Method, apparatus, electronic device and readable storage medium for benefit distribution

Abstract

The present invention relates to artificial intelligence technology, and discloses a method for issuing rights and interests, including: constructing a blank matrix according to the quantity of rights and interests in historical rights and interests usage data; calculating the rights and interests utilization rate of each right and interest according to the acquisition times and actual usage times, and filling the blank matrix with the rights and interests utilization rate to obtain a rights and interests utilization rate matrix; performing multiple random samplings on the elements in the rights and interests utilization rate matrix to obtain multiple subset matrices of the rights and interests utilization rate matrix; using a pre-constructed user classification model to extract matrix features from each subset matrix to obtain matrix eigenvalues; using the matrix eigenvalues to screen all subset matrices to obtain a target subset matrix; and screening rights and interests according to the target subset matrix to issue them to users. The present invention also relates to blockchain technology, and the historical rights and interests usage data can be stored in a blockchain node. The present invention also proposes a rights and interests issuing device, equipment, and medium. The present invention can improve the accuracy of rights and interests issuance.

Description

Technical Field

[0001] The present invention relates to artificial intelligence technology, and in particular, to a method, device, electronic device and readable storage medium for issuing rights and interests. Background Art

[0002] With the gradual increase of people's needs, the differences between products in the market are gradually decreasing. Therefore, product suppliers such as enterprises or companies will regularly send some rights and interests outside the products to users to increase user stickiness, such as coupons, cash vouchers, etc.

[0003] The existing methods for issuing rights and interests are mostly based on the popularity of products, that is, by counting the usage popularity of multiple current products, and uniformly issuing rights and interests to all users according to the usage popularity. In this method, the large differences in the needs of different users are not taken into account, and only the popularity of products is used to determine how to issue rights and interests, resulting in a low accuracy of rights and interests issuance, issuing rights and interests that users do not need to users, reducing the user experience, and reducing user stickiness. Therefore, how to improve the accuracy of rights and interests issuance has become an urgent problem to be solved. Summary of the Invention

[0004] The present invention provides a method, device, electronic device and computer-readable storage medium for issuing rights and interests, and its main purpose is to improve the accuracy of rights and interests issuance.

[0005] To achieve the above object, a method for issuing rights and interests provided by the present invention includes:

[0006] Obtain the historical rights and interests usage data of the user, where the historical rights and interests usage data includes: the acquisition times and actual usage times of different rights and interests;

[0007] Construct a blank matrix according to the number of rights and interests in the historical rights and interests usage data;

[0008] Calculate the rights and interests usage rate of each right and interest in the historical rights and interests usage data according to the acquisition times and the actual usage times, and use the rights and interests usage rate to fill the blank matrix to obtain a rights and interests usage rate matrix;

[0009] Perform multiple random samplings on the elements in the rights and interests usage rate matrix according to a preset quantity to obtain multiple subset matrices of the rights and interests usage rate matrix;

[0010] Use a pre-constructed user classification model to extract matrix features from each subset matrix in the multiple subset matrices to obtain matrix feature values;

[0011] Use the matrix feature values to screen all the subset matrices to obtain a target subset matrix;

[0012] Screen all rights and interests in the historical rights and interests usage data according to the target subset matrix, and distribute the screened rights and interests to the user.

[0013] Optionally, constructing a blank matrix according to the number of rights and interests in the historical rights and interests usage data includes:

[0014] Construct a blank matrix with the same number of elements according to the number of rights and interests in the historical rights and interests usage data;

[0015] Use all the rights and interests in the historical rights and interests usage data to label each element in the blank matrix with a right and interest in turn.

[0016] Optionally, calculating the usage rate of each right and interest in the historical rights and interests usage data according to the acquisition times and the actual usage times, and filling the blank matrix with the usage rate to obtain a usage rate matrix, includes:

[0017] Calculate according to the acquisition times and the usage times corresponding to each right and interest to obtain the corresponding usage rate of the right and interest;

[0018] Successively replace the elements marked with the same right and interest in the blank matrix with the usage rates of all the rights and interests corresponding to the user to obtain a usage rate matrix.

[0019] Optionally, randomly sampling the elements in the usage rate matrix multiple times according to a preset quantity to obtain multiple subset matrices of the usage rate matrix, includes:

[0020] Randomly sample the elements in the usage rate matrix according to a preset quantity, and gather the sampled elements into a subset matrix of the usage rate matrix;

[0021] Judge whether the number of the subset matrices is equal to a preset threshold;

[0022] If the number of the sampled elements is not equal to the preset threshold, return to the step of randomly sampling the elements in the usage rate matrix according to a preset quantity;

[0023] If the number of the sampled elements is equal to the preset quantity, gather all the subset matrices into multiple subset matrices of the usage rate matrix.

[0024] Optionally, using a pre-constructed user classification model to extract matrix features from each subset matrix in the multiple subset matrices to obtain matrix eigenvalues, includes:

[0025] Select one matrix from the multiple subset matrices one by one as the target matrix;

[0026] Input the target matrix into the user classification model;

[0027] Obtain the output values of all nodes in the last fully connected layer of the user classification model for calculation to obtain the matrix eigenvalue.

[0028] Optionally, the screening of all the subset matrices by using the matrix eigenvalue to obtain a target subset matrix includes:

[0029] Judge the number of the maximum values among all the matrix eigenvalues;

[0030] When the number of the maximum values is greater than 1, select the maximum value of the interest utilization rate in the subset matrix corresponding to each maximum value to obtain the maximum value of the subset matrix;

[0031] Select the subset matrix corresponding to the maximum value among all the maximum values of the subset matrix to obtain the target subset matrix;

[0032] When the number of the maximum values is equal to 1, select the subset matrix corresponding to the maximum value to obtain the target subset matrix.

[0033] Optionally, the screening of all the interests in the historical interest utilization data according to the target subset matrix and distributing the screened interests to the user includes:

[0034] Select the maximum interest utilization rate in the target subset matrix to obtain the target interest utilization rate;

[0035] Distribute the interest corresponding to the target interest utilization rate to the user.

[0036] To solve the above problems, the present invention further provides an interest distribution device, and the device includes:

[0037] A matrix construction module, configured to obtain the historical interest utilization data of a user, where the historical interest utilization data includes the acquisition times and actual usage times of different interests; construct a blank matrix according to the number of interests in the historical interest utilization data; calculate the interest utilization rate of each interest in the historical interest utilization data according to the acquisition times and the actual usage times, and use the interest utilization rate to fill the blank matrix to obtain an interest utilization rate matrix; perform multiple random samplings on the elements in the interest utilization rate matrix according to a preset quantity to obtain multiple subset matrices of the interest utilization rate matrix;

[0038] A feature extraction module, configured to perform matrix feature extraction on each of the multiple subset matrices by using a pre-built user classification model to obtain matrix eigenvalues; and use the matrix eigenvalues to screen all the subset matrices to obtain target subset matrices;

[0039] An interest distribution module, configured to screen all interests in the historical interest usage data according to the target subset matrices, and distribute the screened interests to the user.

[0040] To solve the above problems, the present invention further provides an electronic device, which includes:

[0041] A memory, storing at least one computer program; and

[0042] A processor, configured to execute the computer program stored in the memory to implement the above-mentioned interest distribution method.

[0043] To solve the above problems, the present invention further provides a computer-readable storage medium, in which at least one computer program is stored, and the at least one computer program is executed by a processor in an electronic device to implement the above-mentioned interest distribution method.

[0044] In an embodiment of the present invention, all the subset matrices are screened by using the matrix eigenvalues to obtain target subset matrices; all interests in the historical interest usage data are screened according to the target subset matrices, and the screened interests are distributed to the user. The matrix eigenvalues are used to judge the influence degree of the interests on the user, and then the subset matrix with the greatest influence on the user is selected. Further, the interests that the user likes most are selected from the subset matrix with the greatest influence on the user and distributed to the user, and the accuracy of interest distribution is higher. Therefore, the interest distribution method, device, electronic device and readable storage medium provided by the embodiments of the present invention improve the accuracy of interest distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic flowchart of an interest distribution method provided by an embodiment of the present invention;

[0046] Figure 2 It is a schematic block diagram of an interest distribution device provided by an embodiment of the present invention;

[0047] Figure 3 It is a schematic internal structure diagram of an electronic device for implementing an interest distribution method provided by an embodiment of the present invention;

[0048] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] It should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0050] An embodiment of the present invention provides a method for issuing rights and interests. The execution subject of the method for issuing rights and interests includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiments of the present application. In other words, the method for issuing rights and interests can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0051] Referring to Figure 1 the flowchart of the method for issuing rights and interests provided in an embodiment of the present invention shown in

[0052] S1. Obtain the historical rights and interests usage data of the user. Among them, the historical rights and interests usage data includes: the acquisition times and actual usage times of different rights and interests;

[0053] In an embodiment of the present invention, the historical rights and interests usage data includes: information such as the types, acquisition times, usage times, and time of the rights and interests obtained by the user. The rights and interests include, but are not limited to, coupons, discount coupons, vouchers, etc. Among them, the rights and interests can be actively issued to the user by companies, enterprises, etc. that can provide corresponding rights and interests services.

[0054] Specifically, computer statements with data scraping functions (such as java statements, python statements, etc.) can be used to obtain the rights and interests acquisition records from the pre-constructed access area for storing the rights and interests acquisition records. Among them, the storage area includes, but is not limited to, a database, a blockchain node, and a network cache.

[0055] S2. Construct a blank matrix according to the quantity of rights and interests in the historical rights and interests usage data;

[0056] In the embodiments of the present invention, since users do not necessarily use every acquired right, but select some rights from the multiple acquired rights according to their own needs or preferences and other factors, the right usage rate of each right of the user can be calculated based on the acquisition times and the usage times, and a right usage rate matrix is generated, which is beneficial to improving the subsequent preference degree of the user for different preset rights by using the right usage rate matrix, and further improving the accuracy of right distribution.

[0057] Specifically, in the embodiments of the present invention, a blank matrix with the same number of elements is constructed according to the number of rights in the historical right usage data; all rights in the historical right usage data are used to label each element in the blank matrix with a right in turn. For example, if there are 3 rights in the historical right usage data, namely right A and right B, and the blank matrix is a 1*2 matrix, then the element in the first row of the blank matrix is labeled as right A, and the element in the second row of the blank matrix is labeled as right B.

[0058] Further, generally, all elements in the blank matrix are 0. In the embodiments of the present invention, to avoid confusion between the subsequent right usage rate of 0 and the elements in the blank matrix, the blank matrix, that is, a matrix with all elements being -1, can create a blank matrix with m rows and n columns through the B = zeros(m,n) function in the R language library.

[0059] S3. Calculate the right usage rate of each right in the historical right usage data according to the acquisition times and the actual usage times, and use the right usage rate to fill the blank matrix to obtain a right usage rate matrix;

[0060] Specifically, in the embodiments of the present invention, the following right usage rate function is used to calculate the right usage rate of each right:

[0061]

[0062] where x is the right usage rate of the right i acquired by the user, Use j is the usage times of the right i acquired by the user, Release j is the acquisition times of the right i acquired by the user.

[0063] Further, in the embodiments of the present invention, all the right usage rates corresponding to the user are sequentially replaced with the elements in the blank matrix marked with the same right to obtain a right usage rate matrix, where the replacement process does not affect the right label corresponding to the element at that position.

[0064] S4. Randomly sample the elements in the right usage rate matrix multiple times according to a preset quantity to obtain multiple subset matrices of the right usage rate matrix;

[0065] In one actual application scenario of the present invention, since the rights and interests utilization rate matrix contains the rights and interests utilization rates corresponding to each right and interest in the historical rights and interests usage data, if the preference of the user for each of the multiple preset rights and interests is directly analyzed based on this rights and interests utilization rate matrix, some rights and interests with relatively high rights and interests utilization rates in the matrix will have a greater impact on the analysis result, resulting in an incomplete analysis result, and further causing a low accuracy in recommending and distributing rights and interests to the user based on this analysis result.

[0066] Therefore, in an embodiment of the present invention, the elements in the rights and interests utilization rate matrix can be randomly sampled multiple times according to a preset quantity to obtain multiple subset matrices of the rights and interests utilization rate matrix, so as to avoid the influence of some preset rights and interests on other preset rights and interests in the matrix due to the too high calculated rights and interests utilization rate.

[0067] In an embodiment of the present invention, the randomly sampling the elements in the rights and interests utilization rate matrix multiple times according to a preset quantity to obtain multiple subset matrices of the rights and interests utilization rate matrix includes:

[0068] Randomly sampling the elements in the rights and interests utilization rate matrix according to a preset quantity, and pooling the sampled elements into a subset matrix of the rights and interests utilization rate matrix;

[0069] Judging whether the number of the subset matrices is equal to a preset threshold;

[0070] If the number of the sampled elements is not equal to the preset threshold, then return to the step of randomly sampling the elements in the rights and interests utilization rate matrix according to a preset quantity;

[0071] If the number of the sampled elements is equal to the preset threshold, then pool all the subset matrices into multiple subset matrices of the rights and interests utilization rate matrix.

[0072] For example, the rights and interests utilization rate matrix includes 100 elements. When the preset quantity is 20, then randomly collect 20 elements from the rights and interests utilization rate matrix, and pool the 20 collected elements into a subset matrix of this rights and interests utilization rate matrix; judge whether the number (1) of the subset matrices is equal to the preset threshold (2). It can be seen that the number (1) of the subset matrices is not equal to the preset threshold (2), then resample 20 elements in the rights and interests utilization rate matrix again, and pool the sampling result into another subset matrix of this rights and interests utilization rate matrix. At this time, the number (2) of the subset matrices is not equal to the preset threshold (2), and pool the two obtained subset matrices to obtain multiple subset matrices of this rights and interests utilization rate matrix.

[0073] S5. Use the pre - built user classification model to perform matrix feature extraction on each of the multiple subset matrices to obtain matrix eigenvalues;

[0074] Specifically, in the embodiments of the present invention, the user classification model is a pre - trained deep learning model. The deep learning model can be an artificial intelligence model. When constructing the deep learning model, a structure of multiple fully - connected layers is adopted to enhance the network's ability to express data, increase the complexity of the network, and thus improve the accuracy of subsequent feature extraction.

[0075] Further, in the embodiments of the present invention, before using the pre - trained classification model to extract the matrix eigenvalues of each of the multiple subset matrices respectively, it includes:

[0076] Obtain a historical subset matrix set, where each historical subset matrix in the historical subset matrix set has a corresponding user category label.

[0077] In the embodiments of the present invention, for each historical subset matrix in the historical subset matrix set, the corresponding user category label, the historical subset matrix has the same type but different content as the subset matrix, and the user category label is the corresponding user category, including: high - quality users and ordinary users. Through the user classification model, the differences in the sensitivity of different types of users to user rights and interests can be judged, and rights and interests recommendations can be better distributed to users.

[0078] Use the historical subset matrix set to train the pre - built deep learning model to obtain the user classification model.

[0079] Specifically, in the embodiments of the present invention, before using the historical subset matrix set to train the pre - built deep learning model, the method further includes:

[0080] Obtain a deep neural network framework;

[0081] Construct a feature input layer in the deep neural network framework;

[0082] Construct a weight initialization layer after the feature input layer;

[0083] Establish multiple fully - connected layers after the feature input layer;

[0084] Construct a batch normalization layer and a dropout layer between the multiple fully - connected layers;

[0085] Construct a decision output layer after the multiple fully - connected layers to obtain the deep learning model.

[0086] Specifically, the deep neural network framework can be pre-given by the user, and functions corresponding to different network levels can be written in the deep neural network framework using computer languages such as Java and Python to implement the construction of the feature input layer, weight initialization layer, fully connected layer, batch normalization layer, dropout layer, and decision output layer.

[0087] Furthermore, when training a pre-constructed deep learning model using the historical subset matrix set, the input layer is used to perform feature partitioning on the historical subset matrix set to obtain different initial data features for model input. The weight initialization layer sets different weights for the input initial data features. The fully connected layer extracts features from the initial data features with set weights to obtain data features. The decision output layer selects the data features extracted by the last fully connected layer and calculates them using a preset activation function to obtain the prediction probabilities for different classes. The batch normalization layer and the dropout layer are used to adjust the parameters of the fully connected layer.

[0088] Specifically, the feature input layer is used to perform data partitioning on the input data.

[0089] The fully connected layer is used to express and analyze the data features input by the feature input layer according to preset weights to better display the hidden relationships between features, and then obtain the training results of the training data. Among them, the structure of multiple fully connected layers is beneficial to increasing the complexity of the network to improve the accuracy of the training results output by the network, and the output layer of the model is included in the multiple fully connected layers to output the results of model analysis.

[0090] For example, when training deep learning using the historical subset matrix set, the fully connected layer is used to express and analyze the data features of the historical subset matrix set, and the decision output layer after multiple fully connected layers selects the data features extracted and expressed by the last fully connected layer and calculates them using a preset activation function to obtain the prediction probabilities for different classes.

[0091] The batch normalization layer is used to standardize the data features expressed by the fully connected layer to solve the problem of gradient disappearance during network training, and can adjust the weights of the data features expressed by the fully connected layer according to preset weights to optimize the gradient flow of the network.

[0092] The discarded layer, i.e., the Dropout layer, can temporarily discard the data features expressed by the fully connected layer according to a preset probability parameter to prevent the network from overfitting when the training data is scarce. In one embodiment of the present invention, the deep learning includes an 8-layer network structure. The first layer is the feature input layer, the second layer is the weight initialization layer, the third layer is a fully connected layer with 64 neurons, the fourth layer is the batch normalization layer, the fifth layer is the discarded layer, the sixth layer is a fully connected layer with 32 neurons, the seventh layer is a fully connected layer with 16 neurons, and the seventh layer is a fully connected layer with 1 neuron (output layer). Among them, the third and sixth layers use the Relu function as the activation function, the seventh layer uses the Sigmoid function as the activation function, and the probability parameter of the discarded layer is 0.3.

[0093] Among them, the output nodes of the decision output layer are set according to each category label of the user historical information in the historical subset matrix set. For example, in each category of the category labels of the user historical information in the historical subset matrix set, there are a total of: high-quality users and ordinary users, a total of 2 categories. Then, it can be set that the decision output layer has 2 output nodes. Among them, the first output node corresponds to the high-quality user category, and the second output node corresponds to the ordinary user category.

[0094] In the embodiment of the present invention, training the pre-constructed deep learning model using the historical subset matrix set to obtain a classification model includes:

[0095] Step I: Train the deep learning model using each piece of user historical information in the historical subset matrix set, extract the output values of the decision output layer in the deep learning model, and obtain classification prediction values.

[0096] Step II: Determine the classification true values according to each user label in the historical subset matrix set.

[0097] Step III: Calculate a preset loss function according to the classification true values and the classification prediction values to obtain a loss value.

[0098] Optionally, in the embodiment of the present invention, the loss function is the cross-entropy loss function.

[0099] Step IV: When the loss value is greater than or equal to a preset loss threshold, adjust the model parameters of the deep learning model according to the loss value and return to Step I; when the loss value is less than the preset loss threshold, stop training, output the deep learning model, and obtain the user classification model.

[0100] In one embodiment of the present invention, when adjusting the model parameters of the deep learning model according to the loss value, a preset optimization algorithm can be used to adjust the parameters of the adversarial generation network. The preset optimization algorithm includes, but is not limited to: batch gradient descent algorithm, mini-batch gradient descent algorithm, and stochastic gradient descent algorithm.

[0101] For example, input the current parameters of the deep learning model into the optimization algorithm, and use the optimization algorithm to perform optimization calculations on the input current parameters to obtain optimized parameters. Then use the optimized parameters to update the current parameters of the adversarial generation network to achieve the adjustment of the parameters in the adversarial generation network.

[0102] Furthermore, in the implementation of the present invention, the complete classification model is used for user classification. The purpose of training the classification model is to improve the performance of the model. In the embodiment of the present invention, to extract the matrix eigenvalue of the subset matrix, only the output value of the last fully connected layer in the classification model is needed.

[0103] In the embodiment of the present invention, the matrix eigenvalue extraction for each subset matrix in the multiple subset matrices by using the pre-constructed user classification model includes:

[0104] Select one matrix from the multiple subset matrices one by one as the target matrix;

[0105] Input the target matrix into the user classification model;

[0106] Obtain the output values of all nodes in the last fully connected layer of the user classification model for calculation to obtain the matrix eigenvalue.

[0107] Optionally, in the embodiment of the present invention, all the obtained output values are averaged to obtain the matrix eigenvalue.

[0108] In the embodiment of the present invention, the matrix eigenvalues of each subset matrix in the multiple subset matrices can be extracted respectively. Measuring the rights and interests distribution corresponding to the usage rate of all rights and interests in the subset matrix by the matrix eigenvalue helps to cultivate users into high-quality users, avoiding inaccurate rights and interests distribution caused by directly extracting the rights and interests with high usage rates in the rights and interests usage rate matrix.

[0109] S6. Use the matrix eigenvalue to screen all the subset matrices to obtain the target subset matrix;

[0110] Specifically, in the embodiments of the present invention, the matrix eigenvalue measures the influence degree of the rights and interests issuance corresponding to the usage rates of all rights and interests in the subset matrix on the user becoming a high-quality user. The higher the matrix eigenvalue, the greater the influence degree of the corresponding subset matrix. Therefore, in the embodiments of the present invention, the subset matrix corresponding to the largest matrix eigenvalue is selected.

[0111] Specifically, the embodiments of the present invention use the matrix eigenvalue to screen all the subset matrices to obtain a target subset matrix, including:

[0112] Judge the number of the maximum values among all the matrix eigenvalues;

[0113] When the number of the maximum values is greater than 1, select the maximum value of the usage rates of the rights and interests in the subset matrix corresponding to each maximum value to obtain the maximum value of the subset matrix;

[0114] Select the subset matrix corresponding to the maximum value among all the maximum values of the subset matrix to obtain the target subset matrix;

[0115] When the number of the maximum values is equal to 1, select the subset matrix corresponding to the maximum value to obtain the target subset matrix.

[0116] S7. Screen all the rights and interests in the historical rights and interests usage data according to the target subset matrix, and issue the screened rights and interests to the user.

[0117] In the embodiments of the present invention, the matrix eigenvalue in the embodiments of the present invention measures the influence degree of the rights and interests issuance corresponding to the usage rates of all rights and interests in the subset matrix on the user becoming a high-quality user. Therefore, the rights and interests corresponding to the usage rate in the target subset matrix have the greatest influence on the user. Further, it is also necessary to select the rights and interests liked by the user. Therefore, in the embodiments of the present invention, the maximum usage rate of the rights and interests in the target subset matrix is selected to obtain the target usage rate of the rights and interests; the rights and interests corresponding to the target usage rate of the rights and interests are issued to the user.

[0118] As Figure 2 shown, it is a functional module diagram of the rights and interests issuance device of the present invention.

[0119] The rights and interests issuance device 100 of the present invention can be installed in an electronic device. According to the functions to be realized, the rights and interests issuance device may include a matrix construction module 101, a feature extraction module 102, and a rights and interests issuance module 103. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of the electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0120] In this embodiment, the functions of each module / unit are as follows:

[0121] The matrix construction module 101 is used to obtain the historical rights and interests usage data of the user. Among them, the historical rights and interests usage data includes: the acquisition times and actual usage times of different rights and interests; construct a blank matrix according to the number of rights and interests in the historical rights and interests usage data; calculate the rights and interests utilization rate of each right and interest in the historical rights and interests usage data according to the acquisition times and the actual usage times, and use the rights and interests utilization rate to fill the blank matrix to obtain a rights and interests utilization rate matrix; perform multiple random samplings on the elements in the rights and interests utilization rate matrix according to a preset quantity to obtain multiple subset matrices of the rights and interests utilization rate matrix;

[0122] The feature extraction module 102 is used to extract matrix features of each subset matrix in the multiple subset matrices by using a pre-constructed user classification model to obtain matrix eigenvalues; use the matrix eigenvalues to screen all the subset matrices to obtain a target subset matrix;

[0123] The rights and interests granting module 103 is used to screen all the rights and interests in the historical rights and interests usage data according to the target subset matrix and grant the screened rights and interests to the user.

[0124] Specifically, each module in the rights and interests granting device 100 in the embodiment of the present invention adopts the same technical means as the Figure 1 rights and interests granting method described above and can produce the same technical effects, which will not be elaborated here.

[0125] As Figure 2 shown, it is a schematic structural diagram of an electronic device for implementing the rights and interests granting method of the present invention.

[0126] The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program stored in the memory 11 and operable on the processor 10, such as a rights and interests granting program.

[0127] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device, such as the mobile hard disk of the electronic device. In some other embodiments, the memory 11 can 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 Card, etc. equipped on the electronic device. Further, the memory 11 can also include both the internal storage unit and the external storage device of the electronic device. The memory 11 can be used not only to store application software installed on the electronic device and various types of data, such as the code of the rights and interests distribution program, etc., but also to temporarily store the data that has been output or will be output.

[0128] In some embodiments, the processor 10 can be composed of integrated circuits. For example, it can be composed of a single packaged integrated circuit, or can also be composed of multiple integrated circuits with the same or different functions packaged, including the combination of one or more Central Processing Units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and circuits, and by running or executing programs or modules (such as the rights and interests distribution program, etc.) stored in the memory 11, and calling the data stored in the memory 11, to perform various functions of the electronic device and process data.

[0129] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The communication bus 12 is set to realize the connection and communication between the memory 11 and at least one processor 10, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0130] Figure 2 Only the electronic device with components is shown. Those skilled in the art can understand that Figure 2The structures shown do not constitute a limitation on the electronic device, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0131] For example, although not shown, the electronic device may further include a power source (such as a battery) for powering each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charging management, discharging management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure classification circuit, a power converter or inverter, a power status indicator, etc. The electronic device may also include a variety of sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0132] Optionally, the communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is generally used to establish a communication connection between this electronic device and other electronic devices.

[0133] Optionally, the communication interface 13 may further include a user interface. The user interface may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, and is used to display the information processed in the electronic device and to display a visual user interface.

[0134] It should be understood that the embodiments are only for illustration purposes and are not limited by this structure in the scope of the patent application.

[0135] The rights and interests distribution program stored in the memory 11 in the electronic device is a combination of multiple computer programs. When running in the processor 10, it can implement:

[0136] Obtain the historical rights and interests usage data of the user, where the historical rights and interests usage data includes: the acquisition times and actual usage times of different rights and interests;

[0137] Construct a blank matrix according to the number of rights and interests in the historical rights and interests usage data;

[0138] Calculate the rights and interests usage rate of each right and interest in the historical rights and interests usage data according to the acquisition times and the actual usage times, and use the rights and interests usage rate to fill the blank matrix to obtain a rights and interests usage rate matrix;

[0139] Randomly sample the elements in the rights and interests utilization rate matrix multiple times according to a preset quantity to obtain multiple subset matrices of the rights and interests utilization rate matrix;

[0140] Use a pre-constructed user classification model to extract matrix features from each subset matrix in the multiple subset matrices to obtain matrix eigenvalues;

[0141] Use the matrix eigenvalues to screen all the subset matrices to obtain a target subset matrix;

[0142] Screen all the rights and interests in the historical rights and interests usage data according to the target subset matrix, and distribute the screened rights and interests to the user.

[0143] Specifically, for the specific implementation method of the above computer program by the processor 10, reference can be made to Figure 1 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0144] Furthermore, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable medium can be non-volatile or volatile. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM, Read-Only Memory).

[0145] An embodiment of the present invention can also provide a computer-readable storage medium. The readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, it can implement:

[0146] Obtain the historical rights and interests usage data of a user, where the historical rights and interests usage data includes: the acquisition times and actual usage times of different rights and interests;

[0147] Construct a blank matrix according to the quantity of the rights and interests in the historical rights and interests usage data;

[0148] Calculate the rights and interests utilization rate of each right and interest in the historical rights and interests usage data according to the acquisition times and the actual usage times, and use the rights and interests utilization rate to fill the blank matrix to obtain a rights and interests utilization rate matrix;

[0149] Randomly sample the elements in the rights and interests utilization rate matrix multiple times according to a preset quantity to obtain multiple subset matrices of the rights and interests utilization rate matrix;

[0150] Performing matrix feature extraction on each subset matrix in the multiple subset matrices by using a pre-built user classification model to obtain matrix eigenvalues;

[0151] Using the matrix eigenvalues to screen all the subset matrices to obtain target subset matrices;

[0152] Screening all the rights and interests in the historical rights and interests usage data according to the target subset matrices, and distributing the screened rights and interests to the user.

[0153] Furthermore, the computer-usable storage medium may mainly include a storage program area and a storage data area. Among them, the storage program area may store an operating system, application programs required for at least one function, etc.; the storage data area may store data created according to the usage of blockchain nodes, etc.

[0154] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0155] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] Embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0157] In addition, the functional modules in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional modules.

[0158] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention.

[0159] Therefore, in any aspect, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Accordingly, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced by the present invention. Any reference signs in the claims should not be construed as limiting the claims concerned.

[0160] The blockchain referred to in the present invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm. Blockchain, in essence, is a decentralized database, a series of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (anti-counterfeiting) and generate the next block. The blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer, etc.

[0161] In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. A plurality of units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. Words such as "second" are used to denote names and do not denote any particular order.

[0162] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for issuing rights and interests, characterized in that, The method comprises: Obtaining historical rights and interests usage data of the user, wherein the historical rights and interests usage data includes: the number of times different rights and interests were obtained and actually used; constructing a blank matrix according to the number of equity in the historical equity usage data; Calculate the equity utilization rate of each equity in the historical equity utilization data according to the acquisition times and the actual usage times, and use the equity utilization rate to fill the blank matrix to obtain an equity utilization rate matrix; Performing multiple random sampling of elements in the equity utilization rate matrix according to a preset number to obtain multiple subset matrices of the equity utilization rate matrix; Selecting one of the matrices from the plurality of subset matrices one by one as a target matrix, and inputting the target matrix into a pre-built user classification model; Obtaining the output values ​​of all nodes of the last fully connected layer in the user classification model for calculation to obtain matrix eigenvalues; Using the matrix eigenvalues ​​to screen all the subset matrices to obtain a target subset matrix; All the rights and interests in the historical rights and interests usage data are screened according to the target subset matrix, and the screened rights and interests are issued to the user.

2. The rights and interests distribution method according to claim 1, characterized in that, The step of constructing a blank matrix according to the number of equity in the historical equity usage data comprises: Construct a blank matrix with the same number of elements according to the number of equity in the historical equity usage data; All the interests in the historical interest usage data are used to mark each element in the blank matrix with one interest in turn.

3. The rights and interests distribution method according to claim 2, wherein The calculating the equity utilization rate of each equity in the historical equity utilization data according to the acquisition times and the actual usage times, and using the equity utilization rate to fill the blank matrix to obtain an equity utilization rate matrix includes: Calculate the corresponding equity utilization rate according to the acquisition times and the usage times corresponding to each equity; All equity utilization rates corresponding to the user are used to replace the elements marked with the same equity in the blank matrix in sequence to obtain an equity utilization rate matrix.

4. The rights and interests distribution method according to claim 1, characterized in that, The randomly sampling the elements in the equity utilization rate matrix multiple times according to a preset number to obtain multiple subset matrices of the equity utilization rate matrix includes: Randomly sampling the elements in the equity utilization rate matrix according to a preset number, and aggregating the sampled elements into a subset matrix of the equity utilization rate matrix; Determining whether the number of the subset matrices is equal to a preset threshold; If the number of sampled elements is not equal to the preset threshold, returning to the step of randomly sampling the elements in the equity utilization rate matrix according to the preset number; If the number of the sampling elements is equal to the preset number, all subset matrices are aggregated into a plurality of subset matrices of the equity utilization rate matrix.

5. The method for distributing rights and interests according to claim 1, wherein The method of screening all the subset matrices by using the matrix eigenvalues ​​to obtain a target subset matrix includes: Determine the number of maximum values ​​among all the matrix eigenvalues; When the number of the maximum values ​​is greater than 1, the maximum value of the equity utilization rate in the subset matrix corresponding to each of the maximum values ​​is selected to obtain the maximum value of the subset matrix; Select the subset matrix corresponding to the maximum value among the maximum values of all the said subset matrices to obtain the target subset matrix; When the number of the maximum values is equal to 1, select the subset matrix corresponding to the maximum value to obtain the target subset matrix.

6. The rights and interests distribution method as described in claim 5, wherein The screening of all the rights and interests in the historical rights and interests usage data according to the target subset matrix and distributing the screened rights and interests to the user includes: Select the maximum rights and interests utilization rate in the target subset matrix to obtain the target rights and interests utilization rate; Distribute the rights and interests corresponding to the target rights and interests utilization rate to the user.

7. An entitlement distribution device for implementing the entitlement distribution method according to any one of claims 1 to 6, characterized in that It includes: A matrix construction module, configured to obtain the historical rights and interests usage data of a user, where the historical rights and interests usage data includes the acquisition times and actual usage times of different rights and interests; construct a blank matrix according to the number of rights and interests in the historical rights and interests usage data; calculate the rights and interests utilization rate of each right and interest in the historical rights and interests usage data according to the acquisition times and the actual usage times, and use the rights and interests utilization rate to fill the blank matrix to obtain a rights and interests utilization rate matrix; perform multiple random samplings on the elements in the rights and interests utilization rate matrix according to a preset quantity to obtain multiple subset matrices of the rights and interests utilization rate matrix; A feature extraction module, configured to perform matrix feature extraction on each subset matrix in the multiple subset matrices by using a pre-constructed user classification model to obtain matrix eigenvalues; screen all the subset matrices by using the matrix eigenvalues to obtain a target subset matrix; A rights and interests distribution module, configured to screen all the rights and interests in the historical rights and interests usage data according to the target subset matrix and distribute the screened rights and interests to the user.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the rights and interests distribution method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, The computer program, when executed by a processor, implements the rights and interests distribution method according to any one of claims 1 to 6.

Images