Disclosure of Invention
The invention provides a self-adaptive optimization method and device for the informatization level of fresh cold chains, which are used for solving the technical problem of low informatization level of fresh cold chains in the prior art.
The invention provides a fresh cold chain informatization level self-adaptive optimization method, which comprises the following steps:
determining coupling correlation factors among the correlation feature dimensions based on a plurality of correlation feature dimensions of fresh cold chain informatization levels;
based on the coupling correlation factor, fresh cold chain multi-source data are obtained;
determining the informatization level change rate of the fresh cold chain at different time intervals based on the fresh cold chain multi-source data;
Determining a key influence factor of the fresh cold chain informatization level change rate based on the fresh cold chain informatization level change rate at different time intervals;
And determining the input cost and the corresponding time node for optimizing the fresh cold chain informatization level based on the key influence factors, the fresh cold chain informatization level dynamic prediction model and the particle swarm algorithm model.
According to the self-adaptive optimization method for the fresh cold chain informatization level provided by the invention, the input cost and the corresponding time node for optimizing the fresh cold chain informatization level are determined based on the key influence factors, the fresh cold chain informatization level dynamic prediction model and the particle swarm algorithm model, and the method comprises the following steps:
inputting the key influence factors into the fresh cold chain informatization level dynamic prediction model to obtain a predicted value of the fresh cold chain informatization level output by the fresh cold chain informatization level dynamic prediction model;
Inputting the key influence factors and the maximum value in the predicted value of the fresh cold chain informatization level into a particle swarm algorithm model to obtain the input cost of optimizing the fresh cold chain informatization level and the corresponding time node output by the particle swarm algorithm model;
The method comprises the steps of determining a particle swarm algorithm model, wherein the key influence factors are particle swarm individuals in the particle swarm algorithm model, the maximum value in the predicted value of the fresh cold chain informatization level is a target value of global optimization in the particle swarm algorithm model, and constraint conditions of the key influence factors are input cost and corresponding time nodes.
According to the self-adaptive optimization method for the informatization level of the fresh cold chain, which is provided by the invention, the dynamic prediction model for the informatization level of the fresh cold chain comprises the following steps:
The input module is used for acquiring the key influence factors;
the feature extraction module is used for extracting key features according to the key influence factors;
the prediction module is used for predicting the fresh cold chain informatization level according to the key characteristics;
and the output module is used for outputting the predicted value of the fresh cold chain informatization level.
According to the self-adaptive optimization method for the informatization level of the fresh cold chain, which is provided by the invention, the change rate of the informatization level of the fresh cold chain under different time intervals is determined based on the multi-source data of the fresh cold chain, and the self-adaptive optimization method comprises the following steps:
Determining the influence proportion of each source data on the informatization level of the fresh cold chain;
and carrying out weighted summation on the fresh cold chain multisource data based on the influence proportion of each source data on the fresh cold chain informatization level, and determining the change rate of the fresh cold chain informatization level at different time intervals.
According to the self-adaptive optimization method for the fresh cold chain informatization level provided by the invention, the key influence factors of the fresh cold chain informatization level change rate are determined based on the fresh cold chain informatization level change rate at different time intervals, and the method comprises the following steps:
Inputting the information level change rate of the fresh cold chain into a Monte Carlo simulation algorithm model at different time intervals to obtain a key influence factor of the information level change rate of the fresh cold chain output by the Monte Carlo simulation algorithm model.
According to the self-adaptive optimization method for the fresh cold chain informatization level, the associated feature dimension comprises an informatization input level, an informatization management level, an informatization service level, an informatization innovation level, an informatization security level and an informatization increment level;
The informationized investment level comprises a hardware facility investment duty ratio, a software system update frequency and an IT personnel configuration density;
the informatization management level comprises a data standardization coverage rate, a flow digitizing rate and an abnormal event closed-loop processing rate;
The informatization service level comprises order response timeliness, customer information tracing integrity rate and intelligent early warning accuracy rate;
the informatization innovation level comprises a patent technology conversion rate, a new technology application coverage rate and a research and development investment growth rate;
the informationized security level comprises data encryption transmission rate, system vulnerability restoration timeliness and disaster recovery success rate;
the informationized increment level comprises a data service gain ratio, a resource optimization saving rate and a market prediction matching degree.
The invention also provides a fresh cold chain informatization level self-adaptive optimization device, which comprises the following modules:
the first determining module is used for determining coupling association factors among a plurality of association feature dimensions based on the fresh cold chain informatization level;
the acquisition module is used for acquiring fresh cold chain multi-source data based on the coupling correlation factor;
The second determining module is used for determining the information level change rate of the fresh cold chain at different time intervals based on the fresh cold chain multi-source data;
The third determining module is used for determining key influence factors of the fresh cold chain informatization level change rate based on the fresh cold chain informatization level change rate at different time intervals;
and the fourth determining module is used for determining the input cost and the corresponding time node for optimizing the informatization level of the fresh cold chain based on the key influence factor, the dynamic prediction model of the informatization level of the fresh cold chain and the particle swarm algorithm model.
The invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor realizes the self-adaptive optimization method of the fresh cold chain informatization level when executing the computer program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a fresh cold chain informatization level adaptive optimization method as described in any one of the above.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, implements the fresh cold chain informatization level self-adaptive optimization method as described in any one of the above.
The self-adaptive optimization method for the fresh-air-cooling chain informatization level provided by the invention is used for determining coupling correlation factors among the correlation characteristic dimensions based on the multiple correlation characteristic dimensions of the fresh-air-cooling chain informatization level, so that the multiple dimension characteristics of the fresh-air-cooling chain informatization level are accurately described, the problem of evaluation deviation caused by single dimension in the traditional method is avoided, fresh-air-cooling chain multisource data are acquired based on the coupling correlation factors, the change rate of the fresh-air-cooling chain informatization level under different time intervals is determined based on the fresh-air-cooling chain multisource data, so that the dynamic law of the evolution of the fresh-air-cooling chain informatization level along with time is accurately captured, the subsequent prediction accuracy is improved, the key influence factor of the change rate of the fresh-air-cooling chain informatization level is determined based on the different time intervals, the input cost for optimizing the fresh-air-cooling chain informatization level is determined based on the key influence factors, the fresh-air-cooling chain informatization level dynamic prediction model and the particle swarm algorithm model, the self-optimization of the fresh-air-cooling chain informatization level is realized, the self-optimizing of the fresh-air-cooling chain informatization level is improved, the self-adaptive control of the fresh-air-cooling chain informatization level is formed, the self-adaptive control system is formed, and the self-adaptive control cost of the self-adaptive control system is satisfied under the requirement of the self-adaptive control of the fresh-cooling system and industry.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without any inventive effort, are intended to be within the scope of the invention.
In the field of fresh cold chain logistics management, the improvement of informatization level has important significance for improving logistics efficiency, reducing loss and optimizing resource allocation. However, the level of informatization of fresh cold chain enterprises is often affected by a variety of factors, including multiple dimensions of informatization investment, management, service, innovation, security, and added value level. These factors are interrelated to form a complex system, making the assessment and optimization of the informatization level particularly complex.
Traditional informatization level promotion methods often lack system evaluation and prediction mechanisms, resulting in high input cost and difficulty in quantifying effects. Therefore, how to realize the self-adaptive optimization of the fresh cold chain informatization level under the constraint of cost becomes the current problem to be solved urgently.
Therefore, the invention provides a self-adaptive optimization method of fresh cold chain informatization level facing to cost and time constraint, which comprises the steps of firstly, establishing an identification model by quantitatively describing the associated characteristics of the fresh cold chain informatization level, then, utilizing a multi-source information acquisition technology and a dynamic prediction model to determine key influence factors, and finally, determining the lowest cost investment and time node for maximally improving the fresh cold chain informatization level based on a swarm intelligence algorithm-particle swarm algorithm, thereby realizing the self-adaptive optimization of the fresh cold chain informatization level.
The following describes a fresh cold chain informatization level self-adaptive optimization method and device according to the invention with reference to fig. 1 to 4.
Fig. 1 is a schematic flow chart of a fresh cold chain informatization level self-adaptive optimization method provided by the invention, and as shown in fig. 1, the method comprises the following steps:
Step 101, determining coupling association factors among a plurality of association feature dimensions based on fresh cold chain informatization levels.
Specifically, first, a coupling correlation factor between correlation feature dimensions is determined by quantitatively describing a plurality of correlation feature dimensions of fresh cold chain informatization levels.
Optionally, the associated feature dimension includes an informatization input level, an informatization management level, an informatization service level, an informatization innovation level, an informatization security level, and an informatization increment level;
The informationized investment level comprises a hardware facility investment duty ratio, a software system update frequency and an IT personnel configuration density;
the informatization management level comprises a data standardization coverage rate, a flow digitizing rate and an abnormal event closed-loop processing rate;
The informatization service level comprises order response timeliness, customer information tracing integrity rate and intelligent early warning accuracy rate;
the informatization innovation level comprises a patent technology conversion rate, a new technology application coverage rate and a research and development investment growth rate;
the informationized security level comprises data encryption transmission rate, system vulnerability restoration timeliness and disaster recovery success rate;
the informationized increment level comprises a data service gain ratio, a resource optimization saving rate and a market prediction matching degree.
Specifically, the associated feature dimensions comprise six classes of primary dimensions, namely an informatization input level, an informatization management level, an informatization service level, an informatization innovation level, an informatization security level and an informatization increment level, wherein each primary dimension is provided with a plurality of secondary dimensions.
For example, the informatization investment level also comprises a secondary dimension of hardware facility investment ratio, software system update frequency, IT personnel configuration density and the like
The informatization management level also comprises a secondary dimension, such as data standardization coverage rate, flow digitalization rate, abnormal event closed-loop processing rate and the like;
The informatization service level also comprises a secondary dimension, such as order response timeliness, customer information tracing integrity rate, intelligent early warning accuracy rate and the like;
the informatization innovation level also comprises a secondary dimension, such as patent technology conversion rate, new technology application coverage rate, research and development investment growth rate and the like;
the informatization security level also comprises a secondary dimension, such as data encryption transmission rate, system bug repair timeliness, disaster recovery success rate and the like;
the informatization increment level also comprises a secondary dimension, such as a data service income ratio, a resource optimization saving rate, a market prediction matching degree and the like.
And determining coupling correlation factors among the correlation feature dimensions by quantitatively describing a plurality of correlation feature dimensions of the fresh cold chain informatization level, wherein the coupling correlation factors comprise daily operation data, financial statement data, after-sale service data and the like.
And 102, acquiring fresh cold chain multi-source data based on the coupling correlation factor.
Specifically, a coupling correlation factor matrix is constructed according to various sources of data such as daily operation data, financial statement data, after-sales service data and the like in the coupling correlation factors and is used as fresh cold chain multi-source data.
And step 103, determining the informatization level change rate of the fresh cold chain at different time intervals based on the fresh cold chain multisource data.
Optionally, the determining the fresh cold chain informatization level change rate under different time intervals based on the fresh cold chain multisource data comprises:
Determining the influence proportion of each source data on the informatization level of the fresh cold chain;
and carrying out weighted summation on the fresh cold chain multisource data based on the influence proportion of each source data on the fresh cold chain informatization level, and determining the change rate of the fresh cold chain informatization level at different time intervals.
Specifically, by adopting a multi-source data fusion technology, a coupling association factor matrix among all dimensions is calculated based on an association characteristic dimension system, and then multi-source heterogeneous data is fused by using a weighted summation algorithm, wherein weight coefficients are dynamically distributed according to the influence proportion of each data source on the informatization level of a fresh cold chain, and a dynamic weight distribution model is established according to the influence proportion by an entropy method, so that the data fusion result can accurately reflect the time-space evolution characteristics of the informatization level.
On the basis, the embodiment of the invention adopts a time sequence analysis method to calculate the information level change rate of the fresh cold chain at different time intervals (day/week/month) and constructs a dynamic evaluation index system, thereby accurately reflecting the information level change condition of the fresh cold chain.
Step 104, determining key influence factors of the fresh cold chain informatization level change rate based on the fresh cold chain informatization level change rate at different time intervals.
Optionally, the determining a key impact factor of the fresh cold chain informatization level change rate based on the fresh cold chain informatization level change rate at different time intervals includes:
Inputting the information level change rate of the fresh cold chain into a Monte Carlo simulation algorithm model at different time intervals to obtain a key influence factor of the information level change rate of the fresh cold chain output by the Monte Carlo simulation algorithm model.
Specifically, the information level change rate of the fresh cold chain under different time intervals is input into a Monte Carlo simulation algorithm model, and a key influence factor of the information level change rate of the fresh cold chain output by the Monte Carlo simulation algorithm model is obtained.
According to the embodiment of the invention, a model for identifying key influence factors is established through a Monte Carlo simulation algorithm, an informationized level change rate sequence is used as an input parameter, and a key influence factor set with obvious influence on the system state is output through millions of random sampling simulation, so that the key influence factors with obvious influence on the informationized level change rate of the fresh cold chain are determined.
And 105, determining the input cost and the corresponding time node for optimizing the informatization level of the fresh cold chain based on the key influence factors, the dynamic prediction model of the informatization level of the fresh cold chain and the particle swarm algorithm model.
Optionally, the determining, based on the key impact factor, the fresh cold chain informatization level dynamic prediction model and the particle swarm algorithm model, the investment cost and the corresponding time node for optimizing the fresh cold chain informatization level includes:
inputting the key influence factors into the fresh cold chain informatization level dynamic prediction model to obtain a predicted value of the fresh cold chain informatization level output by the fresh cold chain informatization level dynamic prediction model;
Inputting the key influence factors and the maximum value in the predicted value of the fresh cold chain informatization level into a particle swarm algorithm model to obtain the input cost of optimizing the fresh cold chain informatization level and the corresponding time node output by the particle swarm algorithm model;
The method comprises the steps of determining a particle swarm algorithm model, wherein the key influence factors are particle swarm individuals in the particle swarm algorithm model, the maximum value in the predicted value of the fresh cold chain informatization level is a target value of global optimization in the particle swarm algorithm model, and constraint conditions of the key influence factors are input cost and corresponding time nodes.
The method comprises the steps of determining key influence factors, inputting the key influence factors into a fresh cold chain informatization level dynamic prediction model, wherein the model comprises a four-layer structure, an input module is used for receiving multidimensional feature data, a feature extraction module adopts a principal component analysis method to perform dimension reduction processing to extract key features, a prediction module integrates a convolutional neural network (Convolutional Neural Network, CNN) and a Long-Short-Term Memory (LSTM) in a circulating neural network (Recurrent Neural Network, RNN) to process the input key features, a prediction value of the fresh cold chain informatization level is predicted, and an output module generates and outputs an informatization level prediction curve with multiple time scales according to the predicted fresh cold chain informatization level.
Based on the above embodiment, the maximum value of the predicted value of the information level of the fresh air chain, which is the highest point of the predicted curve, is input into the particle swarm algorithm model at this time to obtain the input cost of optimizing the information level of the fresh air chain and the corresponding time node output by the particle swarm algorithm model. The method comprises the steps of determining a critical influence factor, wherein the critical influence factor is a particle swarm individual in a particle swarm algorithm model, the maximum value in a predicted value of the fresh air/cold chain informatization level is a target value of global optimization in the particle swarm algorithm model, and the constraint condition of the critical influence factor is set as input cost and a corresponding time node.
According to the embodiment of the invention, a particle swarm optimization algorithm model is constructed according to a particle swarm optimization algorithm, key influence factors are mapped into dimensional parameters of a particle swarm space, maximization of fresh cold chain informatization level predicted values is used as a target value of global optimization of the particle swarm algorithm, meanwhile, input cost and corresponding time nodes are set as constraint conditions, and the constraint conditions are encoded as boundary conditions of individual motion tracks of the particle swarm, so that an optimal solution set is obtained through iterative calculation, an optimization scheme containing cost-benefit-time three-dimensional constraint is output, dynamic planning of fresh cold chain informatization level lifting paths is realized, and the technical problems of single evaluation dimension, dynamic response lag, multi-objective co-operation deficiency and the like in traditional cold chain logistics informatization construction are effectively solved.
The self-adaptive optimization method for the fresh-air-cooling chain informatization level provided by the invention is used for determining coupling correlation factors among the correlation characteristic dimensions based on the multiple correlation characteristic dimensions of the fresh-air-cooling chain informatization level, so that the multiple dimension characteristics of the fresh-air-cooling chain informatization level are accurately described, the problem of evaluation deviation caused by single dimension in the traditional method is avoided, fresh-air-cooling chain multisource data are acquired based on the coupling correlation factors, the change rate of the fresh-air-cooling chain informatization level under different time intervals is determined based on the fresh-air-cooling chain multisource data, so that the dynamic law of the evolution of the fresh-air-cooling chain informatization level along with time is accurately captured, the subsequent prediction accuracy is improved, the key influence factor of the change rate of the fresh-air-cooling chain informatization level is determined based on the different time intervals, the input cost for optimizing the fresh-air-cooling chain informatization level is determined based on the key influence factors, the fresh-air-cooling chain informatization level dynamic prediction model and the particle swarm algorithm model, the self-optimization of the fresh-air-cooling chain informatization level is realized, the self-optimizing of the fresh-air-cooling chain informatization level is improved, the self-adaptive control of the fresh-air-cooling chain informatization level is formed, the self-adaptive control system is formed, and the self-adaptive control cost of the self-adaptive control system is satisfied under the requirement of the self-adaptive control of the fresh-cooling system and industry.
Optionally, the fresh cold chain informatization level dynamic prediction model comprises:
The input module is used for acquiring the key influence factors;
the feature extraction module is used for extracting key features according to the key influence factors;
the prediction module is used for predicting the fresh cold chain informatization level according to the key characteristics;
and the output module is used for outputting the predicted value of the fresh cold chain informatization level.
Specifically, fig. 2 is a schematic structural diagram of a fresh cold chain informatization level dynamic prediction model provided by the invention, as shown in fig. 2, wherein the fresh cold chain informatization level dynamic prediction model comprises a four-layer structure, an input module is used for receiving multidimensional feature data, acquiring key influence factors (such as key factor 1, key factor 2 and key factor 3 in fig. 2), a feature extraction module adopts a principal component analysis method to perform dimension reduction treatment, extract key features, a prediction module integrates CNN and LSTM in RNN to process the input key features, predicts the fresh cold chain informatization level, and an output module generates and outputs an informatization level prediction curve under a multi-time scale t according to a predicted value of the fresh cold chain informatization level, so that a basis is provided for determining an optimal target value of the fresh cold chain informatization level accurately, efficiently and intuitively.
The fresh cold chain informatization level self-adaptive optimization device provided by the invention is described below, and the fresh cold chain informatization level self-adaptive optimization device described below and the fresh cold chain informatization level self-adaptive optimization method described above can be correspondingly referred to each other.
Based on any one of the above embodiments, fig. 3 is a schematic structural diagram of a fresh cold chain informatization level adaptive optimization device provided by the present invention, as shown in fig. 3. The embodiment of the invention provides a fresh cold chain informatization level self-adaptive optimization device, which comprises a first determination module 301, an acquisition module 302, a second determination module 303, a third determination module 304 and a fourth determination module 305, wherein:
The method comprises the steps of determining a coupling correlation factor between correlation feature dimensions based on a plurality of correlation feature dimensions of fresh cold chain informatization levels, obtaining a module 302 for obtaining fresh cold chain multi-source data based on the coupling correlation factor, determining fresh cold chain informatization level change rates at different time intervals based on the fresh cold chain multi-source data, determining key influence factors of the fresh cold chain informatization level change rates at the different time intervals based on the fresh cold chain informatization level change rates, and determining input cost and corresponding time nodes for optimizing the fresh cold chain informatization levels by a fourth determining module 305 based on the key influence factors, a fresh cold chain informatization level dynamic prediction model and a particle swarm algorithm model.
The self-adaptive optimizing device for the fresh-air cooling chain informatization level provided by the invention is used for determining coupling correlation factors among the correlation characteristic dimensions based on the multiple correlation characteristic dimensions of the fresh-air cooling chain informatization level, so that multiple dimension characteristics of the fresh-air cooling chain informatization level are accurately described, the problem of evaluation deviation caused by single dimension in a traditional method is avoided, fresh-air cooling chain multisource data are acquired based on the coupling correlation factors, the change rate of the fresh-air cooling chain informatization level in different time intervals is determined based on the fresh-air cooling chain multisource data, so that the dynamic law of the fresh-air cooling chain informatization level evolving along with time is accurately captured, the subsequent prediction accuracy is improved, the key influence factor of the fresh-air cooling chain informatization level change rate is determined based on the different time intervals, the input cost for optimizing the fresh-air cooling chain informatization level is determined based on the key influence factors, the fresh-air cooling chain informatization level dynamic prediction model and the particle swarm algorithm model, the self-optimizing of the fresh-air cooling chain informatization level is realized, the self-optimizing of the fresh-air cooling chain informatization level is improved, the self-adaptive control of the fresh-air cooling chain informatization level is formed at different time intervals, the self-adaptive control of the fresh-air cooling chain informatization level is formed, the self-adaptive control system is formed, and the self-adaptive control cost of the self-adaptive control system is satisfied, and the self-adaptive control system is good, and the self-adaptive control system is controlled, and the self-adaptive control method is realized, and the self-adaptive control.
Fig. 4 illustrates a physical schematic diagram of an electronic device, as shown in fig. 4, which may include a processor (processor) 410, a communication interface (Communications Interface) 420, a memory (memory) 430, and a communication bus 440, where the processor 410, the communication interface 420, and the memory 430 perform communication with each other through the communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to perform a fresh cold chain informatization level adaptive optimization method comprising:
determining coupling correlation factors among the correlation feature dimensions based on a plurality of correlation feature dimensions of fresh cold chain informatization levels;
based on the coupling correlation factor, fresh cold chain multi-source data are obtained;
determining the informatization level change rate of the fresh cold chain at different time intervals based on the fresh cold chain multi-source data;
Determining a key influence factor of the fresh cold chain informatization level change rate based on the fresh cold chain informatization level change rate at different time intervals;
And determining the input cost and the corresponding time node for optimizing the fresh cold chain informatization level based on the key influence factors, the fresh cold chain informatization level dynamic prediction model and the particle swarm algorithm model.
Further, the logic instructions in the memory 430 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. The storage medium includes a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of executing the method for adaptively optimizing the informatization level of fresh cold chain provided by the above methods, the method comprising:
determining coupling correlation factors among the correlation feature dimensions based on a plurality of correlation feature dimensions of fresh cold chain informatization levels;
based on the coupling correlation factor, fresh cold chain multi-source data are obtained;
determining the informatization level change rate of the fresh cold chain at different time intervals based on the fresh cold chain multi-source data;
Determining a key influence factor of the fresh cold chain informatization level change rate based on the fresh cold chain informatization level change rate at different time intervals;
And determining the input cost and the corresponding time node for optimizing the fresh cold chain informatization level based on the key influence factors, the fresh cold chain informatization level dynamic prediction model and the particle swarm algorithm model.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the fresh cold chain informatization level adaptive optimization method provided by the above methods, the method comprising:
determining coupling correlation factors among the correlation feature dimensions based on a plurality of correlation feature dimensions of fresh cold chain informatization levels;
based on the coupling correlation factor, fresh cold chain multi-source data are obtained;
determining the informatization level change rate of the fresh cold chain at different time intervals based on the fresh cold chain multi-source data;
Determining a key influence factor of the fresh cold chain informatization level change rate based on the fresh cold chain informatization level change rate at different time intervals;
And determining the input cost and the corresponding time node for optimizing the fresh cold chain informatization level based on the key influence factors, the fresh cold chain informatization level dynamic prediction model and the particle swarm algorithm model.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
It should be noted that, in this document, 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 one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
In the embodiment of the application, the "determining B based on a" means that a is considered when determining B. B is not limited to "B can be determined based on A alone," B is determined based on A and C, "" B is determined based on A, C and E, "C is determined based on A, B is further determined based on C," etc. In addition, a may be included as a condition for determining B, for example, "when a satisfies a first condition, B is determined using a first method," for example, "when a satisfies a second condition, B is determined," for example, "when a satisfies a third condition, B is determined based on a first parameter," for example. Of course, a may be a condition in which a is a factor for determining B, for example, "when a satisfies the first condition, C is determined using the first method, and B is further determined based on C", or the like.
The term "plurality" in the present invention means two or more, and other adjectives are similar thereto.
It should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention, and not for limiting the same, and although the present invention has been described in detail with reference to the above-mentioned embodiments, it should be understood by those skilled in the art that the technical solution described in the above-mentioned embodiments may be modified or some technical features may be equivalently replaced, and these modifications or substitutions do not make the essence of the corresponding technical solution deviate from the spirit and scope of the technical solution of the embodiments of the present invention.