Community portrait generation method, apparatus, device, medium, and program product

Abstract

Embodiments of the present disclosure disclose community portrait generation methods, devices, equipment, media and program products. A specific implementation of the method comprises: obtaining a first encrypted feature vector from a first terminal, the first encrypted feature vector being obtained by encrypting a first feature vector by the first terminal using a public key of a server; obtaining a second encrypted feature vector from a second terminal, the second encrypted feature vector being obtained by encrypting a second feature vector by the second terminal using the public key; decrypting the first encrypted feature vector and the second encrypted feature vector using a private key of the server to obtain a first decrypted feature vector and a second decrypted feature vector; fusing the first decrypted feature vector and the second decrypted feature vector to obtain a fused vector; and predicting using the fused vector to obtain a community portrait. The implementation is related to federated learning, and the accuracy of the community portrait is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of computer, and specifically to a community portrait generation method, device, equipment, medium and program product. BACKGROUND

[0002] A community portrait is a digital description corresponding to a community, which can effectively reflect various indicators of a community. A commonly used way to generate a community portrait is to abstract community portrait generation as a classification or regression task, and generate a community portrait through a deep learning network.

[0003] However, the inventors have found that when generating a community portrait in the above manner, the following technical problems often exist:

[0004] In order to ensure the safety of private data, it is impossible to train a deep learning network using multiple data sources, which in turn causes the accuracy of the community portrait generated by the deep learning network to be low.

[0005] The above information disclosed in this BACKGROUND section is only for the purpose of enhancing the understanding of the background of the present inventive concepts, and therefore, it can contain information that does not form the prior art that is already known to those of ordinary skill in the art in the country to which this patent belongs. SUMMARY

[0006] The summary section of the present disclosure is used to introduce the concepts in a brief manner, which will be described in detail in the following detailed description section. The summary section of the present disclosure is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to be used to limit the scope of the claimed technical solutions.

[0007] Some embodiments of the present disclosure propose a community portrait generation method, device, equipment, medium and program product to solve one or more of the technical problems mentioned in the above BACKGROUND section.

[0008] In a first aspect, some embodiments of the present disclosure provide a community portrait generation method, which comprises: obtaining a first encrypted feature vector from a first terminal, the first encrypted feature vector being obtained by encrypting a first feature vector by the first terminal using a public key of a server; obtaining a second encrypted feature vector from a second terminal, the second encrypted feature vector being obtained by encrypting a second feature vector by the second terminal using the public key; decrypting the first encrypted feature vector and the second encrypted feature vector using a private key of the server to obtain a first decrypted feature vector and a second decrypted feature vector; fusing the first decrypted feature vector and the second decrypted feature vector to obtain a fused vector; and predicting using the fused vector to obtain a community portrait.

[0009] In a second aspect, some embodiments of the present disclosure provide a community portrait generation apparatus. The apparatus comprises: a first obtaining unit configured to obtain a first encrypted feature vector from a first terminal, the first encrypted feature vector being obtained by encrypting a first feature vector by the first terminal using a public key of a server; a second obtaining unit configured to obtain a second encrypted feature vector from a second terminal, the second encrypted feature vector being obtained by encrypting a second feature vector by the second terminal using the public key; a decryption unit configured to decrypt the first encrypted feature vector and the second encrypted feature vector respectively using a private key of the server to obtain a first decrypted feature vector and a second decrypted feature vector; a fusion unit configured to fuse the first decrypted feature vector and the second decrypted feature vector to obtain a fused vector; and a prediction unit configured to perform prediction using the fused vector to obtain a community portrait.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device. The electronic device comprises: one or more processors; and a storage storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method described in any implementation manner of the first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium storing a computer program, wherein the program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0012] In a fifth aspect, some embodiments of the present disclosure provide a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method described in any implementation manner of the first aspect.

[0013] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: the accuracy of the generated community portrait is improved. The reason why the related method of generating a community portrait has low accuracy is that the training of the deep learning network using a single data source cannot fully train the network, thereby causing the low accuracy of the community portrait. Due to the limitation of data privacy and security, data sources from multiple parties cannot be collected to one party for processing. Based on this, some embodiments of the present disclosure obtain a first encrypted feature vector and a second encrypted feature vector from a first terminal and a second terminal respectively, and then implement the fusion of multiple data sources, thereby improving the richness and diversity of features and the accuracy of the community portrait. In this process, since it is an encrypted feature vector, the data security problem caused by directly transmitting the feature vector is avoided. BRIEF DESCRIPTION OF DRAWINGS

[0014] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The same or similar components have the same or similar reference labels. It should be understood that the drawings are not necessarily to scale, with emphasis instead being placed upon illustrating the principles of the embodiments of the present disclosure.

[0015] Figure 1 is a schematic diagram of one application scenario of a community portrait generation method according to some embodiments of the present disclosure;

[0016] Figure 2 is a flowchart of some embodiments of a community portrait generation method according to the present disclosure;

[0017] Figure 3 is an exemplary schematic diagram of a community portrait generation model in a community portrait generation method according to the present disclosure;

[0018] Figure 4 is a flowchart of other embodiments of a community portrait generation method according to the present disclosure;

[0019] Figure 5 is a structural schematic diagram of some embodiments of a community portrait generation apparatus according to the present disclosure;

[0020] Figure 6 is a structural schematic diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0021] Embodiments of the present disclosure will be described in more detail with reference to the drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure can be more thoroughly and completely understood. It should be understood that the drawings and embodiments of the present disclosure are for exemplary purposes only, and are not intended to limit the scope of protection of the present disclosure.

[0022] It should also be noted that, for ease of description, only parts related to the present application are shown in the drawings. The embodiments in the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0023] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not intended to limit the order or interdependence of the functions performed by these devices, modules or units.

[0024] It should be noted that the modification of "one" and "multiple" mentioned in the present disclosure is illustrative rather than limiting, and those skilled in the art should understand that "one or more" should be understood unless the context clearly indicates otherwise.

[0025] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not used to limit the scope of the messages or information.

[0026] The collection, storage, use, etc. of user personal information (such as feature vectors, user behavior data) involved in the present disclosure should be carried out by the relevant organization or individual to fulfill the obligations including conducting personal information security impact assessment, informing the personal information subject, obtaining the authorization consent of the personal information subject in advance, and complying with the relevant laws and regulations before performing the corresponding operation.

[0027] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0028] Figure 1 is a schematic diagram of one application scenario of a community portrait generation method according to some embodiments of the present disclosure.

[0029] As Figure 1 indicated, the first terminal takes the terminal of community A as an example, and the second terminal takes the terminal of internet agency B as an example. As shown in the figure, the first terminal includes interest point data, shop data, and community order data. The second terminal includes internet e-commerce data. On this basis, the features can be constructed by federated feature engineering using these data. Among them, the interest point data can be represented as the location of the community, the category of the interest point, and other features, and the shop data can be represented as the related features of the surrounding offline shops. In practice, the input data can be converted into vectorized features by methods such as one-hot representation and real number representation. As for the community order data, since it contains time sequence features (such as purchase cycle), the community order data can be input into Transform to obtain a set of time sequence features (such as user partial portrait and community related information as shown in the figure). For internet e-commerce data, features in dimensions such as user behavior, commodity category, and sales order can be extracted.

[0030] On the basis of constructing features by federated feature engineering, a spatio-temporal federated heterogeneous community portrait model can be trained. Further, community portrait prediction can be performed by the spatio-temporal federated heterogeneous community portrait model to obtain a portrait result.

[0031] It should be noted that the execution subject of federated model training and federated online inference can be the same or different, and the present disclosure does not limit this.

[0032] Continuing to refer to Figure 2FIG. 2 shows a flow 200 of some embodiments of the community portrait generation method according to the present disclosure. The community portrait generation method comprises the following steps:

[0033] At step 201, a first encrypted feature vector is obtained from a first terminal. The first encrypted feature vector is obtained by encrypting a first feature vector using a public key of a server by the first terminal.

[0034] In some embodiments, the subject performing the community portrait generation method can be, for example, the server. In practice, the server can be hardware or software. When it is hardware, it can be implemented as a distributed cluster composed of multiple servers, or as a single server. When it is software, it can be installed in the above-mentioned servers, and it can be implemented as, for example, multiple software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.

[0035] On this basis, the above-mentioned subject can obtain the first encrypted feature vector from the first terminal. The first terminal can first receive the public key issued by the server, then encrypt the first feature vector using the public key, and further obtain the first encrypted feature vector. In practice, the first feature vector is a feature vector constructed using data possessed by the first terminal. For example, it can be a feature vector corresponding to a certain community, which can include multiple indicators of the community, including but not limited to: community location, community store sales category, community store sales, and other indicators related to community sales. In practice, the indicator values of these indicators can be determined by manual extraction, and then the first feature vector of the community is obtained.

[0036] In some optional implementations of some embodiments, the first feature vector is obtained by the following steps: obtaining store data, community order data, and point of interest data of a target community; generating point of interest features according to the point of interest data; inputting the point of interest data and the store data into a convolutional neural network (CNN) to obtain first item features; generating first time series features according to the community order data; and fusing the point of interest features, the first item features, and the first time series features to obtain the first feature vector. The target community can be any community. According to needs, the point of interest data can be converted into point of interest features using one-hot representation, real number representation, etc. In addition, the time series features can be extracted through a Transform network to obtain the first time series features. Feature fusion can use feature concatenation, feature addition, feature dot product, etc.

[0037] In some embodiments, the server can pre-generate a private key and a public key. On this basis, the server can send the public key to the first terminal and the second terminal respectively. Then, the first terminal and the second terminal can encrypt using the public key through the asymmetric encryption algorithm RSA respectively.

[0038] Step 202, obtaining a second encrypted feature vector from the second terminal, the second encrypted feature vector being obtained by encrypting the second feature vector by the second terminal using the public key.

[0039] In some embodiments, the above execution subject can obtain the second encrypted feature vector from the second terminal. Wherein, the second terminal can first receive the public key issued by the server, then encrypt the second feature vector using the public key, and further obtain the second encrypted feature vector. The specific encryption method can refer to the encryption algorithm in step 201, which will not be repeated here.

[0040] In some optional implementations of some embodiments, the second feature vector is obtained by the following steps: obtaining user behavior data, platform item data, and platform order data of the target platform; inputting the platform item data into a graph neural network model to obtain a second item feature; generating a second time sequence feature according to the user behavior data and the platform order data; and fusing the second item feature and the second time sequence feature to obtain the second feature vector. Wherein, the user behavior data can be data such as the number of views and the number of collections. The platform item data can be a multi-level category of items. The platform order data includes order timestamp, amount, and item information contained in the order. The graph neural network (GNN) can be, for example, a graph convolution network. Wherein, RNN (Recurrent Neural Network), LSTM (Long Short Term Memory), GRU, etc. can be used.

[0041] Step 203, decrypting the first encrypted feature vector and the second encrypted feature vector using the private key of the server to obtain a first decrypted feature vector and a second decrypted feature vector.

[0042] In some embodiments, the above execution subject can decrypt the first encrypted feature vector and the second encrypted feature vector using the pre-generated private key to obtain the first decrypted feature vector and the second decrypted feature vector. It can be understood that the first decrypted feature vector obtained by decryption is the same as the first feature vector, and the second decrypted feature vector is the same as the second feature vector. As can be seen, through public key encryption and private key decryption, the fusion of multi-party data while ensuring data security is realized.

[0043] Step 204, fusing the first decrypted feature vector and the second decrypted feature vector to obtain a fusion vector.

[0044] In some embodiments, the above execution subject can use feature splicing, feature addition, feature dot product, etc. to fuse features and further obtain a fusion vector.

[0045] Step 205, predicting by using the fusion vector to obtain the community portrait.

[0046] In some embodiments, the above execution subject can input the fusion vector into a prediction network to obtain the community portrait. The prediction network can include a full connection network and a loss function.

[0047] In some optional implementations of some embodiments, predicting by using the fusion vector to obtain the community portrait includes: inputting the fusion vector into a self-attention network and a multi-layer perception to obtain the community portrait.

[0048] Some embodiments of the present disclosure provide a method for obtaining a community portrait. The method includes: obtaining a first encrypted feature vector from a first terminal and a second encrypted feature vector from a second terminal, and predicting by using the first encrypted feature vector and the second encrypted feature vector to obtain the community portrait. The method can fuse multiple data sources, thereby improving the richness and diversity of features and improving the accuracy of the community portrait. In this process, since the feature vectors are encrypted, the data security problem caused by directly transmitting the feature vectors is avoided.

[0049] Further reference is made to Figure 3 FIG. 4 shows an exemplary schematic diagram of a community portrait generation model in a community portrait generation method according to some embodiments of the present disclosure. The community portrait generation model includes a first sub-network 301 deployed on a first terminal, a second sub-network 302 deployed on a second terminal, and a third sub-network 303 deployed on a server. Exemplarily, the first sub-network 301 includes an embedding layer, a transform layer and a CNN layer, and a feature fusion layer. The second sub-network 302 includes an embedding layer, a transform layer and a GNN layer, and a feature fusion layer. The third sub-network 303 includes an interaction layer, a self-attention layer, a multi-layer perception, and an output layer. The interaction layer is used for feature fusion.

[0050] Further reference is made to Figure 4 FIG. 4 shows a flow 400 of another embodiment of the community portrait generation method. The flow 400 of the community portrait generation method includes the following steps:

[0051] Step 401, obtaining a first encrypted feature vector from a first terminal. The first encrypted feature vector is obtained by encrypting a first feature vector by the first terminal using a public key of a server.

[0052] Step 402, obtaining a second encrypted feature vector from a second terminal. The second encrypted feature vector is obtained by encrypting a second feature vector by the second terminal using the public key.

[0053] Step 403, decrypting the first encrypted feature vector and the second encrypted feature vector by using a private key of the server to obtain a first decrypted feature vector and a second decrypted feature vector.

[0054] Step 404, fusing the first decrypted feature vector and the second decrypted feature vector to obtain a fused vector.

[0055] Step 405, predicting by using the fused vector to obtain a community portrait.

[0056] In some embodiments, the specific implementation of steps 401-405 and the technical effects brought by them can be referred to Figure 2 Corresponding embodiments are not described here.

[0057] Step 406, controlling a resource allocation device to allocate resources to the community according to the community portrait.

[0058] In some embodiments, in the application scenario of community material allocation, the material allocation device can be controlled to allocate resources according to the community portrait. For example, the community portrait is an old-age community, and a large number of nursing materials can be allocated to the community.

[0059] As can be seen from Figure 4 , compared with Figure 2 the description of some embodiments corresponding to the above-mentioned methods, Figure 4 the flow 400 of the community portrait generation method in some embodiments corresponding to the above-mentioned methods, the resources are allocated by using the community portrait, so as to realize the high allocation efficiency and the high demand matching degree, and avoid the resource shortage or waste.

[0060] Further referring to Figure 5 , as an implementation of the above-mentioned method, the present disclosure provides some embodiments of a community portrait generation device, which correspond to the above-mentioned method embodiments, and the device can be specifically applied to various electronic devices. Figure 2

[0061] As shown in Figure 5 , the community portrait generation device 500 of some embodiments includes: a first acquisition unit 501 configured to acquire a first encrypted feature vector from a first terminal, the first encrypted feature vector being obtained by encrypting a first feature vector by the first terminal using a public key of a server; a second acquisition unit 502 configured to acquire a second encrypted feature vector from a second terminal, the second encrypted feature vector being obtained by encrypting a second feature vector by the second terminal using the public key; a decryption unit 503 configured to decrypt the first encrypted feature vector and the second encrypted feature vector respectively by using a private key of the server to obtain a first decrypted feature vector and a second decrypted feature vector; a fusion unit 504 configured to fuse the first decrypted feature vector and the second decrypted feature vector to obtain a fused vector; and a prediction unit 505 configured to predict by using the fused vector to obtain a community portrait.

[0062] ​In an optional implementation of some embodiments, the first feature vector is obtained by the following steps: obtaining store data of a target community, community order data, and point of interest data; generating point of interest features according to the point of interest data; inputting the point of interest data and the store data into a convolutional network to obtain first item features; generating first time sequence features according to the community order data; and fusing the point of interest features, the first item features, and the first time sequence features to obtain the first feature vector.

[0063] In an optional implementation of some embodiments, the second feature vector is obtained by the following steps: obtaining user behavior data, platform item data, and platform order data of a target platform; inputting the platform item data into a graph neural network model to obtain second item features; generating second time sequence features according to the user behavior data and the platform order data; and fusing the second item features and the second time sequence features to obtain the second feature vector.

[0064] In an optional implementation of some embodiments, the prediction unit is further configured to: input the fused vector into a self-attention network and a multi-layer perception to obtain the community portrait.

[0065] In an optional implementation of some embodiments, the apparatus further includes a deployment unit configured to control a resource deployment device to deploy resources for the community according to the community portrait.

[0066] It can be understood that the units described in the apparatus 500 correspond to the respective steps in the method described with reference to Figure 2 The operations, features, and advantages described above for the method also apply to the apparatus 500 and the units included therein, and thus are not described here again.

[0067] Reference is made below to Figure 6 which shows a structural schematic diagram of an electronic device 600 (e.g., a server in Figure 3 adapted to implement some embodiments of the present disclosure. Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present disclosure.

[0068] As Figure 6As shown, the electronic device 600 can include a processing device 601 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or loaded into a random access memory (RAM) 603 from a storage device 608. Various programs and data required for the operation of the electronic device 600 are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0069] Generally, the following devices can be connected to the I / O interface 605: input devices 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 609. The communication devices 609 can allow the electronic device 600 to communicate wirelessly or wired with other devices to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that all of the illustrated devices are not required, and more or fewer devices can alternatively be implemented. Figure 6 Each block shown in the flowcharts can represent a device, or a plurality of devices, as needed.

[0070] In particular, processes described above with reference to the flowcharts can be implemented as a computer software program according to some embodiments of the present disclosure. For example, some embodiments of the present disclosure include a computer program product including a computer program carried on a computer readable medium, the computer program containing program codes for performing the methods shown in the flowcharts. In some such embodiments, the computer program can be downloaded and installed from a network through the communication devices 609, or installed from the storage devices 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-described functions defined in the methods of some embodiments of the present disclosure are performed.

[0071] Note that the computer readable medium in some embodiments of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program used by an instruction execution system, apparatus or device, or that can be used by or in connection with an instruction execution system, apparatus or device. In some embodiments of the present disclosure, the computer readable signal medium can include a computer readable program code propagated in or on a carrier medium, in which the computer readable program code is embodied. Such propagated computer readable program code can take many forms, including but not limited to, an electromagnetic signal, an optical signal or any suitable combination of the foregoing. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. Program code embodied on a computer readable medium can be transmitted using any suitable medium, including but not limited to, wire, cable, wireless, RF, infrared or any suitable combination of the foregoing.

[0072] In some embodiments, the client, server, or both can communicate using any current known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any current known or future developed networks.

[0073] The computer readable medium can be included in the electronic device; or can exist independently of the electronic device. The computer readable medium bears one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire a first encrypted feature vector from a first terminal, the first encrypted feature vector being obtained by the first terminal encrypting a first feature vector using a public key of a server; acquire a second encrypted feature vector from a second terminal, the second encrypted feature vector being obtained by the second terminal encrypting a second feature vector using the public key; decrypt the first encrypted feature vector and the second encrypted feature vector using a private key of the server to obtain a first decrypted feature vector and a second decrypted feature vector; fuse the first decrypted feature vector and the second decrypted feature vector to obtain a fused vector; and perform prediction using the fused vector to obtain a community portrait.

[0074] Computer program code for carrying out operations of some embodiments of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0075] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a procedure, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0076] The units described in some embodiments of the present disclosure can be implemented in the form of software, or can be implemented in the form of hardware. The described units can also be arranged in a processor, for example, can be described as: a processor comprising a first acquisition unit, a second acquisition unit, a decryption unit, a fusion unit and a prediction unit. Among them, the name of these units does not constitute a limitation to the unit itself in some cases, for example, the first acquisition unit can also be described as "a unit for acquiring a first encrypted feature vector".

[0077] The functions described above in the present document can be performed at least in part by one or more hardware logic components. For example, non-limitingly, example types of hardware logic components that can be used include: field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0078] Some embodiments of the present disclosure also provide a computer program product comprising a computer program which, when executed by a processor, implements any of the above community portrait generation methods.

[0079] The above description is merely some preferred embodiments of the present disclosure and a description of the principles of the technology used. Those skilled in the art should understand that the scope of the application involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features and the technical features disclosed in the embodiments of the present disclosure (but not limited to) with similar functions are replaced with each other to form a technical solution.

Claims

1. A community portrait generation method applied to a server, comprising: obtaining a first encrypted feature vector from a first terminal, the first encrypted feature vector being obtained by the first terminal encrypting a first feature vector using a public key of the server; obtaining a second encrypted feature vector from a second terminal, the second encrypted feature vector being obtained by the second terminal encrypting a second feature vector using the public key; decrypting the first encrypted feature vector and the second encrypted feature vector respectively using a private key of the server to obtain a first decrypted feature vector and a second decrypted feature vector; fusing the first decrypted feature vector and the second decrypted feature vector to obtain a fused vector; using the fused vector to make a prediction to obtain a community portrait.

2. The method of claim 1, wherein, The first feature vector is obtained by the following steps: obtaining store data, community order data, and point of interest data of a target community; generating a point of interest feature according to the point of interest data; inputting the point of interest data and the store data into a convolutional network to obtain a first item feature; generating a first time sequence feature according to the community order data; fusing the point of interest feature, the first item feature, and the first time sequence feature to obtain the first feature vector.

3. The method of claim 1, wherein, The second feature vector is obtained by the following steps: obtaining user behavior data, platform item data, and platform order data of a target platform; inputting the platform item data into a graph neural network model to obtain a second item feature; generating a second time sequence feature according to the user behavior data and the platform order data; fusing the second item feature and the second time sequence feature to obtain the second feature vector.

4. The method of claim 1, wherein, The using the fused vector to make a prediction to obtain a community portrait comprises: inputting the fused vector into a self-attention network and a multi-layer perception machine to obtain a community portrait.

5. The method of claim 1, wherein, The method further comprises: controlling a resource allocation device to allocate resources to a community according to the community portrait.

6. A community portrait generation apparatus, comprising: a first obtaining unit configured to obtain a first encrypted feature vector from a first terminal, the first encrypted feature vector being obtained by the first terminal encrypting a first feature vector using a public key of a server; a second obtaining unit configured to obtain a second encrypted feature vector from a second terminal, the second encrypted feature vector being obtained by the second terminal encrypting a second feature vector using the public key; a decryption unit configured to decrypt the first encrypted feature vector and the second encrypted feature vector respectively using a private key of the server to obtain a first decrypted feature vector and a second decrypted feature vector; a fusion unit configured to fuse the first decrypted feature vector and the second decrypted feature vector to obtain a fused vector; a prediction unit configured to use the fused vector to make a prediction to obtain a community portrait.

7. The apparatus of claim 6, wherein, The prediction unit is further configured to: input the fused vector into a self-attention network and a multi-layer perception machine to obtain a community portrait.

8. An electronic device, comprising: one or more processors; a storage device having stored thereon one or more programs, when the one or more programs are executed by the one or more processors, cause the one or more processors to carry out the method of any one of claims 1-5.

9. A computer readable medium having stored thereon a computer program, wherein, the computer program, which causes the processor to implement the method of any one of claims 1-5 when the computer program is executed by the processor.

10. A computer program product comprising a computer program which, when executed by a processor, carries out the method of any one of claims 1-5.

Images