A CN114358569A CN202111649055.1A CN202111649055A CN114358569A CN 114358569 A CN114358569 A CN 114358569A CN 202111649055 A CN202111649055 A CN 202111649055A CN 114358569 A CN114358569 A CN 114358569A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- model
- training
- data
- evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an enterprise core competitiveness evaluation method based on multi-level model fusion and a storage medium, wherein the method comprises the steps of collecting enterprise data, carrying out dimension division on an enterprise, and obtaining and quantifying enterprise characteristics; calculating index subjective weighted value by adopting an analytic hierarchy process; calculating an objective weight value of the index by an entropy method; determining an index subjective weight combination proportion coefficient and an index objective weight combination proportion coefficient by adopting a variation coefficient method and a Lagrange extreme value method; and establishing a combined weight model; constructing a linear weighting and evaluation model according to the evaluation index system and the combined weight model, evaluating the capacity of the enterprise to be analyzed according to the linear weighting and evaluation model, and respectively establishing a GBDT model for the evaluation result; inputting the enterprise information and the characteristics into the model; and realizing model fusion on different levels by using a Stacking technology and outputting the evaluation result of the core competitiveness of the enterprise. According to the invention, through the Stacking integrated learning idea, the fault tolerance and disturbance resistance of the model are enhanced, and the model precision is effectively improved.
Description
Technical Field
The invention relates to the technical field of evaluation, in particular to an enterprise core competitiveness evaluation method based on multi-level model fusion and a storage medium.
Background
In the current society, various emerging enterprises emerge endlessly, new enterprises are continuously filled in the market, all the industries face the challenges in the aspect of enterprise development, in the enterprise development process, the understanding of the core competitiveness of the enterprise becomes an important part in forming the advantages of the enterprise, and the enterprise can continuously improve and strengthen the enterprise only by establishing the core competitiveness while the core competitiveness of the enterprise is clear, so that the competitive advantages of the enterprise in the past, the present and the future are supported, and the enterprise can obtain the active core capability for a long time in the competitive environment.
The enterprise core competitiveness evaluation based on multi-level model fusion is characterized in that a core competitiveness characteristic evaluation model, a core technology evaluation model, an enterprise brand culture evaluation model, a scientific and technological innovation capability evaluation model, an enterprise management capability evaluation model, an enterprise development strategy evaluation model, an enterprise development potential evaluation model, a policy matching model and other multi-level models are added through algorithms on the basis of comprehensively analyzing factors influencing the enterprise core competitiveness by combining the existing enterprise core competitiveness evaluation theory, and relevant parameters of evaluation are respectively calculated through machine learning of a large number of samples and the evaluation model is continuously optimized, so that the evaluation result is more accurate.
To sum up, enterprise core competitiveness plays decisive role to enterprise development and trade competition, and current enterprise can't judge enterprise core competitiveness through enterprise self condition is accurate, need rely on evaluation system to judge, and the existing evaluation model evaluation dimension in current market is less, lacks a large amount of enterprise's samples and learns the optimization precision lack to the model, how through a plurality of dimensions, accurate carry out enterprise core competitiveness evaluation, becomes the problem that needs to solve at present badly.
Disclosure of Invention
The invention provides a method, a system and a storage medium for evaluating enterprise core competitiveness based on multi-level model fusion, which can at least solve one of the technical problems in the background art.
In order to achieve the purpose, the invention adopts the following technical scheme:
an enterprise core competitiveness evaluation method based on multi-level model fusion executes the following steps through computer equipment, and comprises the following steps,
s1, enterprise data are collected, dimensionality division is carried out on the enterprises, and enterprise characteristics are obtained and quantified;
s2, calculating index subjective weight values by adopting an analytic hierarchy process;
s3, calculating an objective weight value of the index by an entropy method;
s4, determining index subjective weight combination proportion coefficient and objective weight combination proportion coefficient by using a variation coefficient method and a Lagrange extreme value method;
s5, establishing a combined weight model according to the index subjective weight value, the index objective weight value, the subjective weight combined proportion coefficient and the objective weight combined proportion coefficient;
s6, constructing a linear weighting and evaluating model according to the evaluation index system and the combined weight model, and evaluating the core competitiveness characteristic capability, the core technology capability, the enterprise brand culture capability, the scientific and technological innovation capability, the enterprise management capability, the enterprise development capability and the enterprise development potential of the enterprise to be analyzed according to the linear weighting and evaluating model;
s7, respectively establishing a GBDT model according to the core competitiveness characteristic ability, the core technical ability, the enterprise brand cultural ability, the technological innovation ability, the enterprise management ability, the enterprise development ability and the enterprise development potential evaluation result;
s8, inputting the enterprise information and the characteristics into the model;
and S9, realizing model fusion on different levels through a Stacking technology to obtain a prediction result and outputting an enterprise core competitiveness evaluation result.
Further, step S9 specifically includes,
the first layer adopts four models of RF, ET, GBDT and XGB, respectively predicts the training samples, and then takes the prediction result as the training sample of the next layer; wherein, RF is a Random Forest Random model, ET is an eXtreme Random Tree model of ExtraTree, GBDT is a Gradient Boosting Decision Tree model of Decision Tree, XGB is an eXtreme Gradient Boosting model of eXtrement;
firstly, dividing training data into K-fold data and laying a foundation for training each model;
respectively carrying out K times of training aiming at each model RF, ET, GBDT and XGB, reserving one-half K samples for each time of training for testing during training, predicting the testingdata after the training is finished, wherein one model corresponds to 5 prediction results, and averaging the 5 results;
for the first model RF, the data set is first divided into 5 folds, a1, a2, a3, a4, a5, as follows:
the training of a2, a3, a4 and a5 is reserved, the effect of the current training is checked by using a1 as test data, the prediction result of the test data can be recorded by matching with early stop, and meanwhile, the testdata is predicted, wherein the testdata is the part of data for finally submitting the result;
keeping a1, a3, a4 and a5 training, using a2 as test data, recording the prediction result of the test data, and predicting testdata;
keeping a1, a2, a4 and a5 training, using a3 as test data, recording the prediction result of the test data, and predicting testdata;
keeping a1, a2, a3 and a5 training, using a4 as test data, recording the prediction result of the test data, and predicting testdata;
keeping a1, a2, a3 and a4 training, using a5 as test data, recording the prediction result of the test data, and predicting testdata;
five predicted values aiming at the testing data are obtained after five rounds of training, an average value is taken, and the prediction results of each series of models on the training data set are spliced simultaneously;
then, the ET, GBDT and XGB are trained by the same method, the consistency of K-fold data is kept, and after all training is finished, the obtained four prediction results are brought into the next layer of prediction;
the four results of the previous layer are brought into a new model for the second time, and training and forecasting are carried out;
and then splicing the four prediction results with the real label of each sample, bringing the real label into a model for training, finally predicting to obtain a final prediction result after stacking fusion, and outputting the core competitiveness evaluation result of the enterprise at the moment.
Further, the step S1 specifically includes,
enterprise data is collected through data collection and filling, enterprises are divided according to dimensions of areas, industry fields, technical fields, product classification, industry classification, enterprise scale, life cycles, scientific and technological activities and intellectual property rights, and enterprise features are obtained and quantified.
In yet another aspect, the present invention also discloses a computer readable storage medium storing a computer program, which when executed by a processor causes the processor to perform the steps of the method as described above.
In yet another aspect, the present invention also discloses a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the above method.
According to the technical scheme, the enterprise core competitiveness evaluation method and system based on the multi-level model fusion solve the problem that the multi-dimensional evaluation cannot be performed on the enterprise core competitiveness in the prior art through a multi-level model fusion algorithm, and the Stacking integrated learning idea enhances the fault tolerance and disturbance resistance of the model, effectively improves the model precision, and provides a more efficient, accurate, objective, scientific and reasonable core competitiveness evaluation result for an enterprise.
Drawings
FIG. 1 is a block diagram of the process of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
As shown in fig. 1, the method for evaluating enterprise core competitiveness based on multi-level model fusion according to the present embodiment performs the following steps by using a computer device,
enterprise data is collected through data collection, filling and the like, enterprises are divided according to dimensions such as areas, industry fields, technical fields, product classification, industry classification, enterprise scale, life cycles, scientific and technological activities, intellectual property rights and the like, and enterprise features are obtained and quantified.
Calculating index subjective weighted value by adopting an analytic hierarchy process;
calculating an objective weight value of the index by an entropy method;
determining an index subjective weight combination proportion coefficient and an index objective weight combination proportion coefficient by adopting a variation coefficient method and a Lagrange extreme value method;
establishing a combined weight model according to the index subjective weight value, the index objective weight value, the subjective weight combined proportion coefficient and the objective weight combined proportion coefficient;
and constructing a linear weighting and evaluating model according to the evaluation index system and the combined weight model, and evaluating the core competitiveness characteristic capability, the core technical capability, the enterprise brand cultural capability, the technological innovation capability, the enterprise management capability, the enterprise development potential and the like of the enterprise to be analyzed according to the linear weighting and evaluating model.
And respectively establishing a GBDT model according to the evaluation results of the core competitiveness characteristic capacity, the core technical capacity, the enterprise brand cultural capacity, the technological innovation capacity, the enterprise management capacity, the enterprise development capacity and the enterprise development potential.
And inputting the enterprise information and the characteristics into the model.
Model fusion at different levels is realized by the Stacking technology:
the first layer adopts four models of RF, ET, GBDT and XGB, respectively predicts the training samples, and then takes the prediction result as the training sample of the next layer; wherein, RF is a Random Forest Random model, ET is an eXtreme Random Tree model of ExtraTree, GBDT is a Gradient Boosting Decision Tree model of Decision Tree, XGB is an eXtreme Gradient Boosting model of eXtrement;
firstly, dividing training data into K-fold data and laying a foundation for training each model;
respectively carrying out K times of training aiming at each model RF, ET, GBDT and XGB, reserving one-half K samples for each time of training for testing during training, predicting the testingdata after the training is finished, wherein one model corresponds to 5 prediction results, and averaging the 5 results;
for the first model RF, the dataset is first partitioned into 5 folds, a1, a2, a3, a4, a 5. The method comprises the following steps:
keeping a2, a3, a4 and a5 training, recording the predicted result of the test data by using a1 as test data (looking at the effect of the current training and being matched with early stop), and predicting the testdata (the testdata is the part of data to be finally submitted as the result);
keeping a1, a3, a4 and a5 training, using a2 as test data, recording the prediction result of the test data, and predicting testdata;
keeping a1, a2, a4 and a5 training, using a3 as test data, recording the prediction result of the test data, and predicting testdata;
keeping a1, a2, a3 and a5 training, using a4 as test data, recording the prediction result of the test data, and predicting testdata;
keeping a1, a2, a3 and a4 training, using a5 as test data, recording the prediction result of the test data, and predicting testdata;
five predicted values aiming at the testing data are obtained after five rounds of training, an average value is taken, and the prediction results of each series of models on the training data set are spliced simultaneously;
then, the ET, GBDT and XGB are trained by the same method, the consistency of K-fold data is kept, and after all training is finished, the obtained four prediction results are substituted into the next layer of prediction.
And the four results of the previous layer are brought into a new model for the second time, and training and forecasting are carried out. The model of the second layer will generally employ a simple model to prevent overfitting.
And then splicing the four prediction results with the real label of each sample, bringing the real label into a model for training, finally predicting to obtain a final prediction result after stacking fusion, and outputting the core competitiveness evaluation result of the enterprise at the moment.
According to the enterprise core competitiveness evaluation method and system based on multi-level model fusion, the defect that multi-dimensional evaluation cannot be performed on enterprise core competitiveness in the prior art is overcome through a multi-level model fusion algorithm, the integrated learning thought of Stacking is adopted, the fault tolerance and disturbance resistance of the model are enhanced, the model precision is effectively improved, and a more efficient, accurate, objective, scientific and reasonable core competitiveness evaluation result is provided for an enterprise.
In yet another aspect, the present invention also discloses a computer readable storage medium storing a computer program, which when executed by a processor causes the processor to perform the steps of the method as described above.
In yet another aspect, the present invention also discloses a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the above method.
In yet another embodiment provided by the present application, there is further provided a computer program product containing instructions, which when run on a computer, causes the computer to perform any of the above-described embodiments of the method for enterprise core competence assessment based on multi-level model fusion.
It is understood that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, the example and the beneficial effects of the related contents can refer to the corresponding parts in the method.
The embodiment of the application also provides an electronic device, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus,
a memory for storing a computer program;
the processor is used for realizing the enterprise core competitiveness evaluation method based on the multi-level model fusion when executing the program stored in the memory, and the method comprises the following steps:
s1, enterprise data are collected, dimensionality division is carried out on the enterprises, and enterprise characteristics are obtained and quantified;
s2, calculating index subjective weight values by adopting an analytic hierarchy process;
s3, calculating an objective weight value of the index by an entropy method;
s4, determining index subjective weight combination proportion coefficient and objective weight combination proportion coefficient by using a variation coefficient method and a Lagrange extreme value method;
s5, establishing a combined weight model according to the index subjective weight value, the index objective weight value, the subjective weight combined proportion coefficient and the objective weight combined proportion coefficient;
s6, constructing a linear weighting and evaluating model according to the evaluation index system and the combined weight model, and evaluating the core competitiveness characteristic capability, the core technology capability, the enterprise brand culture capability, the scientific and technological innovation capability, the enterprise management capability, the enterprise development capability and the enterprise development potential of the enterprise to be analyzed according to the linear weighting and evaluating model;
s7, respectively establishing a GBDT model according to the core competitiveness characteristic ability, the core technical ability, the enterprise brand cultural ability, the technological innovation ability, the enterprise management ability, the enterprise development ability and the enterprise development potential evaluation result;
s8, inputting the enterprise information and the characteristics into the model;
and S9, realizing model fusion on different levels through a Stacking technology to obtain a prediction result and outputting an enterprise core competitiveness evaluation result.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus may be divided into an address bus, a data bus, a control bus, etc.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other Programmable logic devices, discrete Gate or transistor logic devices, or discrete hardware components.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (5)
1. An enterprise core competitiveness evaluation method based on multi-level model fusion is characterized by comprising the following steps,
s1, enterprise data are collected, dimensionality division is carried out on the enterprises, and enterprise characteristics are obtained and quantified;
s2, calculating index subjective weight values by adopting an analytic hierarchy process;
s3, calculating an objective weight value of the index by an entropy method;
s4, determining index subjective weight combination proportion coefficient and objective weight combination proportion coefficient by using a variation coefficient method and a Lagrange extreme value method;
s5, establishing a combined weight model according to the index subjective weight value, the index objective weight value, the subjective weight combined proportion coefficient and the objective weight combined proportion coefficient;
s6, constructing a linear weighting and evaluating model according to the evaluation index system and the combined weight model, and evaluating the core competitiveness characteristic capability, the core technology capability, the enterprise brand culture capability, the scientific and technological innovation capability, the enterprise management capability, the enterprise development capability and the enterprise development potential of the enterprise to be analyzed according to the linear weighting and evaluating model;
s7, respectively establishing a GBDT model according to the core competitiveness characteristic ability, the core technical ability, the enterprise brand cultural ability, the technological innovation ability, the enterprise management ability, the enterprise development ability and the enterprise development potential evaluation result;
s8, inputting the enterprise information and the characteristics into the model;
and S9, realizing model fusion on different levels through a Stacking technology to obtain a prediction result and outputting an enterprise core competitiveness evaluation result.
2. The enterprise core competitiveness assessment method based on multi-level model fusion according to claim 1, wherein: the step S9 specifically includes the steps of,
the first layer adopts four models of RF, ET, GBDT and XGB, respectively predicts the training samples, and then takes the prediction result as the training sample of the next layer; wherein, RF is a Random Forest Random model, ET is an eXtreme Random Tree model of ExtraTree, GBDT is a Gradient Boosting Decision Tree model of Decision Tree, XGB is an eXtreme Gradient Boosting model of eXtrement;
firstly, dividing training data into K-fold data and laying a foundation for training each model;
respectively carrying out K times of training aiming at each model RF, ET, GBDT and XGB, reserving one-half K samples for each time of training for testing during training, predicting the testingdata after the training is finished, wherein one model corresponds to 5 prediction results, and averaging the 5 results;
for the first model RF, the data set is first divided into 5 folds, a1, a2, a3, a4, a5, as follows:
the training of a2, a3, a4 and a5 is reserved, the effect of the current training is checked by using a1 as test data, the prediction result of the test data can be recorded by matching with early stop, and meanwhile, the testdata is predicted, wherein the testdata is the part of data for finally submitting the result;
keeping a1, a3, a4 and a5 training, using a2 as test data, recording the prediction result of the test data, and predicting testdata;
keeping a1, a2, a4 and a5 training, using a3 as test data, recording the prediction result of the test data, and predicting testdata;
keeping a1, a2, a3 and a5 training, using a4 as test data, recording the prediction result of the test data, and predicting testdata;
keeping a1, a2, a3 and a4 training, using a5 as test data, recording the prediction result of the test data, and predicting testdata;
five predicted values aiming at the testing data are obtained after five rounds of training, an average value is taken, and the prediction results of each series of models on the training data set are spliced simultaneously;
then, the ET, GBDT and XGB are trained by the same method, the consistency of K-fold data is kept, and after all training is finished, the obtained four prediction results are brought into the next layer of prediction;
the four results of the previous layer are brought into a new model for the second time, and training and forecasting are carried out;
and then splicing the four prediction results with the real label of each sample, bringing the real label into a model for training, finally predicting to obtain a final prediction result after stacking fusion, and outputting the core competitiveness evaluation result of the enterprise at the moment.
3. The enterprise core competitiveness assessment method based on multi-level model fusion according to claim 1, wherein: the step S1 specifically includes the steps of,
enterprise data is collected through data collection and filling, enterprises are divided according to dimensions of areas, industry fields, technical fields, product classification, industry classification, enterprise scale, life cycles, scientific and technological activities and intellectual property rights, and enterprise features are obtained and quantified.
4. A computer-readable storage medium, storing a computer program which, when executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 3.
5. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111649055.1A CN114358569A (en) | 2021-12-31 | 2021-12-31 | Enterprise core competitiveness evaluation method based on multi-level model fusion and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111649055.1A CN114358569A (en) | 2021-12-31 | 2021-12-31 | Enterprise core competitiveness evaluation method based on multi-level model fusion and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114358569A true CN114358569A (en) | 2022-04-15 |
Family
ID=81103335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111649055.1A Withdrawn CN114358569A (en) | 2021-12-31 | 2021-12-31 | Enterprise core competitiveness evaluation method based on multi-level model fusion and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358569A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114819003A (en) * | 2022-07-01 | 2022-07-29 | 天津金城银行股份有限公司 | Wind control model processing method, engine, equipment and medium |
| CN116911911A (en) * | 2023-09-12 | 2023-10-20 | 杭州慧泰数据科技有限公司 | Public product release prediction method and system |
| CN117744928A (en) * | 2023-12-19 | 2024-03-22 | 深圳市力合产业研究有限公司 | Competitive power assessment method, system, equipment and readable storage medium for regional industry |
| CN117993776A (en) * | 2024-02-01 | 2024-05-07 | 北京热力智能控制技术有限责任公司 | Heat supply network energy consumption index monitoring device and assessment system |
-
2021
- 2021-12-31 CN CN202111649055.1A patent/CN114358569A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114819003A (en) * | 2022-07-01 | 2022-07-29 | 天津金城银行股份有限公司 | Wind control model processing method, engine, equipment and medium |
| CN116911911A (en) * | 2023-09-12 | 2023-10-20 | 杭州慧泰数据科技有限公司 | Public product release prediction method and system |
| CN116911911B (en) * | 2023-09-12 | 2024-05-28 | 杭州慧泰数据科技有限公司 | Public product release prediction method and system |
| CN117744928A (en) * | 2023-12-19 | 2024-03-22 | 深圳市力合产业研究有限公司 | Competitive power assessment method, system, equipment and readable storage medium for regional industry |
| CN117993776A (en) * | 2024-02-01 | 2024-05-07 | 北京热力智能控制技术有限责任公司 | Heat supply network energy consumption index monitoring device and assessment system |
| CN117993776B (en) * | 2024-02-01 | 2024-09-06 | 北京热力智能控制技术有限责任公司 | Heat supply network energy consumption index monitoring device and assessment system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114358569A (en) | Enterprise core competitiveness evaluation method based on multi-level model fusion and storage medium | |
| CN111582538B (en) | Community value prediction method and system based on graph neural network | |
| CN110570111A (en) | Enterprise risk prediction method, model training method, device and equipment | |
| EP4120653A1 (en) | Communication network performance and fault analysis using learning models with model interpretation | |
| CN111695719A (en) | User value prediction method and system | |
| CN107168995B (en) | Data processing method and server | |
| CN117632905B (en) | Database management method and system based on cloud use records | |
| CN115391561A (en) | Method and device for processing graph network data set, electronic equipment, program and medium | |
| CN113807469A (en) | Multi-energy user value prediction method, device, storage medium and equipment | |
| CN114519519A (en) | Method, device and medium for assessing enterprise default risk based on GBDT algorithm and logistic regression model | |
| CN113762579A (en) | Model training method and device, computer storage medium and equipment | |
| CN116451081A (en) | Data drift detection method, device, terminal and storage medium | |
| CN114971891A (en) | Risk prediction method and device, processor and electronic equipment | |
| CN116362894A (en) | Multi-objective learning method, multi-objective learning device, electronic equipment and computer readable storage medium | |
| CN111242425A (en) | Power data processing method and device | |
| CN116128361A (en) | Multistage efficiency calculation method, device, equipment and medium for intelligent reconnaissance system | |
| Pei | Construction and application of talent evaluation model based on nonlinear hierarchical optimization neural network | |
| CN114387089A (en) | Client credit risk assessment method, device, equipment and storage medium | |
| JP7314723B2 (en) | Image processing system and image processing program | |
| KR102596740B1 (en) | Method for predicting macroeconomic factors and stock returns in the context of economic uncertainty news sentiment using machine learning | |
| CN115204493A (en) | Interest rate sensitivity prediction method and device, electronic device and storage medium | |
| CN117437004A (en) | Risk identification method and device for resource borrowing service and computer equipment | |
| CN114692886A (en) | Model training method and system, and storage medium | |
| Kafabihi | Predicting Laptop Prices Based on Specifications Using Machine Learning Techniques: An Empirical Study | |
| CN118446744A (en) | Rights and interests data conversion method and system based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220415 |