NL2029769B1 - Method and system for generating credit rating of agricultural specialized service provider - Google Patents
Method and system for generating credit rating of agricultural specialized service provider Download PDFInfo
- Publication number
- NL2029769B1 NL2029769B1 NL2029769A NL2029769A NL2029769B1 NL 2029769 B1 NL2029769 B1 NL 2029769B1 NL 2029769 A NL2029769 A NL 2029769A NL 2029769 A NL2029769 A NL 2029769A NL 2029769 B1 NL2029769 B1 NL 2029769B1
- Authority
- NL
- Netherlands
- Prior art keywords
- credit
- service
- agricultural
- specialized
- service provider
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 106
- 238000011156 evaluation Methods 0.000 claims abstract description 70
- 230000008859 change Effects 0.000 claims abstract description 22
- 230000008569 process Effects 0.000 claims abstract description 22
- 238000013135 deep learning Methods 0.000 claims abstract description 17
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 42
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 230000001186 cumulative effect Effects 0.000 claims description 12
- 238000010606 normalization Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000012097 association analysis method Methods 0.000 claims description 10
- 238000000556 factor analysis Methods 0.000 claims description 10
- 238000005065 mining Methods 0.000 claims description 10
- 238000011176 pooling Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000000586 desensitisation Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims 1
- 238000013145 classification model Methods 0.000 abstract description 19
- 238000007405 data analysis Methods 0.000 abstract 1
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000004913 activation Effects 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 230000007306 turnover Effects 0.000 description 4
- 238000012271 agricultural production Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000001052 transient effect Effects 0.000 description 3
- 230000002079 cooperative effect Effects 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 235000006679 Mentha X verticillata Nutrition 0.000 description 1
- 235000002899 Mentha suaveolens Nutrition 0.000 description 1
- 235000001636 Mentha x rotundifolia Nutrition 0.000 description 1
- 238000013398 bayesian method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Mining & Mineral Resources (AREA)
- General Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Technology Law (AREA)
- Health & Medical Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a method and system for generating a credit rating of an agricultural specialized service provider. The method includes: selecting an agricultural specialized service provider credit evaluation index set through big data analysis, and acquiring index values of all agricultural specialized service providers from each historical time to the current time; respectively inputting the index values of each service subject at all times into a preset deep learning credit classification model, and outputting the credit category of each service subject at each time; determining a comprehensive credit rating of each service subject according to the credit categories of each service subject at all historical times and the current time; and visually displaying the credit rating of the service subject and a change process. According to the method; the credit ratings of the agricultural specialized service provider are classified by using a deep learning technology; so that a credit rating result can reflect the credit conditions of the agricultural specialized service provider more objectively and accurately; which helps to improve the scientific and intelligent level of credit rating of the agricultural specialized service provider.
Description
METHOD AND SYSTEM FOR GENERATING CREDIT RATING OF
AGRICULTURAL SPECIALIZED SERVICE PROVIDER
[01] The present invention relates to the technical field of agricultural intelligent information processing, and in particular, to a method and system for generating a credit rating of an agricultural specialized service provider based on big data.
[02] Agricultural specialized service can realize organic connection between small farmers and modern agricultural development, and is an important way to lead the small farmers to carry out appropriate large-scale operation and develop modern agriculture. In recent years, various types of agricultural specialized service providers have organically combined with farmer operation before, in, and after agricultural production service. Many effective agricultural specialized service modes are innovated and developed, which form effective forms, such as agricultural production trusteeship, order service, platform service, and site service, that directly serve farmers and agricultural production, and play an important role in promoting service driven large-scale operation and solving the problems about "who will farm", "how to farm", etc.
[03] However, service organizations in different industries and regions are uneven in the aspects of service scope, service capability, service quality, etc., which highlights many problems. For example, most agricultural specialized service organizations are small in scale, narrow in service scope, and more in concurrent business. The service operation of many service organizations is not standardized, so there is a default risk, and legitimate rights and interests of the served farmers are damaged. Meanwhile, the agricultural specialized service organizations generally lack a standardized financial system, and it is difficult for financial institutions to evaluate their credit through conventional means, so an asymmetric information problem between two credit parties increases the risk control difficulty of the financial institutions and increases their unit credit cost, resulting in the problems of difficulty, high cost, and the like of financing of agricultural specialized service providers.
[04] Embodiments of the present invention provide a method and system for generating a credit rating of an agricultural specialized service provider to overcome the defects in the prior art.
[05] The embodiments of the present invention provide a system for generating a credit rating of an agricultural specialized service provider, including: a data acquisition module, configured to acquire agricultural specialized service data from a plurality of information channels by using a web crawler; a data fusion module, configured to perform semantic association on the obtained multi-source heterogeneous agricultural specialized service big data, so as to eliminate the heterogeneity among different modes of information; an index set determination module, configured to select credit evaluation indexes from a plurality of dimensions to obtain a primarily selected index set, and screen and reduce the primarily selected index set to obtain an agricultural specialized service provider credit evaluation index set, wherein a method for screening and reducing includes: any one or more of big data association rule mining, a hierarchy analysis method, a factor analysis method, and a gray association analysis method; an index value acquisition module, configured to acquire index values of all service subjects from each historical time to the current time for the agricultural specialized service provider credit evaluation index set, a category determination module, configured to respectively input the index values of all service subjects at each time into a preset deep learning credit classification model, and output credit categories of all service subjects at each time; a rating determination module, configured to determine a comprehensive credit rating of each service subject according to the credit categories of each service subject at all times; and a data display module, configured to visually display the credit rating of each service subject and change processes at different times, wherein the credit classification model is obtained by training after taking the determined credit category as a label and the index value of the evaluation index set of the service subject as an input.
[06] The embodiments of the present invention further provide a method for generating a credit rating of an agricultural specialized service provider, and the method is applied to the above-mentioned system, and includes: acquiring agricultural specialized service data from a plurality of information channels by using a web crawler, and performing semantic association on the obtained multi-source heterogeneous agricultural specialized service big data; selecting credit evaluation indexes from a plurality of dimensions to obtain a primarily selected index set, and screening and reducing the primarily selected index set to obtain an agricultural specialized service provider credit evaluation index set, wherein a method for screening and reducing includes: any one or more of big data association rule mining, a hierarchy analysis method, a factor analysis method, and a gray association analysis method, acquiring index values of all service subjects from each historical time to the current time for the agricultural specialized service provider credit evaluation index set; respectively inputting the index values of all service subjects at each time into a preset deep learning credit classification model, and outputting credit categories of all service subjects at each time; determining a comprehensive credit rating of each service subject according to the credit categories of each service subject at all times; and visually displaying the credit rating of each service subject and change processes at different times, wherein the credit classification model is obtained by training after taking the determined credit category as a label and the index value of the evaluation index set of the service subject as an input.
[07] According to the method for generating the credit rating of the agricultural specialized service provider of one embodiment of the present invention, the evaluation index set includes indexes in a plurality of dimensions of basic quality, service capability, operation conditions, management normalization, and social evaluation. The index in the dimension of the basic quality includes at least one of a subject type, establishment time, a registered address, a business scope, registered capital, and the number of people employed. The index in the dimension of the service capability includes at least one of a service area scope, a service field scope, business development time, the number of professional and technical personnel, a service compliance rate, the number of devices owned, the number of intellectual property rights, and the number of new products. The index in the dimension of the operation condition includes at least one of turnover, net profit, the cumulative number of farmers served, the cumulative number of villages and towns served, and the cumulative area of farmland served. The index in the dimension of the management normalization includes at least one of the number of complaints, the number of notifications, whether it has ever been blacklisted, abnormal business information, the number of administrative penalties, the number of cases involving litigation, a customer satisfaction rate, and informatization degree. The index in the dimension of the social evaluation includes at least one of a service positive comment rate, a service moderate comment rate, a service negative comment rate, a sampling survey satisfaction degree, network influence, network influence, Internet word of mouth, brand awareness, and social reputation.
[08] According to the method for generating the credit rating of the agricultural specialized service provider of one embodiment of the present invention, the visually displaying the credit rating of each service subject and change processes at different times includes: visually displaying the comprehensive credit rating of the agricultural specialized service provider at a selected time and subitem ratings in all dimensions by using a radar map, and dynamically displaying historical change processes of the comprehensive credit rating of the agricultural specialized service provider and the subitem ratings; and visually displaying an average credit rating of all service subjects in a certain selected geographical area and a historical change process thereof by using a Geographic Information System (GIS) technology and a thermodynamic chart.
[09] According to the method for generating the credit rating of the agricultural specialized service provider of one embodiment of the present invention, the performing semantic association on the obtained multi-source heterogeneous agricultural specialized service big data includes: performing semantic association on agricultural specialized service provider credit information from different sources and channels on the basis of an ontology alignment or mode alignment method, so as to 5 eliminate the heterogeneity among different modes of information and determine the agricultural specialized service provider credit evaluation index set.
[10] According to the method for generating the credit rating of the agricultural specialized service provider of one embodiment of the present invention, the determining a comprehensive credit rating of each service subject according to the credit categories of each service subject at all times includes: recording n credit ratings as {r,---,r, +r}, where the value of an element +, is f(r)=k ; respectively classifying the credit conditions of each agricultural specialized service provider at time £=1,2,:,7 to obtain a classification result C, ={c!,---,¢}, where
C, represents a credit classification result of the ith service subject at each time; calculating a comprehensive score score, of the ith service subject, and the formula is as follows: 7 score, = round QO w, f(c))) t=] t=1 (7 =)!
[11] If the value of score, is equal to 4, then the credit rating of the ith service subjectis +, where the round(e) is a rounding function, w, is a weight coefficient at the rth time, T is the total number of times of performing credit classification, f(c!) represents the value corresponding to a classification rating c/ that the ith service subject belongs at the 7th time, e is a natural constant, and A is a constant in the interval [0.1,0.5].
[12] The embodiments of the present invention further provide an electronic device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor. Steps of any one of the above-mentioned methods for generating the credit rating of the agricultural specialized service provider are implemented when the processor executes the program.
[13] The embodiments of the present invention further provide a non-transient computer readable storage medium, having a computer program stored thereon. Steps of any one of the above-mentioned methods for generating the credit rating of the agricultural specialized service provider are implemented when the computer program is executed by the processor.
[14] According to the method and the system for generating the credit rating of the agricultural specialized service provider provided by the embodiments of the present invention, the credit ratings of the agricultural specialized service provider are classified by using a deep learning technology, and then the comprehensive credit rating of each service subject is determined on the basis of the credit categories of each service subject at all times. The method can comprehensively and accurately reflect the credit conditions of the agricultural specialized service provider, which helps to improve the scientific and intelligent level of credit rating of the agricultural specialized service provider.
[15] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required to be used in the description of the embodiments or the prior art will be briefly described below. It is apparent that the drawings in the following description are some embodiments of the present invention, and other drawings can also be obtained by those of ordinary skill in the art according to these drawings without any creative work.
[16] FIG. 1 is a schematic flowchart of a method for generating a credit rating of an agricultural specialized service provider provided according to the embodiments of the present invention;
[17] FIG. 2 is a schematic structural diagram of a system for generating a credit rating of an agricultural specialized service provider according to the embodiments of the present invention; and
[18] FIG. 3 is a schematic structural diagram of an electronic device according to the embodiments of the present invention.
[19] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following clearly and completely describes the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Apparently, the described embodiments are part rather than all of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present invention.
[20] In the present embodiment, agricultural specialized service providers usually include the following types: agricultural enterprises, farmer specialized cooperatives, public welfare service organizations, scientific research institutions, supply and marketing cooperatives, family farms, and large agricultural professionals.
[21] A method and a system for generating a credit rating of an agricultural specialized service provider of the embodiments of the present invention are described below in combination with FIG. 1 to FIG. 3. FIG. 1 1s a schematic flowchart of a method for generating a credit rating of an agricultural specialized service provider according to the embodiments of the present invention. As shown in FIG. 1, the embodiments of the present invention provide a method for generating a credit rating of an agricultural specialized service provider, including the following steps.
[22] At 101, agricultural specialized service data is acquired from a plurality of information channels by using a web crawler, and semantic association is performed on the obtained multi-source heterogeneous agricultural specialized service big data.
[23] The agricultural specialized service data usually includes: business registration information, specialized service operation data, production and operation information, supervision and law enforcement information, consumption rights protection information, social evaluation information, network public opinion information, and credit history information. Information sources and channels usually come from: market supervision and management institutions, self-disclosure information, administrative law enforcement notices, bank reference, consumer's associations, trade associations, professional evaluation institutions, statistical survey data, media reports, and social media.
[24] In practical application, in order to comprehensively and accurately reflect the credit conditions of the agricultural specialized service provider, it is necessary to combine internal structured data with external unstructured data. The external unstructured data may use the information related to an agricultural specialized service field crawled from specific websites by using a network theme crawler program. The specific websites usually include the Web sites of the types, such as government websites, industry information websites, news portals, social media, Internet forums, and search engines.
[25] Semantic association is performed on agricultural specialized service provider credit information from different sources and channels on the basis of an ontology alignment or mode alignment method, so as to eliminate the heterogeneity among different modes of information and determine the agricultural specialized service provider credit evaluation index set.
[26] In practical application, semantic transformation and merge between feature words may be realized with the help of a semantic function of a domain ontology by constructing an agricultural specialized service domain ontology. For example, the feature words "Unmanned Aerial Vehicle (UAV) air control", "plant protection air control", and "UAV pesticide application” are considered to be the same feature word.
[27] The mode alignment method may establish a mapping relationship between different modes of information by using the similarity of attribute names, types, and values and an adjacency relationship between attributes. The ontology alignment method realizes ontology matching of a plurality of strategies in a manner of combining an ontology tree and multiple similarity measures.
[28] At 102, credit evaluation indexes are selected from a plurality of dimensions to obtain a primarily selected index set, and the primarily selected index set is screened and reduced to obtain an agricultural specialized service provider credit evaluation index set, wherein a method for screening and reducing includes: any one or more of big data association rule mining, a hierarchy analysis method, a factor analysis method, and a gray association analysis method.
[29] Credit data of the agricultural specialized service provider is screened to extract the index set. Preferably, in the present embodiment, credit evaluation indexes are selected from the five dimensions of basic quality, service capability, operation conditions, management normalization, and social evaluation to obtain an evaluation index set.
[30] Further, the above-mentioned primarily selected index set is screened and reduced by using any one or more of big data association rule mining, a hierarchy analysis method, a factor analysis method, and a gray association analysis method to obtain a final agricultural specialized service provider credit evaluation index set.
Indexes that objectively describe a comprehensive credit rating can be obtained by screening the primarily selected index set through the hierarchy analysis method and the like.
[31] At 103, index values of all service subjects from each historical time to the current time are acquired for the agricultural specialized service provider credit evaluation index set.
[32] The index values of the agricultural specialized service providers at a plurality of historical times, for example, the index values of all service subjects at 1, 2, ..., T-1 and the current time T, are acquired. The time period granularity between two adjacent times may be a plurality of weeks, a plurality of months, a plurality of years, etc., or may be custom settings.
[33] At 104, the index values of all service subjects at each time are respectively input into a preset deep learning credit classification model, and credit categories of all service subjects at each time are output.
[34] The credit classification model is implemented on the basis of a deep learning technology, and is obtained by training after taking the determined credit category as a label and the index value of the evaluation index set of the service subject as an input.
Optionally, a plurality of service subjects and a plurality of corresponding index values can be acquired in advance. The plurality of service subjects are clustered according to the index values to obtain different categories of service subjects, for example, five categories. Then, part index values or all index values are selected according to each category, a rating score of the category is calculated, and values, for example, 1, 2, 3, 4, and 5, are assigned to the categories according to rating scores. The model is trained by taking the categories assigned with values as labels and the corresponding service subject index values as the input of the model. After model training is completed, the credit conditions of all agricultural specialized service providers are classified and predicted. After the index values of all service subjects at each time are input into the model, the credit category at each time can be obtained.
[35] At 105, a comprehensive credit rating of each service subject is determined according to the credit categories of each service subject at all times.
[36] The credit conditions of all agricultural specialized service providers are classified and predicted to obtain the credit categories ¢ of the agricultural specialized service providers at the time £. The comprehensive credit ratings of the agricultural specialized service providers are determined in combination with the historical credit categories ¢',---,¢’ and the current credit category ¢’ of the agricultural specialized service providers.
[37] For example, the comprehensive credit rating may be at a certain specific time, for example, the comprehensive credit rating at the current time determined according to the historical credit categories cc" and the current credit category ¢’, may also be the comprehensive credit rating at time T-1 determined according to the historical credit categories c¢',---,¢’" , and specifically, may also be the comprehensive credit rating obtained after weighting by setting weights according to the credit categories at a plurality of times.
[38] At 106, the credit rating of each service subject and change processes at different times are visually displayed.
[39] The comprehensive credit rating of the agricultural specialized service provider at each time and subitem credit ratings in all dimensions are displayed visually, which is beneficial to the analysis and online monitoring of the change trend of the credit rating of the agricultural specialized service provider.
[40] According to the method for generating the credit rating of the agricultural specialized service provider of the embodiments of the present invention, the index values of all service subjects from each historical time to the current time are used, so that the obtained comprehensive credit rating is more accurate and objective. The credit ratings of the agricultural specialized service provider are classified by using a deep learning technology, so that a credit rating result can reflect the credit conditions of the agricultural specialized service provider more objectively and accurately, which helps to improve the scientific and intelligent level of credit rating of the agricultural specialized service provider.
[41] Based on the content of the above-mentioned embodiments, as an optional embodiment, the operation that the index values of all service subjects at each time are respectively input into a preset deep learning credit classification model includes: the index values of all service subjects at each time are transformed into an index matrix to obtain an input feature map, feature extraction is performed on the feature map by using a convolutional layer and a pooling layer; and the extracted features are integrated by using a fully connected layer, the likelihood probability of each credit rating is calculated by using a likelihood function at an output layer, and the credit category with the maximum probability is selected as a classification result.
[42] Specifically, the deep learning credit classification model may be a
Convolutional Neural Network-based credit classification model, and all indexes in the evaluation index set S may be transformed into an mxm index matrix (J, where the values of the elements in the matrix (J) respectively correspond to the values of all indexes in S, the deficiency is replaced by 0, m is equal to a value rounded up after
S| is subjected to root extraction, and |.S| is the number of the elements in the evaluation index set §'.
[43] Convolution operation is performed on the input feature map (index matrix (J) byusing kxk convolution kernels XK, and a convolution result is taken as an output feature map after being calculated through an activation function. The calculation formula is: x= fi) = LO XT HK] +h) iel,
[44] Where, x; is an output of a jth channel of the convolutional layer 7, x." is an output feature map of the previous layer, LZ, is an input feature map subset used for convolution calculation of the previous layer, K; is a convolution kernel matrix, b is a biasing amount, and f,(e) is an activation function.
[45] At the pooling layer, each output feature map after convolution is subjected to a downsampling operation by using a downsampling function. The calculation formula is: xi = f (u) = f(a xdown(x") +b)
[46] Where, f,(e) is an activation function, u, is a value after the output feature map x)! of the previous layer is subjected to downsampling weighting and biasing, a; is a weighting coefficient, down(e) is a downsampling function, x! is an output feature map of the previous layer, and bi is a biasing amount.
[47] Through a plurality of convolutional layers and pooling layers, local feature information extracted by the convolutional layers or the pooling layers is integrated by using one or more fully connected layers, and an output value of the last fully connected layer is passed to an output layer. The output of each neuron is: h, (x)= f,0¢" x +b)
[48] Where, A, ,(x) is an output value of the neuron, x is an input vector of the neuron, w is a weight vector, b is a biasing amount, and f,(e) is an activation function.
[49] At an output layer, the likelihood probability of each credit rating can be calculated by using a likelihood function, and the credit category with the maximum probability 1s selected as a classification result.
[50] Further, the likelihood probability calculation formula is: exp(x;) > exp(x) il
[51] Where, p(y,) is the likelihood probability of a kth neuron, x, is a kth input of the output layer, and exp is an exponential function taking a natural constant e as a base.
[52] Further, before the credit ratings of all service subjects from each historical time to the current time are acquired, the method further includes that: the credit classification model is trained by using an error back propagation algorithm, and the model is cross-validated by using a K -folded cross validation method.
[53] Further, before the credit ratings of all service subjects from each historical time to the current time are acquired, the method further includes that: an optimized combination of preset parameters in the model is found by using a genetic algorithm or a particle swarm optimization algorithm. The preset parameters include: the convolution kernel size k, the number of convolution kernels, the number of the convolutional layers, the number of the pooling layers, the number of the fully connected layers, a weighting parameter w and a biasing parameter ó of each layer.
[54] Further, before the convolution operation is performed, the method further includes that zero padding processing is performed on an edge of the input feature map, and the padding size is p=(k—1)/2, where, k is the convolution kernel size.
During the convolution operation, a sliding step size of the convolution kernel is 1.
[55] In practical application, in order to prevent the model from an over-fitting problem, the generalization ability of the model may be improved by using a Dropout method or a DropConnect method. A specific method is that: in the Dropout method, part units in an intermediate layer are temporarily dropped from a network according to a certain probability during model training, and the units are enabled not to work by setting the outputs of the units as 0; and in the DropConnect method, part connection weights are set as 0 according to a certain probability.
[56] In practical application, parameters, such as the convolution kernel size k the number of the convolution kernels, the number of the convolutional layers, the number of the pooling layers, the number of the fully connected layers, the number of feature maps of each layer, the probability of Dropout, a learning rate, the number of iterations, etc. may be reasonably determined according to the factors, such as own computing resources and a model training effect. A more optimized combination may be continuously selected from the above-mentioned parameter combinations by using the genetic algorithm and the particle swarm optimization algorithm, so as to make the model achieve a better classification effect. Generally, the initial values of related parameters may be set as follows: the convolution kernel size k is 2, the number of the convolutional layers is 3 to 5, the number of the fully connected layer is 1, and the number of the pooling layers is 0 to 2. If the number of the evaluation indexes 1s small, the pooling layers may also be omitted.
[57] Further, the activation functions f,(¢), f,(®), and f,(¢) are selected from the following functions: a Sigmoid function, a Tanh function, a Rectified Linear Unit (ReLU) function, a Leakly ReLU function, a Parameterized Rectified Linear Unit (PReLU) function, a Random Rectified Linear Unit (RReLU) function, an Exponential
Linear Unit (ELU) function, and a Softmax function. |58] The above-mentioned functions are defined as follows:
[59] The Sigmoid function is defined by the following formula: 1 fx) =—= l+e
[60] The Tanh function is defined by the following formula: tanh(x) = EE e+e
[61] The ReLU function is defined by the following formula:
J (x) =max(0, x)
[62] The Leakly ReLU is defined by the following formula:
X; if Xx; 2 0
X,)= x) la, if x <0
[63] Where, 4, is a fixed constant in the interval (1,400).
[64] The definition of the PReLU function is similar to that of the Leakly ReLU function. The difference therebetween is that a, in the definition of the PReLU function varies according to data, and the value of a, in the RReLU function is fixed.
[65] The RReLU function is defined by the following formula:
J x, ifx,=0
Hr lax, if Xi <0
[66] Where, a, is a numerical value extracted randomly from uniform distribution
U(l,uy, I<u and [,ue[0,1).
[67] The ELU function is defined by the following formula:
Fx) = EG 1), if x <0 x , if x=0
[68] The Softmax function is defined by the following formula: pix=k)= Lr
Dae
[69] The model is trained and cross-validated by a K -folded cross validation method, and function combinations with good model generalization performance are found from the above-mentioned functions to serve as activation functions of f,(e), f(e), and f,(e). Different function combinations may be tried based on human experience, and function combination optimizations may also be solved by using heuristic methods, such as the genetic algorithm.
[70] Based on the content of the above-mentioned embodiments, as an optional embodiment, the operation that credit evaluation indexes are selected from a plurality of dimensions to obtain an primarily selected index set includes: the acquired agricultural specialized service big data is subjected to preprocessing, the preprocessing including any one or more of dynamic desensitization, data cleaning, missing value processing, noise data processing, data normalization, and standardization; and the credit evaluation indexes of the agricultural specialized service provider are selected to obtain the primarily selected index set.
[71] Index data for rating agricultural specialized service providers can be determined according to the above-mentioned agricultural specialized service provider credit information. In practical application, the data desensitization mainly includes: 1) an identity identifier is removed from identity identifier data, such as an email and phone number, through a dynamic desensitization technology to generate a unique ID, and then the unique ID is encrypted and transformed to generate a new identifier; 2) the accuracy of time and date data is removed through the dynamic desensitization technology to blur the data to hours, days, or months; and 3) text data, such as names and home addresses, is partially masked or transformed into digital data. In the noise data processing, abnormal value detection may be performed on the basis of Bayesian method. Identification variables are introduced into a linear regression model, a calculation method for a posterior probability of the identification variables is given on the basis of Gibbs sampling algorithm, and abnormal value positioning is performed by comparing the posterior probabilities of these identification variables.
[72] The primarily selected index set is selected, for example, the credit evaluation indexes of the agricultural specialized service provider are selected from the five dimensions of basic quality, service capability, operation condition, management normalization, and social evaluation, on the basis of Wu's three-dimensional credit theory, so as to obtain the primarily selected index set.
[73] Further, the data normalization method includes:
[74] if the evaluation index / is a positive index, then x, mint) max(z,,) —min(z,,)
If the evaluation index ; is a reverse index, then x, | mez) If the © max(z.,,)—min(z,) evaluation index j is a moderate index, then +, el) ideal( j)+ | ideal j) — z,
[75] Where, x, is a normalized value of a jth index of an ith service subject, z, is an original value of the jth index of the ith service subject, max(z.;) is the maximum value of the jth index of all data, min(z,) is the minimum value of the jth index of all data, and ideal( 7) is an ideal value of the jth index.
[76] According to the method for generating the credit rating of the agricultural specialized service provider of the embodiment of the present invention, the acquired service subject rating data is preprocessed through a big data processing method, which is beneficial to improving the accuracy of the index values.
[77] Based on the content of the above-mentioned embodiments, as an optional embodiment, the evaluation index set includes the indexes in the dimensions of basic quality, service capability, operation conditions, management normalization, and social evaluation.
[78] The basic quality index includes at least one of a subject type, establishment time, a registered address, a business scope, registered capital, and the number of people employed. The service capability index includes at least one of a service area scope, a service field scope, business development time, the number of professional and technical personnel, a service compliance rate, the number of devices owned, the number of intellectual property rights, and the number of new products. The operation condition index includes at least one of turnover, net profit, the cumulative number of farmers served, the cumulative number of villages and towns served, and the cumulative area of farmland served. The management normalization index includes at least one of the number of complaints, the number of notifications, whether it has ever been blacklisted, abnormal business information, the number of administrative penalties, the number of cases involving litigation, a customer satisfaction rate, and informatization degree. The social evaluation index includes at least one of a service positive comment rate, a service moderate comment rate, a service negative comment rate, a sampling survey satisfaction degree, network influence, network influence,
Internet word of mouth, brand awareness, and social reputation.
[79] As an optional embodiment, in practical application, the index in the dimension of the basic quality mainly includes a name, a subject type, establishment time, a registered address, a business scope, registered capital, and the number of people employed, etc. The index in the dimension of the service capability mainly includes a mode, a service area scope, a service field scope, business development time, the number of professional and technical personnel, a service compliance rate, the number of devices owned, the number of intellectual property rights (the number of
Chinese invention patents, the number of Chinese utility model patents, the number of
Patent Cooperation Treaty (PCT) patents, the number of trademarks, etc.), and the number of new products, etc. The index in the dimension of the operation condition mainly includes the turnover in recent three years, the net profit in recent three years, the cumulative number of farmers served, the cumulative number of villages and towns served, the cumulative area of farmland served, the turnover in recent one year, the net profit in recent one year, the number of farmers served in recent one year, the number of villages and towns served in recent one year, the area of farmland served in recent one year, etc. The index in the dimension of the management normalization mainly includes at least one of the number of complaints, the number of notifications, whether it has ever been blacklisted, abnormal business information, the number of administrative penalties, the number of cases involving litigation, a customer satisfaction rate, and informatization degree, etc. The index in the dimension of the social evaluation mainly includes a service positive comment rate, a service moderate comment rate, a service negative comment rate, a sampling survey satisfaction degree, network influence, network influence, Internet word of mouth, brand awareness, social reputation, etc.
[80] Based on the content of the above-mentioned embodiments, as an optional embodiment, the operation that the credit rating of each service subject and change processes at different times are visually displayed includes: the comprehensive credit rating of the agricultural specialized service provider at a selected time and subitem ratings in all dimensions are visually displayed by using a radar map, and historical change processes of the comprehensive credit rating of the agricultural specialized service provider and the subitem ratings are displayed dynamically.
[81] When the acquired index values of all service subjects from each historical time to the current time are the index values of one of the above-mentioned five dimensions, the subitem rating in a single dimension can be obtained. Finally, the comprehensive credit rating at the selected time and the subitem ratings in all dimensions are displayed visually.
[82] For example, the comprehensive credit rating of the agricultural specialized service provider at a certain time and the subitem ratings in the above-mentioned five dimensions are displayed visually by using a radar map, and historical change processes of the credit rating of the agricultural specialized service provider and the five subitem ratings are displayed dynamically by using, for example, a Timeline technology. An average credit rating of all service subjects and the historical change process thereof in a certain selected geographical area are displayed visually by using a
Geographic Information System (GIS) technology and a thermodynamic chart.
[83] According to the method for generating the credit rating of the agricultural specialized service provider of the embodiments of the present invention, the comprehensive credit rating of the agricultural specialized service provider at the selected time and the subitem ratings in all dimensions are displayed visually, which is beneficial to the analysis and online monitoring of the comprehensive credit rating and the subitem ratings in all dimensions.
[84] Based on the content of the above-mentioned embodiments, as an optional embodiment, the operation that a comprehensive credit rating of the service subject is determined according to the credit categories of each service subject at all times includes:
[85] 7 credit ratings are recorded as {#,---.%,,---7,}, where the quantized value of an element * is f(x )=4k. The credit conditions of each agricultural specialized service provider at time 7=1,2,---,7 are classified, so as to obtain a classification result C, ={c,---,c/}, where C, represents a credit classification result of the ith service subject at each time; a comprehensive score score, of the ith service subject is calculated, and the formula is as follows: , score, = tound(Y_ w, f(c)) r=1
T A
W, = > FT t=1 (1 —1)!
[86] If the value of score, is equal to k, then the credit rating of the ith service subjectis #,.
[87] Where, round(e) is a rounding function, iis a weight coefficient at the
Ith time, 7 is the total number of times of performing credit classification, f(c{) represents the value corresponding to a classification rating c/ that the ith service subject belongs at the {th time, e is a natural constant, and A is a constant in the interval [0.1,0.5].
[88] The smaller the value of A, the smaller the proportion of a historical classification rating, the greater the proportion of a current classification rating, and generally, 4=0.3.
[89] A system for generating a credit rating of an agricultural specialized service provider provided by the embodiments of the present invention is described below. The system for generating the credit rating of the agricultural specialized service provider described below and the method for generating the credit rating of the agricultural specialized service provider described above may mutually correspond and refer to each other.
[90] FIG. 2 is a schematic structural diagram of a system for generating a credit rating of an agricultural specialized service provider according to the embodiments of the present invention. As shown in FIG. 2, the system for generating the credit rating of the agricultural specialized service provider includes a data acquisition module 201, a data fusion module 202, an index set determination module 203, an index value acquisition module 204, a category determination module 205, a rating determination module 206, and a data display module 207. The data acquisition module 201 is configured to acquire agricultural specialized service data from a plurality of information channels by using a web crawler. The data fusion module 202 is configured to perform semantic association on the obtained multi-source heterogeneous agricultural specialized service big data, so as to eliminate the heterogeneity among different modes of information. The index set determination module 203 is configured to select credit evaluation indexes from a plurality of dimensions to obtain a primarily selected index set, and screen and reduce the primarily selected index set to obtain an agricultural specialized service provider credit evaluation index set, wherein a method for screening and reducing includes: any one or more of big data association rule mining, a hierarchy analysis method, a factor analysis method, and a gray association analysis method. The index value acquisition module 204 is configured to acquire index values of all service subjects from each historical time to the current time for the agricultural specialized service provider credit evaluation index set. The category determination module 205 is configured to respectively input the index values of all service subjects at each time into a preset deep learning credit classification model, and output credit categories of all service subjects at each time. The rating determination module 206 is configured to determine a comprehensive credit rating of each service subject according to the credit categories of each service subject at all times. The data display module 207 is configured to visually display the credit rating of each service subject and change processes at different times, wherein the credit classification model is obtained by training after taking the determined credit category as a label and the index value of the evaluation index set of the service subject as an input.
[91] Further, the category determination module 205 is specifically configured to: transform the index values of all service subjects at each time into an index matrix to obtain an input feature map, perform feature extraction on the feature map by using a convolutional layer and a pooling layer, integrate the extracted features by using a fully connected layer, calculate the likelihood probability of each credit rating by using a likelihood function at an output layer, and select the credit category with the maximum probability as a classification result.
[92] Further, the index set determination module 203 is configured to perform preprocessing, including any one or more of dynamic desensitization, data cleaning, missing value processing, noise data processing, data normalization, and standardization, on the acquired agricultural specialized service big data, and select the credit evaluation indexes of the agricultural specialized service provider to obtain the primarily selected index set.
[93] Further, the data display module 207 is specifically configured to visually display the comprehensive credit rating of the agricultural specialized service provider at the selected time and subitem ratings in all dimensions by using a radar map, and dynamically display historical change processes of the comprehensive credit rating of the agricultural specialized service provider and the subitem ratings.
[94] Further, the data fusion module 202 is specifically configured to perform semantic association on agricultural specialized service provider credit information from different sources and channels on the basis of an ontology alignment or mode alignment method, so as to eliminate the heterogeneity among different modes of information and determine the agricultural specialized service provider credit evaluation index.
[95] The system embodiments provided by the embodiments of the present invention are intended to implement above-mentioned various method embodiments.
Reference is made to the foregoing method embodiments for specific processes and detailed content, which will not be elaborated here.
[96] According to the system for generating the credit rating of the agricultural specialized service provider provided by the embodiments of the present invention, the index values of all service subjects from each historical time to the current time are used, so that the obtained comprehensive credit rating is more accurate and objective.
The credit ratings of the agricultural specialized service provider are classified by using a deep learning technology, so that a credit rating result can reflect the credit conditions of the agricultural specialized service provider more objectively and accurately, which helps to improve the scientific and intelligent level of credit rating of the agricultural specialized service provider.
[97] FIG. 3 is a schematic structural diagram of an electronic device provided by the embodiments of the present invention. As shown in FIG. 3, the electronic device may include: a processor 301, a communication interface 302, a memory 303, and a communication bus 304. The processor 301, the communication interface 302, and the memory 303 complete communication with each other through the communication bus 304. The processor 301 may call a logic instruction in the memory 303 to execute the method for generating the credit rating of the agricultural specialized service provider.
The method includes: agricultural specialized service data is acquired from a plurality of information channels by using a web crawler, and semantic association is performed on the obtained multi-source heterogeneous agricultural specialized service big data; credit evaluation indexes are selected from a plurality of dimensions to obtain a primarily selected index set, and the primarily selected index set is screened and reduced to obtain an agricultural specialized service provider credit evaluation index set, wherein a method for screening and reducing includes: any one or more of big data association rule mining, a hierarchy analysis method, a factor analysis method, and a gray association analysis method; index values of all service subjects from each historical time to the current time are acquired for the agricultural specialized service provider credit evaluation index set; the index values of all service subjects at each time are respectively input into a preset deep learning credit classification model, and credit categories of all service subjects at each time are output; a comprehensive credit rating of each service subject is determined according to the credit categories of each service subject at all times; and the credit rating of each service subject and change processes at different times are displayed visually, wherein the credit classification model is obtained by training after taking the determined credit category as a label and the index value of the evaluation index set of the service subject as an input.
[98] In addition, a logic instruction in the above-mentioned memory 303 may be stored in a computer-readable storage medium when implemented in the form of a software functional unit and sold or used as a standalone product. Based on such an understanding, the technical solutions of the present invention essentially, or the part contributing to the prior art, or some of the technical solutions may be implemented in a form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for instructing a computer device (which may be a personal computer, a server, a network device, etc.) to execute all or some of the steps of the methods in various embodiments of the present invention. The foregoing storage medium includes: various media that may store program codes, such as a USB Flash Drive, a mobile hard disk drive, a Read-Only Memory (ROM), a
Random Access Memory (RAM), a magnetic disk, or an optical disk.
[99] On another aspect, the embodiments of the present invention further provide a computer program product. The computer program product includes a computer program stored on a non-transient computer readable storage medium. The computer program includes a program instruction. When the program instruction is executed by a computer, the computer can execute the method for generating the credit rating of the agricultural specialized service provider provided by the above-mentioned various method embodiments. The method includes: agricultural specialized service data is acquired from a plurality of information channels by using a web crawler, and semantic association is performed on the obtained multi-source heterogeneous agricultural specialized service big data; credit evaluation indexes are selected from a plurality of dimensions to obtain a primarily selected index set, and the primarily selected index set is screened and reduced to obtain an agricultural specialized service provider credit evaluation index set, wherein a method for screening and reducing includes: any one or more of big data association rule mining, a hierarchy analysis method, a factor analysis method, and a gray association analysis method; index values of all service subjects from each historical time to the current time are acquired for the agricultural specialized service provider credit evaluation index set; the index values of all service subjects at each time are respectively input into a preset deep learning credit classification model, and credit categories of all service subjects at each time are output; a comprehensive credit rating of each service subject is determined according to the credit categories of each service subject at all times; and the credit rating of each service subject and change processes at different times are displayed visually, wherein the credit classification model is obtained by training after taking the determined credit category as a label and the index value of the evaluation index set of the service subject as an input.
[100] On yet another aspect, the embodiments of the present invention further provide a non-transient computer readable storage medium, having a computer program stored thereon. The computer program implements the method for generating the credit rating of the agricultural specialized service provider provided by the above-mentioned various method embodiments when executed. The method includes that: agricultural specialized service data is acquired from a plurality of information channels by using a web crawler, and semantic association is performed on the obtained multi-source heterogeneous agricultural specialized service big data; credit evaluation indexes are selected from a plurality of dimensions to obtain a primarily selected index set, and the primarily selected index set is screened and reduced to obtain an agricultural specialized service provider credit evaluation index set, wherein a method for screening and reducing includes: any one or more of big data association rule mining, a hierarchy analysis method, a factor analysis method, and a gray association analysis method; index values of all service subjects from each historical time to the current time are acquired for the agricultural specialized service provider credit evaluation index set; the index values of all service subjects at each time are respectively input into a preset deep learning credit classification model, and credit categories of all service subjects at each time are output; a comprehensive credit rating of each service subject is determined according to the credit categories of each service subject at all times; and the credit rating of each service subject and change processes at different times are displayed visually, wherein the credit classification model is obtained by training after taking the determined credit category as a label and the index value of the evaluation index set of the service subject as an input.
[101] The system embodiments described above are merely illustrative. The units described as separate components may be or may not be physically separated, and the components displayed as units may be or may not be physical units, which may be located in one place or distributed to a plurality of network units. Part or all of the modules may be selected according to actual needs to achieve the objective of the solution of the present embodiment. Those of ordinary skill in the art can understand and implement without any creative effort.
[102] Through the description of the above implementations, those of ordinary skill in the art can clearly understand that each implementation mode may be implemented by means of software plus a necessary general hardware platform, and of course, may also be implemented through hardware. Based on such an understanding, the foregoing technical solutions of the present invention essentially or the part contributing to the prior art may be implemented in a form of a software product. The software product may be stored in a computer readable storage medium, such as a ROM/RAM, a magnetic disk, or an optical disc, and includes a plurality of instructions for instructing a computer device (which may be a personal computer, a server, a network device, etc.) to execute the methods described in all embodiments or some parts of the embodiments.
[103] Finally, it is to be noted that the above embodiments are merely used to illustrate the technical solutions of the present invention, and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that the technical solutions described in the foregoing embodiments are modified, or some technical features are equivalently replaced. However, these modifications and replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of various embodiments of the present invention.
Claims (9)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
NL2029769A NL2029769B1 (en) | 2021-11-16 | 2021-11-16 | Method and system for generating credit rating of agricultural specialized service provider |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
NL2029769A NL2029769B1 (en) | 2021-11-16 | 2021-11-16 | Method and system for generating credit rating of agricultural specialized service provider |
Publications (1)
Publication Number | Publication Date |
---|---|
NL2029769B1 true NL2029769B1 (en) | 2023-06-09 |
Family
ID=86729200
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
NL2029769A NL2029769B1 (en) | 2021-11-16 | 2021-11-16 | Method and system for generating credit rating of agricultural specialized service provider |
Country Status (1)
Country | Link |
---|---|
NL (1) | NL2029769B1 (en) |
-
2021
- 2021-11-16 NL NL2029769A patent/NL2029769B1/en active
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Fleming et al. | Is big data for big farming or for everyone? Perceptions in the Australian grains industry | |
CN111737495B (en) | Middle-high-end talent intelligent recommendation system and method based on domain self-classification | |
US20220005125A1 (en) | Systems and methods for collecting and processing alternative data sources for risk analysis and insurance | |
Aguwa et al. | Modeling of fuzzy-based voice of customer for business decision analytics | |
Jiang et al. | A multi-objective PSO approach of mining association rules for affective design based on online customer reviews | |
Schoormann et al. | Artificial intelligence for sustainability—a systematic review of information systems literature | |
US20210120731A1 (en) | Multi-dimension artificial intelligence agriculture advisor | |
CN115423637A (en) | Insurance industry potential customer mining method, insurance industry potential customer mining device and storage medium | |
Lukosius et al. | Marketing theory and big data | |
Liao et al. | Reimagining multi-criterion decision making by data-driven methods based on machine learning: A literature review | |
Singh et al. | Automated machine learning (AutoML): an overview of opportunities for application and research | |
WO2019144035A1 (en) | Systems and methods for collecting and processing alternative data sources for risk analysis and insurance | |
CN115983900A (en) | Method, apparatus, device, medium, and program product for constructing user marketing strategy | |
Yu Chung Wang et al. | Enterprise systems, emerging technologies, and the data-driven knowledge organisation | |
Duarte et al. | Machine Learning and Marketing: A Literature Review. | |
NL2029769B1 (en) | Method and system for generating credit rating of agricultural specialized service provider | |
US20200364275A1 (en) | Characterizing international orientation | |
Bedruz et al. | Analysis of big data technologies for policy building in the Philippines | |
Rajabzadeh et al. | Modelling factors influencing IoT adoption: With a focus on agricultural logistics operations | |
Bączkiewicz et al. | Towards reliable results-a comparative analysis of selected MCDA techniques in the camera selection problem | |
Bhardwaj et al. | Decision-making optimisation in insurance market using big data analytics survey | |
Martins et al. | A fuzzy AHP analysis of potential criteria for initiatives in digital transformation for agribusiness | |
Mahalle et al. | Data Acquisition and Preparation | |
Hidayat et al. | Decision support system for fish quarantine measures in Indonesia | |
Behera et al. | Machine Learning for Customer Segmentation Through Bibliometric Approach |