CN116703498B - Commodity recommendation method and device, electronic equipment and storage medium - Google Patents
Commodity recommendation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116703498B CN116703498B CN202310446260.0A CN202310446260A CN116703498B CN 116703498 B CN116703498 B CN 116703498B CN 202310446260 A CN202310446260 A CN 202310446260A CN 116703498 B CN116703498 B CN 116703498B
- Authority
- CN
- China
- Prior art keywords
- transmission information
- information
- agents
- communication type
- determining
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 239000003795 chemical substances by application Substances 0.000 claims abstract description 118
- 230000005540 biological transmission Effects 0.000 claims abstract description 106
- 238000004891 communication Methods 0.000 claims abstract description 88
- 230000003993 interaction Effects 0.000 claims abstract description 44
- 239000013598 vector Substances 0.000 claims abstract description 35
- 230000006870 function Effects 0.000 claims description 17
- 230000009471 action Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 5
- 230000001629 suppression Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 230000004936 stimulating effect Effects 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 230000005764 inhibitory process Effects 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 7
- 230000002787 reinforcement Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 238000013500 data storage Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000000306 recurrent effect Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 239000002453 shampoo Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000002269 analeptic agent Substances 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000003989 repetitive behavior Effects 0.000 description 1
- 208000013406 repetitive behavior Diseases 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
Abstract
The application provides a commodity recommendation method, a commodity recommendation device, electronic equipment and a storage medium, wherein the commodity recommendation method comprises the following steps: determining a historical commodity interaction sequence; vectorizing the historical commodity interaction sequence, determining an embedded vector, and taking the embedded vector as input of a preset intelligent agent; classifying communication transmission among the agents according to an enhanced classifier, and determining the communication type of the agents; determining target transmission information according to the communication type of the intelligent agent; fusing the target transmission information, determining recommendation information, and recommending commodities according to the recommendation information. According to the method, through vectorization of the historical commodities, each unique historical commodity is regarded as an agent, interaction between the historical commodities is regarded as interaction between the agents, the communication type between the agents is further determined through the classifier, accordingly, target transmission information is determined, commodity recommendation is conducted according to the correlation of the commodities with the target transmission information.
Description
Technical Field
The present disclosure relates to the field of commodity recommendation technologies, and in particular, to a commodity recommendation method, a device, an electronic apparatus, and a storage medium.
Background
In recent years, along with the rapid development of the e-commerce industry, a recommendation method or system of an e-commerce platform is also rapidly developed, and the recommendation method or system mainly recommends commodities which are similar to the type or efficacy of the used historical commodities but not used by the user through the historical interaction process of the user and the commodities, namely, makes novel recommendation. However, it has become a common phenomenon in the e-commerce scenario that users repeatedly click on or purchase a certain commodity, for example, users repeatedly purchase shampoo or paper towel at intervals. As interaction data continues to accumulate, repeated interactions take up an increasing share in the field of electronic commerce. Therefore, it is necessary to propose a recommendation method for repeatedly purchasing commodities.
Disclosure of Invention
In view of the foregoing, an object of the present application is to provide a commodity recommendation method, apparatus, electronic device, and storage medium.
Based on the above objects, the present application provides a commodity recommendation method, including:
determining a historical commodity interaction sequence;
vectorizing the historical commodity interaction sequence, determining an embedded vector, and taking the embedded vector as input of a preset intelligent agent;
classifying communication transmission among the agents according to an enhanced classifier, and determining the communication type of the agents;
determining target transmission information according to the communication type of the intelligent agent;
fusing the target transmission information, determining recommendation information, and recommending commodities according to the recommendation information.
Optionally, the vectorizing includes:
and vectorizing the historical commodity interaction sequence through a cyclic neural network model, and determining the embedded vector.
Optionally, the classifying the communication transmission between the agents according to the enhanced classifier, determining the communication type of the agents includes:
classifying communication transmissions between the agents by Geng Beier distribution as shown below, determining the communication type of the agents:
wherein,for the noise sampled in the Geng Beier distribution, τ is the temperature parameter, e i ，e j For two adjacent agents, < > for said agent>For the embedded vectors of two adjacent agents, MLP is a multi-layer perceptron, M is the communication type of the agent, M e M (m=0, 1, 2), k is the number of times of purchasing the commodity.
Optionally, the communication type of the agent includes:
a first communication type, a second communication type, and a third communication type; the first communication type stimulates type transmission information, the second communication type is restrained type transmission information, and the third communication type is noise type transmission information.
Optionally, the target transmission information includes first target transmission information and second target transmission information;
the determining the target transmission information according to the communication type of the intelligent agent comprises the following steps:
denoising the transmission information of the intelligent agent according to the communication type of the intelligent agent, and determining the transmission information as a first type group and a second type group; wherein the stimulating agent is grouped as the first type of grouping; taking the suppressed-type agent packet as the first-type packet, the noise reduction including discarding the noise-type transmission information;
and determining the stimulated transmission information as the first target transmission information, and taking the suppressed transmission information as the second target transmission information.
Optionally, the fusing the target transmission information to determine the recommendation information includes:
and carrying out weighted fusion on the target transmission information through the following formula to determine the recommended information:
wherein lambda is i A base bias term that is a self-excitation effect;for the first object to transmit information,transmitting information for said second target, +.>For transmitting information +.>Is a stimulating intelligent body>Is a suppression type intelligent agent.
Optionally, after the fusing the target transmission information and determining the recommendation information, the method further includes:
and updating the association information of the intelligent agent according to the recommendation information.
Based on the same inventive concept, the embodiment of the present application further provides a commodity recommendation device, which is characterized by comprising:
a sequence determination module configured to determine a historical merchandise interaction sequence;
the vectorization module is configured to vectorize the historical commodity interaction sequence, determine an embedded vector and take the embedded vector as input of a preset intelligent agent;
the classification module is configured to classify communication transmission among the intelligent agents according to the enhanced classifier, and determine the communication type of the intelligent agents;
the transmission information determining module is configured to determine target transmission information according to the communication type of the intelligent agent;
and the recommendation module is configured to fuse the target transmission information, determine recommendation information and recommend goods according to the recommendation information.
Based on the same inventive concept, the embodiment of the application also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, and is characterized in that the processor executes the program to realize the commodity recommendation method according to any one of the above.
Based on the same inventive concept, the embodiments of the present application further provide a non-transitory computer readable storage medium, where the non-transitory computer readable storage medium stores computer instructions, where the computer instructions are configured to cause a computer to perform any one of the above-mentioned commodity recommendation methods.
Based on the same inventive concept, the embodiments of the present application further provide a computer program product, including computer program instructions, which when run on a computer, cause the computer to perform any one of the above-mentioned commodity recommendation methods.
From the above, it can be seen that the commodity recommendation method, device, electronic equipment and storage medium provided in the present application are a recommendation method based on multi-agent reinforcement learning, including: determining a historical commodity interaction sequence; vectorizing the historical commodity interaction sequence, determining an embedded vector, and taking the embedded vector as input of a preset intelligent agent; classifying communication transmission among the agents according to an enhanced classifier, and determining the communication type of the agents; determining target transmission information according to the communication type of the intelligent agent; fusing the target transmission information, determining recommendation information, and recommending commodities according to the recommendation information. According to the method, through vectorization of the historical commodities, each unique historical commodity is regarded as an agent, interaction between the historical commodities is regarded as interaction between the agents, the communication type between the agents (namely the historical commodities) is further determined through the classifier, so that target transmission information is determined, reinforcement learning is conducted according to the correlation of the target transmission information commodities, and commodity recommendation is conducted according to the agents after reinforcement learning is completed.
Drawings
In order to more clearly illustrate the technical solutions of the present application or related art, the drawings that are required to be used in the description of the embodiments or related art will be briefly described below, and it is apparent that the drawings in the following description are only embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to those of ordinary skill in the art.
Fig. 1 is a schematic diagram of an implementation scenario of a commodity recommendation method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a commodity recommendation method according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an algorithm framework structure of a commodity recommendation method according to an embodiment of the present application;
FIG. 4 is a schematic overall technical flow chart of a commodity recommendation method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a commodity recommendation device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings.
It should be noted that unless otherwise defined, technical or scientific terms used in the embodiments of the present application should be given the ordinary meaning as understood by one of ordinary skill in the art to which the present application belongs. The terms "first," "second," and the like, as used in embodiments of the present application, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As described in the background section, in recent years, with the rapid development of the e-commerce industry, the recommendation method or system of the e-commerce platform has also developed rapidly, and the recommendation method or system mainly recommends the goods which are similar to the type or efficacy of the used historical goods but not used by the user, i.e. makes a novel recommendation, through the historical interaction process of the user and the goods. However, it has become a common phenomenon in the e-commerce scenario that users repeatedly click on or purchase a certain commodity, for example, users repeatedly purchase shampoo or paper towel at intervals. As interaction data continues to accumulate, repeated interactions take up an increasing share in the field of electronic commerce. Therefore, it is necessary to propose a recommendation method for repeatedly purchasing commodities.
By studying the surface, in this particular scenario, the relevance of the merchandise is a key factor of concern, as one merchandise tends to have a different impact on (i.e., stimulate or delay the occurrence of) the repetitive behavior of a subsequent merchandise. In order to better conduct repeated perception recommendation, the invention models the relevance of commodities in detail.
In combination with the above practical situation, the embodiments of the present application provide a method, an apparatus, an electronic device, and a storage medium for recommending goods. For repeating the recommendation of the commodity.
Note that, in this application:
the GRU (Gated Recurrent Unit, i.e. the recurrent neural network) is also called a gated recurrent unit structure, is a variant of the traditional RNN (recurrent neural network), can effectively capture semantic association between long sequences as the LSTM (long short-term neural network) does, relieves the phenomenon of gradient disappearance or explosion, and has simpler structure and calculation than the LSTM.
Geng Beier (Gumbel) distribution is a special case of generalized extremum distribution (also known as Fisher-Tippett distribution). It is also known as log-Weibull distribution and bi-exponential distribution (or terminology sometimes used to represent Laplace distribution). The potential applicability of gummel distribution to represent maximum distribution is related to extremum theory, meaning that it may be useful if the distribution of the underlying sample data is of normal or exponential type. The remainder of this document refers to gummel distribution to model the distribution of maxima.
Referring to fig. 1, an application scenario schematic diagram of a commodity recommendation method provided in an embodiment of the present application is shown.
The application scenario includes a terminal device 101, a server 102, and a data storage system 103. The terminal device 101, the server 102 and the data storage system 103 may be connected through a wired or wireless communication network. Terminal device 101 includes, but is not limited to, a desktop computer, mobile phone, mobile computer, tablet, media player, smart wearable device, personal digital assistant (personal digital assistant, PDA) or other electronic device capable of performing the functions described above, and the like. The server 102 and the data storage system 103 may be independent physical servers, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms.
The server 102 is configured to provide a text correction service to a user of the terminal device 101, a client in communication with the server 102 is installed in the terminal device 101, and the terminal device receives the recommendation information in the server and displays the recommended merchandise and merchandise information by the client.
The data storage system 103 stores a plurality of training data, wherein the training data includes interaction information or interaction sequences for each historical commodity, and the server 102 can train a model for commodity recommendation based on the plurality of training data, so that the commodity recommendation model can automatically recognize the relevance of the commodity. When the accuracy of the commodity recommendation model output reaches a certain requirement, the server 102 can learn based on the commodity recommendation model output, and continuously optimize the text correction model based on the newly added training data so as to update the training data to improve the recognition accuracy, ensure the real-time performance of the information and reduce the error generated by information lag.
The commodity recommendation method disclosed by the embodiment of the application can be applied to recommendation of repeated commodities. The commodity recommendation model can be trained based on training data of different languages respectively to obtain commodity recommendation models applied to the different languages.
The commodity recommendation method according to the exemplary embodiment of the present application is described below in conjunction with the application scenario of fig. 1. It should be noted that the above application scenario is only shown for the convenience of understanding the spirit and principles of the present application, and embodiments of the present application are not limited in any way in this respect. Rather, embodiments of the present application may be applied to any scenario where applicable.
As shown in fig. 2, 3 and 4, the commodity recommendation method based on multi-agent reinforcement learning includes:
step 202, determining a historical commodity interaction sequence;
204, vectorizing the historical commodity interaction sequence, determining an embedded vector, and taking the embedded vector as input of a preset intelligent agent;
step 206, classifying the communication transmission among the agents according to the enhanced classifier, and determining the communication type of the agents;
step 208, determining target transmission information according to the communication type of the intelligent agent;
step 210, fusing the target transmission information, determining recommendation information, and recommending the commodity according to the recommendation information.
In step 202, the historical merchandise interaction sequence may be a history of all merchandise purchased by a user or a browsed merchandise record or a re-purchase record of merchandise used by a certain e-commerce platform. Wherein, the historical commodity interaction sequence is recorded as v 1：n The embedded vector is
Historical merchandise interaction sequence v is processed through the GRU model in step 204 1：n Embedded as a vector as shown below
Wherein,for observation vector at the time of the k-1 st purchase of commodity, I is identity activation functionCount (n)/(l)>Actions of the jth agent for the k-1 th purchase of goods, v k And (5) the commodity purchased for the kth time in the historical commodity interaction sequence.
In step 206, the classification of the agents is determined by categorizing the communication transmissions between agents by a gummel (Geng Beier) enhanced categorizer. Specifically, the gummel Softmax technology is integrated into a communication selection module to support model learning of discrete output, so that classification of communication transmission is realized.
Specifically, the gummel enhanced classifier is as follows:
wherein,for the noise sampled in the Geng Beier distribution, τ is the temperature parameter, e i ，e j For two adjacent agents, < > for said agent>For the embedded vectors of two adjacent agents, MLP is a multi-layer perceptron, M is the communication type of the agent, M e M (m=0, 1, 2), k is the number of times of purchasing the commodity.
Further, in step 206, the communication transmission between the agents is classified by the gummel enhanced classifier, and then the transmission information is classified into three types, namely, a stimulus type transmission information, a suppression type transmission information and a noise type transmission information. In some embodiments of the present application, the stimulus-type transmission information, the suppression-type transmission information, and the noise-type transmission information correspond to three communication types, that is, a first communication type, a second communication type, and a third communication type, respectively.
In some alternative embodiments, the agents may also be classified according to the type of information transmittedAs a subset with stimulatory stimulusInhibitory subgroup->And noise subgroup->
In some alternative embodiments, since the noise signal is an interference signal, the noise-type transmission information is removed, so that the influence caused by the noise-type transmission information is avoided, and the function is finally used to summarize valuable information transmitted by other agents, namely, the target transmission information. The target transmission information shown in fig. 3 includes first target transmission information and second target transmission information, that is, the Attention shown in fig. 3.
The valuable information transmitted by other agents, namely the target transmission information, is summarized using the following function:
wherein,transmitting information for a first object, < >>For the second object to transmit information, cos (,) is a cosine function,/->For the embedded vectors representing two adjacent agents, < +.>In order for the stimulus-type agent to transmit information,is the transmission information of the inhibition type intelligent agent.
In some alternative embodiments, the stimulus-based delivery information is determined to be a first target delivery information and the suppression-based delivery information is determined to be the second target delivery information.
In step 210, after determining the target transmission information, the transmission information of two adjacent agents, i.e., the target transmission information, e.g., agent e, is first represented by a function as shown below j Transmitting to agent e i Information of (3):
wherein,is a kernel function used to simulate the time-decay effect between two interacting goods or agents.
In some alternative embodiments, the transmission information of the two adjacent agents may also be represented as agent e i Transmitting to agent e j Is a piece of information of (a).
In some alternative embodiments, after determining the transmission information, agent e is further subjected to an active site process j Transmitting to agent e i The target transmission information is determined by carrying out weighted fusion on the target transmission information:
wherein lambda is i To transmit the basic bias term of the information self-excitation effect,is the sum of weighted fusion of the transmission information of adjacent agents in the stimulated agent type +.>For the sum of weighted fusion of the transmission information of adjacent agents in the suppressed agent type +.>For transmitting information +.>Is a stimulating intelligent body>Is a suppression type intelligent agent.
In some alternative embodiments, an agent vector is determinedTarget transmission information->And is based on agent vector->Target transmission information->Constructing action value networksAnd determining recommendation information according to the action value network, and further recommending according to the recommendation information. As shown in FIG. 4, the invention adopts a parameter sharing strategy, namely, each agent independently learns an action value network with completely shared parameters among all agents, thereby solving the problem of huge parameter learning expenditure of the existing double Q learning algorithm.
It should be noted that the action value network is formed by a Multi-Layer Perceptron (MLP) which is an artificial neural network with a trend structure, and maps a set of input vectors to a set of output vectors. The MLP can be seen as a directed graph, consisting of multiple layers of nodes, each layer being fully connected to the next. Except for the input nodes, each node is a neuron (or processing unit) with a nonlinear activation function. A supervised learning method called a back propagation algorithm is often used to train the MLP. MLP is popularization of the perceptron, thus overcome the perceptron and can't realize the shortcoming to the linear unable data recognition.
Further, the action value network is optimized using the loss function as follows:
where Θ is all parameters in the learning space. In the present invention, for action selection, 1 indicates a re-interacted commodity, and no value is 0. After each action is taken, if agent e i Corresponding to the successful repeated interaction in the kth step, the invention awardsSet to 1, otherwise->Set to 0.
In some alternative embodiments, as shown in fig. 4, after the loss function is determined by calculating the loss function, the model parameters are updated by back propagation according to the determined loss function, that is, the loss function is sent to a plurality of agents, so that all agents update the data according to the loss function, thereby ensuring the real-time performance of the information and reducing the error generated by information lag.
From the above, it can be seen that the commodity recommendation method based on multi-agent reinforcement learning provided by the present application includes: determining a historical commodity interaction sequence; vectorizing the historical commodity interaction sequence, determining an embedded vector, and taking the embedded vector as input of a preset intelligent agent; classifying communication transmission among the agents according to an enhanced classifier, and determining the communication type of the agents; determining target transmission information according to the communication type of the intelligent agent; fusing the target transmission information, determining recommendation information, and recommending commodities according to the recommendation information. According to the method, through vectorization of the historical commodities, each unique historical commodity is regarded as an agent, interaction between the historical commodities is regarded as interaction between the agents, the communication type between the agents (namely the historical commodities) is further determined through the classifier, so that target transmission information is determined, reinforcement learning is conducted according to the correlation of the target transmission information commodities, and commodity recommendation is conducted according to the agents after reinforcement learning is completed.
It should be noted that, the method of the embodiments of the present application may be performed by a single device, for example, a computer or a server. The method of the embodiment can also be applied to a distributed scene, and is completed by mutually matching a plurality of devices. In the case of such a distributed scenario, one of the devices may perform only one or more steps of the methods of embodiments of the present application, and the devices may interact with each other to complete the methods.
It should be noted that some embodiments of the present application are described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Based on the same inventive concept, the application also provides a commodity recommendation device corresponding to the method in any embodiment.
Referring to fig. 5, the commodity recommending apparatus includes:
a sequence determination module 502 configured to determine a historical merchandise interaction sequence;
the vectorization module 504 is configured to vectorize the historical commodity interaction sequence, determine an embedded vector, and take the embedded vector as input of a preset intelligent agent;
a classification module 506 configured to classify communication transmissions between the agents according to an enhanced classifier, determining a communication type of the agents;
a transmission information determining module 508 configured to determine target transmission information according to the communication type of the agent;
and the recommendation module 510 is configured to fuse the target transmission information, determine recommendation information, and recommend goods according to the recommendation information.
For convenience of description, the above devices are described as being functionally divided into various modules, respectively. Of course, the functions of each module may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.
The device of the foregoing embodiment is configured to implement the corresponding method for recommending commodities in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.
Based on the same inventive concept, the application also provides an electronic device corresponding to the method of any embodiment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the commodity recommendation method of any embodiment when executing the program.
Fig. 6 shows a more specific hardware architecture of an electronic device according to this embodiment, where the device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 implement communication connections therebetween within the device via a bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit ), microprocessor, application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc. for executing relevant programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage device, dynamic storage device, or the like. Memory 1020 may store an operating system and other application programs, and when the embodiments of the present specification are implemented in software or firmware, the associated program code is stored in memory 1020 and executed by processor 1010.
The input/output interface 1030 is used to connect with an input/output module for inputting and outputting information. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.
Communication interface 1040 is used to connect communication modules (not shown) to enable communication interactions of the present device with other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).
Bus 1050 includes a path for transferring information between components of the device (e.g., processor 1010, memory 1020, input/output interface 1030, and communication interface 1040).
It should be noted that although the above-described device only shows processor 1010, memory 1020, input/output interface 1030, communication interface 1040, and bus 1050, in an implementation, the device may include other components necessary to achieve proper operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the embodiments of the present description, and not all the components shown in the drawings.
The electronic device of the foregoing embodiment is configured to implement the corresponding method for recommending a commodity in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.
Based on the same inventive concept, corresponding to any of the above embodiments of the method, the present application further provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the commodity recommendation method according to any of the above embodiments.
The computer readable media of the present embodiments, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage 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 for a computer 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, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.
The storage medium of the foregoing embodiments stores computer instructions for causing the computer to execute the commodity recommendation method according to any one of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein.
Based on the same inventive concept, the present disclosure also provides a computer program product corresponding to the commodity recommendation method according to any of the above embodiments, which includes computer program instructions. In some embodiments, the computer program instructions may be executed by one or more processors of a computer to cause the computer and/or the processor to perform the color correction method. Corresponding to the execution subject corresponding to each step in each embodiment of the color correction method, the processor executing the corresponding step may belong to the corresponding execution subject.
The computer program product of the above embodiment is configured to enable the computer and/or the processor to perform the commodity recommendation method according to any one of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the application (including the claims) is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the present application, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of brevity.
Additionally, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures, in order to simplify the illustration and discussion, and so as not to obscure the embodiments of the present application. Furthermore, the devices may be shown in block diagram form in order to avoid obscuring the embodiments of the present application, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform on which the embodiments of the present application are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the application, it should be apparent to one skilled in the art that embodiments of the application can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative in nature and not as restrictive.
While the present application has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of those embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.
The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Accordingly, any omissions, modifications, equivalents, improvements and/or the like which are within the spirit and principles of the embodiments are intended to be included within the scope of the present application.
Claims (9)
1. A commodity recommendation method, comprising:
determining a historical commodity interaction sequence;
vectorizing the historical commodity interaction sequence, determining an embedded vector, and taking the embedded vector as input of a preset intelligent agent; the method comprises the following steps: historical commodity interaction sequence v is modeled by a GRU as shown below 1：n Embedded as a vector as shown below
Wherein,for the observation vector at the time of the k-1 st purchase, I is the identity activation function,/>Actions of the jth agent for the k-1 th purchase of goods, v k The k-th purchased commodity in the historical commodity interaction sequence is obtained;
classifying communication transmission among the agents according to an enhanced classifier, and determining the communication type of the agents; the method comprises the following steps: classifying communication transmissions between the agents by Geng Beier distribution as shown below, determining the communication type of the agents:
wherein,for the noise sampled in the Geng Beier distribution, τ is the temperature parameter, e i ，e j For two adjacent ones of said agents,the method is characterized in that the method comprises the steps of embedding vectors of two adjacent agents, wherein MLP is a multi-layer perceptron, M is the communication type of the agents, M epsilon M (M=0, 1, 2), 0 is a first communication type, 1 is a second communication type, 2 is a third communication type, and k is the number of times of purchasing commodities;
determining target transmission information according to the communication type of the intelligent agent;
fusing the target transmission information, determining recommendation information, and recommending commodities according to the recommendation information.
2. The method of claim 1, wherein the vectorizing comprises:
and vectorizing the historical commodity interaction sequence through a cyclic neural network model, and determining the embedded vector.
3. The method of claim 2, wherein the communication type of the agent comprises:
a first communication type, a second communication type, and a third communication type; the first communication type is stimulus type transmission information, the second communication type is inhibition type transmission information, and the third communication type is noise type transmission information.
4. The method of claim 3, wherein the target transmission information comprises a first target transmission information and a second target transmission information;
the determining the target transmission information according to the communication type of the intelligent agent comprises the following steps:
denoising the transmission information of the intelligent agent according to the communication type of the intelligent agent, and determining the transmission information as a first type group and a second type group; wherein the stimulus-based transmission information is grouped as the first type; taking the suppressed transmission information as the second type packet, the noise reduction including discarding the noise-type transmission information;
and determining the stimulated transmission information as the first target transmission information, and taking the suppressed transmission information as the second target transmission information.
5. The method of claim 4, wherein fusing the target transmission information to determine recommendation information comprises:
and carrying out weighted fusion on the target transmission information through the following formula to determine the recommended information:
wherein lambda is i A base bias term that is a self-excitation effect;transmitting information for said first target, +.>Transmitting information for said second target, +.>For transmitting information +.>Is a stimulating intelligent body>Is a suppression type intelligent agent.
6. The method of claim 4, wherein the fusing the target transmission information, after determining the recommendation information, further comprises:
and updating the association information of the intelligent agent according to the recommendation information.
7. A commodity recommendation device, comprising:
a sequence determination module configured to determine a historical merchandise interaction sequence;
the vectorization module is configured to vectorize the historical commodity interaction sequence, determine an embedded vector and take the embedded vector as input of a preset intelligent agent; the method comprises the following steps: historical commodity interaction sequence v is modeled by a GRU as shown below 1：n Embedded as a vector as shown below
Wherein,for the observation vector at the time of the k-1 st purchase, I is the identity activation function,/>Movement of the jth agent for the kth-1 purchase of goodsV is as k The k-th purchased commodity in the historical commodity interaction sequence is obtained;
the classification module is configured to classify communication transmission among the intelligent agents according to the enhanced classifier, and determine the communication type of the intelligent agents; the method comprises the following steps: classifying communication transmissions between the agents by Geng Beier distribution as shown below, determining the communication type of the agents:
wherein,for the noise sampled in the Geng Beier distribution, τ is the temperature parameter, e i ，e j For two adjacent ones of said agents,the method is characterized in that the method comprises the steps of embedding vectors of two adjacent agents, wherein MLP is a multi-layer perceptron, M is the communication type of the agents, M epsilon M (M=0, 1, 2), 0 is a first communication type, 1 is a second communication type, 2 is a third communication type, and k is the number of times of purchasing commodities;
the transmission information determining module is configured to determine target transmission information according to the communication type of the intelligent agent;
and the recommendation module is configured to fuse the target transmission information, determine recommendation information and recommend goods according to the recommendation information.
8. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 6.
9. A computer program product comprising computer program instructions which, when run on a computer, cause the computer to perform the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310446260.0A CN116703498B (en) | 2023-04-23 | 2023-04-23 | Commodity recommendation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310446260.0A CN116703498B (en) | 2023-04-23 | 2023-04-23 | Commodity recommendation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116703498A CN116703498A (en) | 2023-09-05 |
| CN116703498B true CN116703498B (en) | 2024-03-26 |
Family
ID=87836323
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310446260.0A Active CN116703498B (en) | 2023-04-23 | 2023-04-23 | Commodity recommendation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116703498B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458643A (en) * | 2019-05-15 | 2019-11-15 | 北京邮电大学 | Repeated commodity information recommendation method and electronic equipment based on Fusion Features |
| CN111914178A (en) * | 2020-08-19 | 2020-11-10 | 腾讯科技（深圳）有限公司 | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium |
| CN113836388A (en) * | 2020-06-08 | 2021-12-24 | 北京达佳互联信息技术有限公司 | Information recommendation method and device, server and storage medium |
| CN114742604A (en) * | 2022-03-02 | 2022-07-12 | 胡曼恬 | APP preference determination method and device, computer-readable storage medium and terminal |
| CN115082142A (en) * | 2022-05-10 | 2022-09-20 | 华南理工大学 | Recommendation method, device and medium based on heterogeneous relational graph neural network |
| CN115239409A (en) * | 2022-05-25 | 2022-10-25 | 北京数元灵科技有限公司 | Sequence recommendation information selection method and system based on multi-agent reinforcement learning |
| WO2023017927A1 (en) * | 2021-08-11 | 2023-02-16 | 오로라월드 주식회사 | Method for recommending product on basis of play type, and method for generating product recommendation model therefor |
-
2023
- 2023-04-23 CN CN202310446260.0A patent/CN116703498B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458643A (en) * | 2019-05-15 | 2019-11-15 | 北京邮电大学 | Repeated commodity information recommendation method and electronic equipment based on Fusion Features |
| CN113836388A (en) * | 2020-06-08 | 2021-12-24 | 北京达佳互联信息技术有限公司 | Information recommendation method and device, server and storage medium |
| CN111914178A (en) * | 2020-08-19 | 2020-11-10 | 腾讯科技（深圳）有限公司 | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium |
| WO2023017927A1 (en) * | 2021-08-11 | 2023-02-16 | 오로라월드 주식회사 | Method for recommending product on basis of play type, and method for generating product recommendation model therefor |
| CN114742604A (en) * | 2022-03-02 | 2022-07-12 | 胡曼恬 | APP preference determination method and device, computer-readable storage medium and terminal |
| CN115082142A (en) * | 2022-05-10 | 2022-09-20 | 华南理工大学 | Recommendation method, device and medium based on heterogeneous relational graph neural network |
| CN115239409A (en) * | 2022-05-25 | 2022-10-25 | 北京数元灵科技有限公司 | Sequence recommendation information selection method and system based on multi-agent reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116703498A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021047593A1 (en) | Method for training recommendation model, and method and apparatus for predicting selection probability | |
| CN109902706B (en) | Recommendation method and device | |
| CN111695415B (en) | Image recognition method and related equipment | |
| WO2022016556A1 (en) | Neural network distillation method and apparatus | |
| WO2023011382A1 (en) | Recommendation method, recommendation model training method, and related product | |
| CN109087138A (en) | Data processing method and system, computer system and readable storage medium storing program for executing | |
| WO2024002167A1 (en) | Operation prediction method and related apparatus | |
| WO2023185925A1 (en) | Data processing method and related apparatus | |
| CN114240555A (en) | Click rate prediction model training method and device and click rate prediction method and device | |
| CN116108267A (en) | Recommendation method and related equipment | |
| CN115879508A (en) | Data processing method and related device | |
| WO2024067779A1 (en) | Data processing method and related apparatus | |
| WO2023246735A1 (en) | Item recommendation method and related device therefor | |
| Yuan et al. | Deep learning from a statistical perspective | |
| WO2024041483A1 (en) | Recommendation method and related device | |
| CN116843022A (en) | Data processing method and related device | |
| CN116910357A (en) | Data processing method and related device | |
| CN116467594A (en) | Training method of recommendation model and related device | |
| CN116703498B (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| WO2023050143A1 (en) | Recommendation model training method and apparatus | |
| CN116204709A (en) | Data processing method and related device | |
| CN112989182A (en) | Information processing method, information processing apparatus, information processing device, and storage medium | |
| CN115545738A (en) | Recommendation method and related device | |
| WO2023051678A1 (en) | Recommendation method and related device | |
| WO2023236900A1 (en) | Item recommendation method and related device thereof |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |