CN116452297A - Intelligent recommendation method and system based on business market data - Google Patents
Intelligent recommendation method and system based on business market data Download PDFInfo
- Publication number
- CN116452297A CN116452297A CN202310425256.6A CN202310425256A CN116452297A CN 116452297 A CN116452297 A CN 116452297A CN 202310425256 A CN202310425256 A CN 202310425256A CN 116452297 A CN116452297 A CN 116452297A
- Authority
- CN
- China
- Prior art keywords
- resource
- attribute data
- data
- difference function
- resource attribute
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000005457 optimization Methods 0.000 claims abstract description 19
- 238000012163 sequencing technique Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 167
- 239000013598 vector Substances 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000003860 storage Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 241000490229 Eucephalus Species 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and discloses an intelligent recommendation method and system based on business market data, wherein the intelligent recommendation method comprises the following steps: extracting resource attribute data and corresponding user attribute data from the history record data of the business market; constructing a characteristic difference function of each resource attribute data, and calculating the function weight of each characteristic difference function; generating a target difference function according to the function weight of the characteristic difference function; performing differential optimization on the pre-constructed initial recommendation model by utilizing the historical record data and the target difference function to obtain an intelligent recommendation model; and recommending and sequencing the resource list to be recommended by using the intelligent recommendation model to obtain a resource recommendation sequence. The method and the device can improve the accuracy of intelligent resource recommendation.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an intelligent recommendation method and system based on business market data.
Background
The business market (business marketing) is comprised of an organization that purchases goods and services and uses them to produce other goods or services for sale, lease, or supply to others. Organizations involved in business not only sell products, but also buy a large number of raw materials, manufacturing parts, devices, auxiliary equipment, supplies and business services, and when companies prepare to sell raw materials, computers and other goods to buyers, the needs, resources, policies and purchasing processes of these purchasing organizations must be known, so that the buyer needs are accurately known, goods are accurately recommended to the buyers, and the success rate of transactions is improved.
However, with the advent of the information age, the data volume of the business market data has increased dramatically, and the business market data contains various information, so that the retrieval efficiency and quality of target data are greatly affected, and the satisfaction degree of users is reduced.
Disclosure of Invention
The invention provides an intelligent recommendation method and system based on business market data, and mainly aims to solve the problem of poor accuracy of resource intelligent recommendation.
In order to achieve the above object, the present invention provides an intelligent recommendation method based on business market data, comprising:
acquiring historical record data of a business market, and extracting resource attribute data and user attribute data corresponding to the resource attribute data from the historical record data;
constructing a characteristic difference function of each resource attribute data according to the resource attribute data and the user attribute data corresponding to the resource attribute data, and calculating the function weight of each characteristic difference function;
generating a target difference function according to the characteristic difference function and the function weight of the characteristic difference function;
performing differential optimization on the pre-constructed initial recommendation model by utilizing the historical record data and the target difference function to obtain an intelligent recommendation model;
and acquiring a resource list to be recommended, and recommending and sequencing the resource list to be recommended by utilizing the intelligent recommendation model to obtain a resource recommendation sequence.
Optionally, the extracting resource attribute data and user attribute data corresponding to the resource attribute data from the history data includes:
extracting resource basic data from the historical record data, and determining resource attribute data according to the data attribute of the resource basic data;
and extracting consumption data in the historical record data, and performing attribute matching according to the consumption data and the resource attribute data to obtain user attribute data corresponding to the resource attribute data.
Optionally, the constructing a feature difference function of each resource attribute data according to the resource attribute data and the user attribute data corresponding to the resource attribute data includes:
carrying out data standardization on the resource attribute data and the user attribute data corresponding to the resource attribute data to obtain standard resource attribute data and standard user attribute data corresponding to the standard resource attribute data;
extracting data features of the resource attribute data and data features of the user resource attribute data according to the standard resource attribute data and standard user resource attribute data corresponding to the standard resource attribute data, and calculating feature average values of the data features;
and constructing a characteristic difference function of each resource attribute data according to the data characteristics and the characteristic mean value.
Optionally, the feature difference function of each resource attribute data is constructed using the following formula:
wherein F (A) represents a characteristic difference function corresponding to the A-th resource attribute data in the resource attribute data, A i The first data characteristic representing the A-th resource attribute datai column vectors, n represents the total number of column vectors, A i ' feature mean value representing data feature of A-th resource attribute data, B i Data characteristics representing user resource attribute data corresponding to the A-th resource attribute data, B i ' represents the characteristic mean of the user resource attribute data corresponding to the A-th resource attribute data.
Optionally, the calculating the function weight of each characteristic difference function includes:
calculating the occurrence frequency of target resource attribute data corresponding to the characteristic difference function and target user attribute data corresponding to the target resource attribute data in the history data;
calculating the resource weight of the target resource attribute data and the user weight of the target user attribute data according to the occurrence frequency;
and calculating the average value of the resource weight and the user weight to obtain the function weight of each characteristic difference function.
Optionally, the objective difference function is generated using the following formula:
wherein minS represents the objective difference function, F (A) represents the A-th characteristic difference function, ω A The function weight representing the A-th feature difference function, K representing the total number of feature difference functions.
Optionally, the performing differential optimization on the pre-constructed initial recommendation model by using the historical record data and the objective difference function to obtain an intelligent recommendation model includes:
generating an initialized population according to the historical record data, and calculating a function difference value of the initialized population by utilizing the target difference function;
performing differential variation on the initialized population according to the function difference value to obtain a variation population, and performing cross selection on the variation population to obtain an updated population;
iteratively updating the updated population until the function difference value of the updated population is smaller than a preset difference value threshold, and taking the updated population as an optimized model parameter corresponding to the initial recommended model;
and carrying out parameter assignment on the initial recommendation model according to the optimization model parameters to obtain an intelligent recommendation model.
Optionally, the recommending and sorting the to-be-recommended resource list by using the intelligent recommending model to obtain a resource recommending sequence includes:
converting the resources to be recommended in the resource list to be recommended into resource vectors, and calculating hidden layer results of the resource vectors by utilizing hidden layers in the intelligent recommendation model;
calculating the output sum of the hidden layer result and the weighted sum result by utilizing a sum layer in the intelligent recommendation model to obtain a first estimated value and a second estimated value of the resource to be recommended;
and sequencing the resources to be recommended according to the first estimated value and the second estimated value to obtain a resource recommendation sequence.
Optionally, the hidden layer result of the resource vector is calculated using the following formula:
wherein alpha is j A hidden layer result representing the j-th hidden layer of the resource vector, X' representing the resource vector, X j And representing a corresponding learning sample in a j-th hidden layer in the intelligent recommendation model, wherein sigma and lambda represent model parameters of the intelligent recommendation model.
In order to solve the above problems, the present invention further provides an intelligent recommendation system based on business market data, the system comprising:
the data extraction module is used for acquiring historical record data of the business market and extracting resource attribute data and user attribute data corresponding to the resource attribute data from the historical record data;
the characteristic difference function calculation module is used for constructing a characteristic difference function of each resource attribute data according to the resource attribute data and the user attribute data corresponding to the resource attribute data, and calculating the function weight of each characteristic difference function;
the target difference function generation module is used for generating a target difference function according to the characteristic difference function and the function weight of the characteristic difference function;
the intelligent recommendation model generation module is used for carrying out differential optimization on the pre-constructed initial recommendation model by utilizing the historical record data and the target difference function to obtain an intelligent recommendation model;
and the resource recommendation module is used for acquiring a resource list to be recommended, and recommending and sequencing the resource list to be recommended by utilizing the intelligent recommendation model to obtain a resource recommendation sequence.
According to the embodiment of the invention, the resource attribute data and the corresponding user attribute data in the historical record data are extracted, so that the push data of the resource and the consumption tendency of the corresponding user can be accurately obtained, and more accurate resource recommendation is realized; constructing a characteristic difference function of each resource attribute data according to the resource attribute data and the corresponding user attribute data, calculating the function weight of each characteristic difference function, determining the resource attribute data with higher matching degree according to the characteristic difference, constructing a target difference function through the function weight of each characteristic function, further obtaining a more accurate initialized population and a target function of an intelligent recommendation model through historical record data, improving the matching degree between recommended resources and users, and further realizing accurate recommendation of the intelligent recommendation model; according to the intelligent recommendation model, intelligent recommendation ordering can be performed on the to-be-recommended resource list, and a more accurate resource recommendation sequence is obtained. Therefore, the intelligent recommendation method and system based on the business market data can solve the problem of poor accuracy of intelligent recommendation of resources.
Drawings
FIG. 1 is a flow chart of an intelligent recommendation method based on business market data according to an embodiment of the present invention;
FIG. 2 is a flow chart of a feature difference function construction according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of differential optimization of an initial recommendation model according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of an intelligent recommendation system based on business market data according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides an intelligent recommendation method based on business market data. The execution subject of the intelligent recommendation method based on the business market data comprises, but is not limited to, at least one of a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the intelligent recommendation method based on the business market data may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of an intelligent recommendation method based on business market data according to an embodiment of the invention is shown. In this embodiment, the intelligent recommendation method based on the business market data includes:
s1, acquiring historical record data of a business market, and extracting resource attribute data and user attribute data corresponding to the resource attribute data from the historical record data.
In the embodiment of the present invention, the historical data of the business market may be recorded data within 5 years, 3 years or two years of the target business market, where the historical data includes resource basic data of the seller, such as commodity types, numbers, commodity grades, and the like, and consumption data of each user, so as to extract each resource attribute data and corresponding user attribute data from the historical data.
In the embodiment of the present invention, the extracting resource attribute data and user attribute data corresponding to the resource attribute data from the history data includes:
extracting resource basic data from the historical record data, and determining resource attribute data according to the data attribute of the resource basic data;
and extracting consumption data in the historical record data, and performing attribute matching according to the consumption data and the resource attribute data to obtain user attribute data corresponding to the resource attribute data.
In the embodiment of the invention, the resource basic data represents initial data of each resource in the history data, such as category of commodity type and basic quantity of commodity, so that corresponding resource attribute data can be determined by each basic data, and the resource attribute data corresponding to the resource basic data can be determined by utilizing a preset resource attribute set; and extracting consumption data in the historical record data, determining the consumption resource attribute of the user according to the consumption data, further obtaining user attribute data, and corresponding the user attribute data with the attribute of the aster resource attribute data to obtain user attribute data corresponding to the resource attribute data.
In the embodiment of the invention, the push data of the resource and the consumption tendency of the corresponding user can be accurately obtained by extracting the user attribute data corresponding to the resource attribute data predicted by the resource attribute data in the historical record data, so as to realize more accurate resource recommendation.
S2, constructing a characteristic difference function of each resource attribute data according to the resource attribute data and the user attribute data corresponding to the resource attribute data, and calculating the function weight of each characteristic difference function.
In the embodiment of the invention, the characteristic difference function is used for judging the difference between the resource attribute data and the user attribute data according to the characteristic difference between the resource attribute data and the user attribute data corresponding to the resource attribute data, wherein each resource attribute data corresponds to one difference function, and further the resource attribute data with high user satisfaction is obtained.
In the embodiment of the present invention, referring to fig. 2, the constructing a feature difference function of each resource attribute data according to the resource attribute data and the user attribute data corresponding to the resource attribute data includes:
s21, carrying out data standardization on the resource attribute data and the user attribute data corresponding to the resource attribute data to obtain standard resource attribute data and standard user resource attribute data corresponding to the standard resource attribute data;
s22, extracting data features of the resource attribute data and data features of the user resource attribute data according to the standard resource attribute data and standard user resource attribute data corresponding to the standard resource attribute data, and calculating feature average values of the data features;
s23, constructing a characteristic difference function of each resource attribute data according to the data characteristics and the characteristic mean value.
In the embodiment of the invention, standardization can be performed according to the data types of the resource attribute data and the corresponding user attribute data, for example, non-numeric data is subjected to One-hot (One-hot) coding and converted into values of 0 and 1, and then the resource attribute data and the corresponding user attribute data are subjected to data outlier processing and normalization so as to remove the dimensions of the resource attribute data and the corresponding user attribute data and obtain standard resource attribute data and the corresponding standard user resource attribute data.
In the embodiment of the invention, the data characteristics represent the data characteristics of standard resource attribute data and the data characteristics of corresponding standard user attribute data, and specifically, the embodiment of the invention can utilize a convolutional neural network to extract the data characteristics and generate the characteristic difference function of each resource data in the resource attribute data by calculating the data characteristics and the corresponding characteristic mean value.
In the embodiment of the invention, the characteristic difference function of each resource attribute data is constructed by using the following formula:
wherein F (A) represents a characteristic difference function corresponding to the A-th resource attribute data in the resource attribute data, A i An ith column vector representing data characteristics of the A-th resource attribute data, n representing the total number of column vectors, A i ' feature mean value representing data feature of A-th resource attribute data, B i Data characteristics representing user resource attribute data corresponding to the A-th resource attribute data, B i ' represents the characteristic mean of the user resource attribute data corresponding to the A-th resource attribute data.
In the embodiment of the invention, the function weight represents the influence of each characteristic difference function on the resource recommendation, and the larger the weight is, the larger the influence on the final resource recommendation is, otherwise, the smaller the weight is, the smaller the influence on the final resource recommendation is, so that importance allocation is required to be carried out on each characteristic difference function according to the function characteristics, and further more accurate resource recommendation is realized.
In an embodiment of the present invention, the calculating the function weight of each feature difference function includes:
calculating the occurrence frequency of target resource attribute data corresponding to the characteristic difference function and target user attribute data corresponding to the target resource attribute data in the history data;
calculating the resource weight of the target resource attribute data and the user weight of the target user attribute data according to the occurrence frequency;
and calculating the average value of the resource weight and the user weight to obtain the function weight of each characteristic difference function.
In the embodiment of the invention, each characteristic difference function corresponds to different resource attribute data and user attribute data, and each resource attribute data and user attribute data have different data weights, so that the function weight of each characteristic difference function is comprehensively calculated according to the resource weight of the resource attribute data and the user weight of the user attribute data, and the precision of function weight distribution is improved.
S3, generating a target difference function according to the characteristic difference function and the function weight of the characteristic difference function.
In the embodiment of the invention, the target difference function is a characteristic difference function with highest matching degree between the resource attribute data and the corresponding user attribute data, and the target difference function is selected according to the characteristic difference function and the function weight.
In the embodiment of the invention, the target difference function is generated by using the following formula:
wherein minS represents the objective difference function, F (A) represents the A-th characteristic difference function, ω A The function weight representing the A-th feature difference function, K representing the total number of feature difference functions.
In the embodiment of the invention, the target of the resource recommendation is determined according to the target difference function, namely, the difference of the matching degree between the resource recommendation and the user is reduced to the minimum, and further, the more accurate resource recommendation is realized.
And S4, performing differential optimization on the pre-constructed initial recommendation model by utilizing the historical record data and the target difference function to obtain an intelligent recommendation model.
In the embodiment of the invention, the initial recommendation model can be a generalized regression neural model (Generalized Regression Neural Network, GRNN), the generalized regression neural network model comprises an input layer, a hidden layer, a summation layer and an output layer, the output layer acquires input characteristics, the hidden layer acquires the result of the hidden layer through an activation function, the summation layer sums the result of the hidden layer, the output layer outputs the predicted result of the initial recommendation model, model parameters such as a smoothing factor of neurons in the hidden layer and a kernel function center have great influence on the precision of the initial recommendation model, a target difference function is used as a target function of the initial recommendation model, and a difference value of the target function is used as a differential optimization target of the initial recommendation model, so that an intelligent recommendation model with higher intelligent recommendation model precision is obtained, and the matching degree between resource recommendation and users is improved.
In the embodiment of the invention, the initial recommendation model is trained by utilizing the historical record data, so that model parameters in the initial recommendation model are optimized, an intelligent recommendation model meeting optimization conditions is obtained, and further intelligent recommendation is performed on resources to be recommended.
In the embodiment of the invention, the differential optimization is a heuristic random search algorithm based on population difference, and an intelligent recommendation model is obtained by utilizing poor variation of the population until model parameters of an initial recommendation model meet the requirements.
In the embodiment of the present invention, referring to fig. 3, the performing differential optimization on the pre-constructed initial recommendation model by using the historical record data and the objective difference function to obtain an intelligent recommendation model includes:
s31, generating an initialized population according to the historical record data, and calculating a function difference value of the initialized population by using the target difference function;
s32, carrying out differential variation on the initialized population according to the function difference value to obtain a variation population, and carrying out cross selection on the variation population to obtain an updated population;
s33, carrying out iterative updating on the updated population until the function difference value of the updated population is smaller than a preset difference value threshold, and taking the updated population as an optimized model parameter corresponding to the initial recommended model;
and S34, carrying out parameter assignment on the initial recommendation model according to the optimization model parameters to obtain an intelligent recommendation model.
In the embodiment of the invention, the initialization population is formed by a plurality of model parameter results of the initial recommendation model, so that the initialization population which is more in line with the actual is generated according to the historical record data, the calculation efficiency can be improved, the differential optimization effect can be effectively improved, the more accurate intelligent recommendation model can be obtained, for example, the numerical upper limit and the numerical lower limit of the initialization population can be determined according to the characteristic difference function of each resource attribute data in the historical record data, and the initialization population is generated within the numerical upper limit and the numerical lower limit.
In the embodiment of the invention, the differential mutation is to randomly select two different individuals in a population, and synthesize the two different individuals with the individuals to be mutated after scaling to obtain a mutated population, randomly select the individuals in the population from the mutated population through differential cross selection, randomly generate new individuals in a probability mode, select better individuals from the new individuals as an updated population, and specifically select the updated population according to the value of an fitness function by using a greedy algorithm, wherein the reciprocal of a target difference function in an initial recommendation model can be used as the fitness function.
In the embodiment of the invention, the initial recommendation model is subjected to differential optimization by utilizing the historical record data and the target difference function, and the obtained model parameters when the function difference value of the large updated population is smaller than the preset difference threshold value enable the matching degree of the resource and the user to date to be higher, so that a more accurate initialization population can be obtained, further more accurate model parameters can be obtained, and the recommendation accuracy of the intelligent recommendation model is improved.
S5, acquiring a resource list to be recommended, and recommending and sorting the resource list to be recommended by using the intelligent recommendation model to obtain a resource recommendation sequence.
In the embodiment of the invention, the resource list to be recommended is a resource list to be recommended, for example, resources possibly existing in commercial markets such as educational resources, building material resources, service resources and the like, and the intelligent recommendation model is utilized to conduct recommendation sequencing on the resource list to be recommended, so that the accuracy of resource recommendation is improved.
In the embodiment of the present invention, the recommending and sorting the resource list to be recommended by using the intelligent recommending model to obtain a resource recommending sequence includes:
converting the resources to be recommended in the resource list to be recommended into resource vectors, and calculating hidden layer results of the resource vectors by utilizing hidden layers in the intelligent recommendation model;
calculating the output sum of the hidden layer result and the weighted sum result by utilizing a sum layer in the intelligent recommendation model to obtain a first estimated value and a second estimated value of the resource to be recommended;
and sequencing the resources to be recommended according to the first estimated value and the second estimated value to obtain a resource recommendation sequence.
In the embodiment of the invention, the hidden layer result of the resource vector is calculated by using the following formula:
wherein alpha is j A hidden layer result representing the j-th hidden layer of the resource vector, X' representing the resource vector, X j And representing a corresponding learning sample in a j-th hidden layer in the intelligent recommendation model, wherein sigma and lambda represent model parameters of the intelligent recommendation model.
In the embodiment of the invention, the hidden layer result is obtained by calculating the hidden result of each hidden layer, the sum of the hidden layer results is used as a first estimated value, the weighted sum result of the hidden layer results is used as a second estimated value, the ratio between the second estimated value and the first estimated value is calculated, the ratio is used as the recommendation score of each resource to be recommended, and the resources to be recommended in the list to be recommended are further sequenced, so that a resource recommendation sequence is obtained.
According to the embodiment of the invention, the recommending and sorting precision of the resources to be recommended can be improved by recommending and sorting the resource list to be recommended through the intelligent recommending model, so that more accurate resource recommendation is realized, and meanwhile, the satisfaction degree of the resource provider to be recommended and the demand party is improved.
According to the embodiment of the invention, the resource attribute data and the corresponding user attribute data in the historical record data are extracted, so that the push data of the resource and the consumption tendency of the corresponding user can be accurately obtained, and more accurate resource recommendation is realized; constructing a characteristic difference function of each resource attribute data according to the resource attribute data and the corresponding user attribute data, calculating the function weight of each characteristic difference function, determining the resource attribute data with higher matching degree according to the characteristic difference, constructing a target difference function through the function weight of each characteristic function, further obtaining a more accurate initialized population and a target function of an intelligent recommendation model through historical record data, improving the matching degree between recommended resources and users, and further realizing accurate recommendation of the intelligent recommendation model; according to the intelligent recommendation model, intelligent recommendation ordering can be performed on the to-be-recommended resource list, and a more accurate resource recommendation sequence is obtained. Therefore, the intelligent recommendation method based on the business market data can solve the problem of poor accuracy of intelligent recommendation of resources.
FIG. 4 is a functional block diagram of an intelligent recommendation system based on business market data according to an embodiment of the present invention.
The intelligent recommendation system 400 based on business market data can be installed in electronic equipment. Depending on the implementation, the intelligent recommendation system 400 based on the business market data may include a data extraction module 401, a feature difference function calculation module 402, a target difference function generation module 403, an intelligent recommendation model generation module 404, and a resource recommendation module 405. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the data extraction module 401 is configured to obtain history data of a business market, and extract resource attribute data and user attribute data corresponding to the resource attribute data from the history data;
the feature difference function calculation module 402 is configured to construct a feature difference function of each resource attribute data according to the resource attribute data and user attribute data corresponding to the resource attribute data, and calculate a function weight of each feature difference function;
the target difference function generating module 403 is configured to generate a target difference function according to the feature difference function and a function weight of the feature difference function;
the intelligent recommendation model generating module 404 is configured to perform differential optimization on the pre-constructed initial recommendation model by using the history data and the target difference function to obtain an intelligent recommendation model;
the resource recommendation module 405 is configured to obtain a to-be-recommended resource list, and perform recommendation ordering on the to-be-recommended resource list by using the intelligent recommendation model to obtain a resource recommendation sequence.
In detail, each module in the intelligent recommendation system 400 based on business market data in the embodiment of the present invention adopts the same technical means as the intelligent recommendation method based on business market data described in fig. 1 to 3, and can produce the same technical effects, which are not described herein.
The present invention also provides an electronic device that may include a processor, a memory, a communication bus, and a communication interface, and may further include a computer program stored in the memory and executable on the processor, such as an intelligent recommendation method program based on business market data.
The processor may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and the like. The processor is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, executes or executes programs or modules stored in the memory (for example, executes intelligent recommendation method programs based on business market data, etc.), and invokes data stored in the memory to perform various functions of the electronic device and process data.
The memory includes at least one type of readable storage medium including flash memory, removable hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory may also include both internal storage units and external storage devices of the electronic device. The memory may be used not only for storing application software installed in an electronic device and various types of data, such as codes of intelligent recommendation method programs based on business market data, but also for temporarily storing data that has been output or is to be output.
The communication bus may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory and at least one processor or the like.
The communication interface is used for communication between the electronic equipment and other equipment, and comprises a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Only an electronic device having components is shown, and it will be understood by those skilled in the art that the structures shown in the figures do not limit the electronic device, and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for powering the respective components, and the power source may be logically connected to the at least one processor 501 through a power management system, so as to perform functions of charge management, discharge management, and power consumption management through the power management system. The power supply may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
Specifically, the specific implementation method of the above instruction by the processor may refer to descriptions of related steps in the corresponding embodiment of the drawings, which are not repeated herein.
Further, the electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, implements the steps of the business market data-based intelligent recommendation method and system as described above:
storage media includes both permanent and non-permanent, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media may include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, read only compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, system and method may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. Multiple units or systems as set forth in the system claims may also be implemented by means of one unit or system in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, 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 preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. An intelligent recommendation method based on business market data, which is characterized by comprising the following steps:
acquiring historical record data of a business market, and extracting resource attribute data and user attribute data corresponding to the resource attribute data from the historical record data;
constructing a characteristic difference function of each resource attribute data according to the resource attribute data and the user attribute data corresponding to the resource attribute data, and calculating the function weight of each characteristic difference function;
generating a target difference function according to the characteristic difference function and the function weight of the characteristic difference function;
performing differential optimization on the pre-constructed initial recommendation model by utilizing the historical record data and the target difference function to obtain an intelligent recommendation model;
and acquiring a resource list to be recommended, and recommending and sequencing the resource list to be recommended by utilizing the intelligent recommendation model to obtain a resource recommendation sequence.
2. The intelligent recommendation method based on business market data according to claim 1, wherein the extracting resource attribute data and user attribute data corresponding to the resource attribute data from the history data comprises:
extracting resource basic data from the historical record data, and determining resource attribute data according to the data attribute of the resource basic data;
and extracting consumption data in the historical record data, and performing attribute matching according to the consumption data and the resource attribute data to obtain user attribute data corresponding to the resource attribute data.
3. The intelligent recommendation method based on business market data according to claim 1, wherein the constructing a feature difference function of each resource attribute data according to the resource attribute data and the user attribute data corresponding to the resource attribute data comprises:
carrying out data standardization on the resource attribute data and the user attribute data corresponding to the resource attribute data to obtain standard resource attribute data and standard user attribute data corresponding to the standard resource attribute data;
extracting data features of the resource attribute data and data features of the user resource attribute data according to the standard resource attribute data and standard user resource attribute data corresponding to the standard resource attribute data, and calculating feature average values of the data features;
and constructing a characteristic difference function of each resource attribute data according to the data characteristics and the characteristic mean value.
4. The intelligent recommendation method based on business market data according to claim 3, wherein the feature difference function of each resource attribute data is constructed using the following formula:
wherein F (A) represents a characteristic difference function corresponding to the A-th resource attribute data in the resource attribute data, A i An ith column vector representing data characteristics of the A-th resource attribute data, n representing the total number of column vectors, A i ′ Feature mean value of data feature representing A-th resource attribute data, B i Data characteristics representing user resource attribute data corresponding to the A-th resource attribute data, B i ′ And representing the characteristic mean value of the user resource attribute data corresponding to the A-th resource attribute data.
5. The intelligent recommendation method based on business market data according to claim 1, wherein said calculating a function weight for each of said feature difference functions comprises:
calculating the occurrence frequency of target resource attribute data corresponding to the characteristic difference function and target user attribute data corresponding to the target resource attribute data in the history data;
calculating the resource weight of the target resource attribute data and the user weight of the target user attribute data according to the occurrence frequency;
and calculating the average value of the resource weight and the user weight to obtain the function weight of each characteristic difference function.
6. The intelligent recommendation method based on business market data according to claim 1, wherein the objective difference function is generated using the following formula:
wherein minS represents the objective difference function, F (A) represents the A-th characteristic difference function, ω A The function weight representing the A-th feature difference function, K representing the total number of feature difference functions.
7. The intelligent recommendation method based on business market data according to claim 1, wherein the performing differential optimization on the pre-constructed initial recommendation model by using the history data and the objective difference function to obtain the intelligent recommendation model comprises:
generating an initialized population according to the historical record data, and calculating a function difference value of the initialized population by utilizing the target difference function;
performing differential variation on the initialized population according to the function difference value to obtain a variation population, and performing cross selection on the variation population to obtain an updated population;
iteratively updating the updated population until the function difference value of the updated population is smaller than a preset difference value threshold, and taking the updated population as an optimized model parameter corresponding to the initial recommended model;
and carrying out parameter assignment on the initial recommendation model according to the optimization model parameters to obtain an intelligent recommendation model.
8. The intelligent recommendation method based on business market data according to claim 1, wherein said using the intelligent recommendation model to perform recommendation ranking on the to-be-recommended resource list to obtain a resource recommendation sequence comprises:
converting the resources to be recommended in the resource list to be recommended into resource vectors, and calculating hidden layer results of the resource vectors by utilizing hidden layers in the intelligent recommendation model;
calculating the output sum of the hidden layer result and the weighted sum result by utilizing a sum layer in the intelligent recommendation model to obtain a first estimated value and a second estimated value of the resource to be recommended;
and sequencing the resources to be recommended according to the first estimated value and the second estimated value to obtain a resource recommendation sequence.
9. The business market data based intelligent recommendation method according to claim 8, wherein the hidden layer result of the resource vector is calculated using the following formula:
wherein alpha is j A hidden layer result, X, representing the j-th hidden layer of the resource vector ′ Representing resource vectors, X j And representing a corresponding learning sample in a j-th hidden layer in the intelligent recommendation model, wherein sigma and lambda represent model parameters of the intelligent recommendation model.
10. An intelligent recommendation system based on business market data, the system comprising:
the data extraction module is used for acquiring historical record data of the business market and extracting resource attribute data and user attribute data corresponding to the resource attribute data from the historical record data;
the characteristic difference function calculation module is used for constructing a characteristic difference function of each resource attribute data according to the resource attribute data and the user attribute data corresponding to the resource attribute data, and calculating the function weight of each characteristic difference function;
the target difference function generation module is used for generating a target difference function according to the characteristic difference function and the function weight of the characteristic difference function;
the intelligent recommendation model generation module is used for carrying out differential optimization on the pre-constructed initial recommendation model by utilizing the historical record data and the target difference function to obtain an intelligent recommendation model;
and the resource recommendation module is used for acquiring a resource list to be recommended, and recommending and sequencing the resource list to be recommended by utilizing the intelligent recommendation model to obtain a resource recommendation sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310425256.6A CN116452297A (en) | 2023-04-18 | 2023-04-18 | Intelligent recommendation method and system based on business market data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310425256.6A CN116452297A (en) | 2023-04-18 | 2023-04-18 | Intelligent recommendation method and system based on business market data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116452297A true CN116452297A (en) | 2023-07-18 |
Family
ID=87131778
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310425256.6A Withdrawn CN116452297A (en) | 2023-04-18 | 2023-04-18 | Intelligent recommendation method and system based on business market data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116452297A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116720896A (en) * | 2023-08-10 | 2023-09-08 | 青岛阿斯顿工程技术转移有限公司 | Enterprise scientific and technological service personalized recommendation method and system based on big data |
-
2023
- 2023-04-18 CN CN202310425256.6A patent/CN116452297A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116720896A (en) * | 2023-08-10 | 2023-09-08 | 青岛阿斯顿工程技术转移有限公司 | Enterprise scientific and technological service personalized recommendation method and system based on big data |
| CN116720896B (en) * | 2023-08-10 | 2023-10-24 | 青岛阿斯顿工程技术转移有限公司 | Enterprise scientific and technological service personalized recommendation method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110111139B (en) | Behavior prediction model generation method and device, electronic equipment and readable medium | |
| US8732015B1 (en) | Social media pricing engine | |
| CN109840730B (en) | Method and device for data prediction | |
| US20200234218A1 (en) | Systems and methods for entity performance and risk scoring | |
| CN112016796B (en) | Comprehensive risk score request processing method and device and electronic equipment | |
| CN109213936B (en) | Commodity searching method and device | |
| CN110135976A (en) | User's portrait generation method, device, electronic equipment and computer-readable medium | |
| CN111966886A (en) | Object recommendation method, object recommendation device, electronic equipment and storage medium | |
| US11367117B1 (en) | Artificial intelligence system for generating network-accessible recommendations with explanatory metadata | |
| CN115391669B (en) | Intelligent recommendation method and device and electronic equipment | |
| Tsai et al. | Comparing the Apple iPad and non-Apple camp tablet PCs: a multicriteria decision analysis | |
| CN110750697A (en) | Merchant classification method, device, equipment and storage medium | |
| CN116452297A (en) | Intelligent recommendation method and system based on business market data | |
| CN113591881B (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN111340522A (en) | Resource recommendation method, device, server and storage medium | |
| US11334935B2 (en) | Method, system, and manufacture for light hypergraph based recommendation | |
| CN113656690A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| WO2020150597A1 (en) | Systems and methods for entity performance and risk scoring | |
| Chu et al. | Deep graph embedding for ranking optimization in e-commerce | |
| CN115049383A (en) | Combined payment recommendation method and device, electronic equipment and storage medium | |
| CN114429384A (en) | Intelligent product recommendation method and system based on e-commerce platform | |
| CN113159877A (en) | Data processing method, device, system and computer readable storage medium | |
| Navarro-Barrientos et al. | Characterization and analysis of sales data for the semiconductor market: An expert system approach | |
| US11941076B1 (en) | Intelligent product sequencing for category trees | |
| CN113592606B (en) | Product recommendation method, device, equipment and storage medium based on multiple decisions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230718 |
|
| WW01 | Invention patent application withdrawn after publication |