Method, device, electronic device and readable medium for pushing information

Abstract

The embodiments of the present application disclose a method, device, electronic device and readable medium for pushing information. A specific implementation of the method includes: obtaining information about second-hand goods and account information for uploading information about second-hand goods; determining feature information of second-hand goods based on the information about second-hand goods, and determining user feature information based on account information; generating probability values ​​of various alternative solutions for disposing of second-hand goods being selected based on the feature information of second-hand goods, user feature information and a pre-trained classification model; and selecting an alternative solution from various alternative solutions and pushing it to a terminal with logged-in account information based on the generated probability values. This implementation improves the efficiency of information push.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular, to a method, device, electronic device, and readable medium for pushing information. Background Art

[0002] With the development of big data and the Internet, users update their products more quickly, and there are more and more second-hand products. Currently, the way to dispose of second-hand products provided to users is relatively simple, usually users upload them to second-hand product trading platforms for sale. Summary of the invention

[0003] The embodiments of the present application provide a method, an apparatus, an electronic device, and a readable medium for pushing information.

[0004] In a first aspect, some embodiments of the present application provide a method for pushing information, the method comprising: obtaining information about second-hand goods and account information for uploading the information about second-hand goods; determining characteristic information of the second-hand goods based on the information about the second-hand goods, and determining user characteristic information based on the account information; generating probability values ​​of various alternative plans for disposing of second-hand goods being selected based on the characteristic information of the second-hand goods, the user characteristic information and a pre-trained classification model; and selecting an alternative plan from various alternative plans based on the generated probability values ​​and pushing it to a terminal with logged-in account information.

[0005] In some embodiments, determining characteristic information of a second-hand commodity based on information of the second-hand commodity includes: determining a vectorized representation of the information of the second-hand commodity as the characteristic information of the second-hand commodity, wherein the information of the second-hand commodity includes at least one of the following: price information, size information, color information, and quality score information.

[0006] In some embodiments, determining user characteristic information based on account information includes: querying associated user information based on the account information; determining a vectorized representation of the user information as the user characteristic information, wherein the user information includes at least one of the following: gender information, age information, location information, membership information, purchasing power information, information on the model of mobile phone used, network information used, weather information, product sales information in the user's area, product preference information, category preference information, brand preference information, price preference information, and store preference information.

[0007] In some embodiments, based on the feature information of the second-hand goods, the feature information of the user and a pre-trained classification model, probability values ​​of each alternative solution for disposing of the second-hand goods being selected are generated, including: performing a merging operation on the feature information of the second-hand goods and the feature information of the user that has a pre-set association relationship, the merging operation including at least one of the following: cosine calculation, inner product calculation, square root calculation, absolute difference calculation; concatenating the results of the merging operation to obtain an input vector of the classification model; inputting the input vector into the classification model to generate probability values ​​of each alternative solution for disposing of the second-hand goods being selected.

[0008] In some embodiments, the classification model includes: a convolutional neural network layer and a deep neural network layer.

[0009] In some embodiments, the alternative plan includes an alternative plan determined by the following steps: determining the value information of the second-hand goods based on the information of the second-hand goods; and determining the alternative plan based on the value information.

[0010] In some embodiments, the alternative solutions include an auction solution; and determining the alternative solution based on the value information includes: determining an estimated transaction price of the auction solution based on the value information.

[0011] In some embodiments, the alternative plans include replacement plans; and determining the alternative plans based on the value information includes: determining the value difference between the second-hand goods and the new goods of the same category based on the value information; or determining the goods to be replaced or the combination of goods to be replaced that match the value information based on the value information.

[0012] In a second aspect, some embodiments of the present application provide a device for pushing information, the device comprising: an acquisition unit, configured to acquire information about second-hand goods and account information for uploading information about second-hand goods; a determination unit, configured to determine feature information of the second-hand goods based on the information about the second-hand goods, and to determine user feature information based on the account information; a generation unit, configured to generate probability values ​​of various alternative plans for disposing of second-hand goods being selected based on the feature information of the second-hand goods, user feature information and a pre-trained classification model; and a push unit, configured to select an alternative plan from various alternative plans based on the generated probability value and push it to a terminal with logged-in account information.

[0013] In some embodiments, it is further configured to: determine the vectorized representation of the information of the second-hand goods as the feature information of the second-hand goods, wherein the information of the second-hand goods includes at least one of the following: price information, size information, color information, and quality score information.

[0014] In some embodiments, the determination unit is further configured to: query associated user information based on account information; determine the vectorized representation of the user information as user feature information, wherein the user information includes at least one of the following: gender information, age information, location information, membership information, purchasing power information, information on the model of mobile phone used, network information used, weather information, product sales information in the user's area, product preference information, category preference information, brand preference information, price preference information, and store preference information.

[0015] In some embodiments, the generation unit is further configured to: perform a merging operation on feature information of second-hand goods and feature information of user feature information that has a pre-set association relationship, the merging operation including at least one of the following: cosine calculation, inner product calculation, square root calculation, absolute difference calculation; concatenate the results of the merging operation to obtain an input vector of the classification model; input the input vector into the classification model to generate probability values ​​of each alternative solution for disposing of second-hand goods being selected.

[0016] In some embodiments, the classification model includes: a convolutional neural network layer and a deep neural network layer.

[0017] In some embodiments, the device further includes an alternative solution determination unit configured to: determine value information of the second-hand commodity based on the information of the second-hand commodity; and determine an alternative solution based on the value information.

[0018] In some embodiments, the alternative solutions include an auction solution; and the alternative solution determination unit is further configured to: determine an estimated transaction price of the auction solution according to the value information.

[0019] In some embodiments, the alternative plans include replacement plans; and the alternative plan determination unit is further configured to: determine the value difference between the second-hand goods and the new goods of the same category based on the value information; or determine the goods to be replaced or the combination of goods to be replaced that matches the value information based on the value information.

[0020] In a third aspect, some embodiments of the present application provide a device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described above in the first aspect.

[0021] In a fourth aspect, some embodiments of the present application provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method described above in the first aspect.

[0022] The method, device, electronic device and readable medium for pushing information provided in the embodiments of the present application generate probability values ​​of various alternative plans for disposing of second-hand goods by using feature information of second-hand goods, user feature information and a pre-trained classification model, and select an alternative plan from various alternative plans based on the generated probability values ​​and push it to the terminal with login account information, thereby realizing the push of plans for disposing of second-hand goods to users based on the features of second-hand goods and user characteristics, and improving the efficiency of information push. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0024] Figure 1 are some exemplary system architecture diagrams to which the present application may be applied;

[0025] Figure 2 is a flow chart of an embodiment of a method for pushing information according to the present application;

[0026] Figure 3 is a schematic diagram of an application scenario of the method for pushing information according to the present application;

[0027] Figure 4 is a flowchart of determining an alternative solution in another embodiment of the method for pushing information according to the present application;

[0028] Figure 5 is a structural diagram of an embodiment of a device for pushing information according to the present application;

[0029] Figure 6 It is a structural diagram of a computer system of a server or terminal suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0030] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It should also be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0031] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0032] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of a method for pushing information or an apparatus for pushing information of the present application can be applied.

[0033] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0034] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various client applications, such as social applications, e-commerce applications, search applications, etc., can be installed on terminal devices 101, 102, 103.

[0035] The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices with display screens, including but not limited to smart watches, smart phones, tablet computers, laptop computers, desktop computers, etc. When the terminal devices 101, 102, 103 are software, they may be installed in the electronic devices listed above. They may be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.

[0036] The server 105 may be a server that provides various services, such as a background server that provides support for applications installed on the terminal devices 101, 102, and 103. The terminal devices 101, 102, and 103 or the server 105 may obtain information about second-hand goods and account information for uploading information about second-hand goods; determine feature information of second-hand goods based on the information about second-hand goods, and determine user feature information based on account information; generate probability values ​​of various alternative solutions for disposing of second-hand goods being selected based on the feature information of second-hand goods, user feature information, and a pre-trained classification model; and select an alternative solution from various alternative solutions based on the generated probability values ​​and push it to the terminal that has logged in the account information.

[0037] It should be noted that the method for pushing information provided in the embodiment of the present application can be executed by the server 105 or by the terminal devices 101, 102, 103. Accordingly, the device for pushing information can be set in the server 105 or in the terminal devices 101, 102, 103.

[0038] It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0039] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0040] Continue to refer Figure 2 , shows a process 200 of an embodiment of a method for pushing information according to the present application. The method for pushing information includes the following steps:

[0041] Step 201, obtaining information about second-hand goods and account information for uploading the information about second-hand goods.

[0042] In this embodiment, the method execution body for pushing information (eg Figure 1 The server or terminal shown in the figure can obtain the information of the second-hand goods and the account information for uploading the information of the second-hand goods. The information of the second-hand goods can include the text information or image information of the second-hand goods input by the user, and the user can log in to the e-commerce website or application to submit the information of the second-hand goods to the above-mentioned execution entity. The account information for uploading the information of the second-hand goods can include the account name, account code, account mobile phone number and other information.

[0043] Step 202: determining characteristic information of the second-hand goods according to the information of the second-hand goods, and determining characteristic information of the user according to the account information.

[0044] In this embodiment, the above-mentioned execution entity can determine the characteristic information of the second-hand goods based on the information of the second-hand goods obtained in step 201, and determine the user characteristic information based on the account information obtained in step 201. The information of the second-hand goods may include information actively provided by the user, and may also include information obtained by further retrieving or analyzing the information provided by the user. Determining the characteristic information of the second-hand goods based on the information of the second-hand goods may include extracting the parameter values ​​of the preset parameters in the information of the second-hand goods, and directly using the parameter values ​​as the characteristic information of the second-hand goods, or obtaining the vectorized representation of the parameter values ​​as the characteristic information of the second-hand goods. Similarly, determining the user characteristic information based on the account information may include directly obtaining the user characteristic information from the user's account information, and may also include searching based on the account information to obtain the user characteristic information.

[0045] Here, the information of second-hand goods may include the price of the goods, the size of the goods, the color of the goods, the offline comprehensive quality score of the goods, the real-time quality score of the goods, etc. Account information may include some information that represents the user's own attributes, such as the user's gender, the user's age, the city where the user is located, whether the user is a member, and the user's purchasing power level. Account information may also include some information that represents the user's commodity interaction characteristics, such as user commodity preferences, user category preferences, user brand preferences, user price range preferences, and user store preferences. Account information may also include some other information, such as the model of the mobile phone used by the user, whether the network used by the user is a wireless network or data, the user's weather conditions at the time, and the hot-selling goods in the user's city.

[0046] As an example, when performing vectorization (embedding), features of different granularities are initialized in different ways to construct the Embedding layer. In the training framework of the symbolic mathematics system (Tensorflow) based on data flow programming, the features can first be randomly initialized using a normal distribution, and the dimension of the embedding can be set, such as 5 or 10 dimensions. Then the pre-trained model directory of the configuration file is detected. If the pre-trained embedding of the relevant features is configured, only the pre-trained embedding is used to replace the previously randomly initialized embedding. In addition, vectorization can also be performed with reference to the prior art, such as the word to vector (word2vector) model or the Bidirectional Encoder Representations from Transformers (Bidirectional Encoder Representations from Transformers, Bert) model.

[0047] In some optional implementations of this embodiment, determining the characteristic information of the second-hand commodity according to the information of the second-hand commodity includes: determining the vectorized representation of the information of the second-hand commodity as the characteristic information of the second-hand commodity, wherein the information of the second-hand commodity includes at least one of the following: price information, size information, color information, and quality score information. The quality score information can be determined according to the information of the second-hand commodity provided by the user, and can also be determined comprehensively in combination with the evaluation information and the usage time of the commodity.

[0048] In some optional implementations of this embodiment, determining user characteristic information based on account information includes: querying associated user information based on account information; determining the vectorized representation of user information as user characteristic information, wherein the user information includes at least one of the following: gender information, age information, location information, membership information, purchasing power information, information on the model of mobile phone used, network information used, weather information, product sales information in the user's area, product preference information, category preference information, brand preference information, price preference information, and store preference information. Purchasing power information and preference information can be determined based on the user's historical purchase records. Product sales information in the user's area can determine products with high sales volume in the area.

[0049] Step 203, based on the feature information of the second-hand goods, the feature information of the user and the pre-trained classification model, generates the probability value of each alternative solution for disposing of the second-hand goods being selected.

[0050] In this embodiment, the above-mentioned execution subject can generate the probability value of each alternative solution for disposing of second-hand goods being selected based on the feature information of second-hand goods, user feature information and pre-trained classification model. The feature information of sample second-hand goods and sample user feature information can be used as input, and the solution for disposing second-hand goods selected by the user marked with the sample can be used as output to train the classification model. The trained samples can be constructed based on historical data. The classification model can also be a correspondence table that stores the correspondence between the feature information of second-hand goods, user feature information and the solution for disposing second-hand goods selected by the user, which is pre-formulated by technicians based on statistics of a large number of feature information of second-hand goods, user feature information and the solution for disposing second-hand goods selected by the user.

[0051] In some optional implementations of the present embodiment, based on the feature information of second-hand goods, user feature information and a pre-trained classification model, the probability values ​​of each alternative solution for disposing of second-hand goods being selected are generated, including: performing a merge operation on the feature information of second-hand goods and the feature information of the user that has a pre-set association relationship, the merge operation includes at least one of the following: cosine calculation, inner product calculation, square root calculation, absolute difference calculation; splicing the results of the merge operation to obtain an input vector of the classification model; inputting the input vector into the classification model to generate the probability values ​​of each alternative solution for disposing of second-hand goods being selected. Performing the above-mentioned merge operation can abstract rich representational meanings, making the output of the classification model more accurate. Similarly, the feature information of second-hand goods and the user feature information can also be directly spliced ​​to obtain the input of the classification model.

[0052] In some optional implementations of this embodiment, the classification model includes: a convolutional neural network layer (CNN) and a deep neural network layer (DNN). Low-order and high-order features can be extracted through CNN, and CNN may include a convolution layer, a pooling layer, a fully connected layer, and an activation layer. Among them, the pooling layer can select the maximum preset number as the output after pooling, and enter the fully connected layer after flattening, and the category to which the activation function output belongs. DNN is a multi-layer perceptron superposition, which is the main structure of deep learning, can fit complex features, and is often used for prediction or classification. The intermediate features extracted by convolution can enter the DNN layer, and the loss function can be constructed by back propagation, and the appropriate optimizer can be debugged. The optimal model parameters can also be updated based on the offline evaluation indicator AUC (Area under the ROC curve). In the pre-release stage of the model before the model is officially launched or after the model is officially launched, multi-angle testing or user feedback can be accepted. If abnormal results are found, they should be recorded in time to facilitate further debugging of subsequent models.

[0053] Step 204 , according to the generated probability value, select an alternative from various alternatives and push it to the terminal that logs in the account information.

[0054] In this embodiment, the execution subject may select an alternative from various alternatives and push it to the terminal with the logged-in account information according to the probability value generated in step 203. The alternative may be determined according to a preset rule. As an example, it may be determined according to the value information of the second-hand goods, the user portrait and other related information.

[0055] Continue to see Figure 3 , Figure 3 FIG. 1 is a schematic diagram of an application scenario of the method for pushing information according to this embodiment. Figure 3 In the application scenario, the server 301 can obtain the second-hand goods information 303 uploaded by the terminal device 302 and the account information 304 logged in to the terminal device 302, and determine the alternative plan 305 to be pushed to the terminal device 302 according to the second-hand goods information 303 and the account information 304.

[0056] The method provided by the above-mentioned embodiment of the present application obtains the information of the second-hand goods and the account information for uploading the information of the second-hand goods; determines the characteristic information of the second-hand goods according to the information of the second-hand goods, and determines the user characteristic information according to the account information; generates the probability value of each alternative plan for disposing of the second-hand goods being selected based on the characteristic information of the second-hand goods, the user characteristic information and the pre-trained classification model; selects an alternative plan from each alternative plan according to the generated probability value and pushes it to the terminal with the login account information, thereby realizing automatic connection of WIFI and improving the efficiency of information push.

[0057] Further references Figure 4 , which shows a process 400 of determining an alternative solution in another embodiment of a method for pushing information. The process 400 of determining an alternative solution includes the following steps:

[0058] Step 401, determining the value information of the second-hand goods according to the information of the second-hand goods.

[0059] In this embodiment, the execution subject of the method for pushing information can determine the value information of the second-hand goods based on the information of the second-hand goods. The information of the second-hand goods may include the name of the goods entered by the user, the uploaded goods pictures, the filtered goods attributes, etc. For example, if the second-hand goods are mobile phones, it is necessary to fill in the brand of the mobile phone, the specific model of the mobile phone, the memory of the mobile phone, whether the mobile phone is within the warranty period, the degree of wear and tear of the mobile phone, etc. The value information of the second-hand goods can be determined using a pre-established valuation model or a pre-established valuation rule, and the valuation model or the valuation rule can be determined based on the historical transaction price of the second-hand goods. In addition, the price reduction risk information of the second-hand goods after a predetermined time period can also be pushed to the user.

[0060] Step 402, determining alternative solutions based on the value information.

[0061] In this embodiment, the execution entity may determine alternative solutions according to the value information determined in step 401. The alternative solutions may include auction, trade-in, platform recycling, exchange of equal value goods or a combination of goods, etc.

[0062] In some optional implementations of this embodiment, the alternative solutions include an auction solution; and determining the alternative solution based on the value information includes: determining an estimated transaction price of the auction solution based on the value information.

[0063] In some optional implementations of this embodiment, the alternative plan includes a replacement plan; and determining the alternative plan based on the value information includes: determining the value difference between the second-hand goods and the new goods of the same category based on the value information; or determining the goods to be replaced or the combination of goods to be replaced that matches the value information based on the value information. The goods to be replaced or the combination of goods to be replaced can be determined based on the user's characteristic information and / or the characteristic information of the second-hand goods. For example, the model can be used to determine the goods or the combination of goods that the user is more interested in.

[0064] In this embodiment, other operations of the method for pushing information are substantially the same as the operations of step 201, step 202, step 203, and step 204, and are not described in detail herein.

[0065] from Figure 4 It can be seen that Figure 2 Compared with the corresponding embodiments, in the process 400 of determining alternative solutions of the method for pushing information in this embodiment, alternative solutions are determined through the value information of second-hand goods, and the determined alternative solutions are more accurate, further improving the efficiency of information pushing.

[0066] Further references Figure 5 As an implementation of the methods shown in the above figures, the present application provides an embodiment of a device for pushing information, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0067] like Figure 5 As shown, the device 500 for pushing information in this embodiment includes: an acquisition unit 501, a determination unit 502, a generation unit 503, and a push unit 504. The acquisition unit is configured to acquire information about second-hand goods and account information for uploading information about second-hand goods; the determination unit is configured to determine feature information of second-hand goods according to the information about second-hand goods, and determine user feature information according to the account information; the generation unit is configured to generate probability values ​​of various alternative solutions for disposing of second-hand goods being selected based on the feature information of second-hand goods, user feature information, and a pre-trained classification model; and the push unit is configured to select an alternative solution from various alternative solutions according to the generated probability value and push it to the terminal that logs in the account information.

[0068] In this embodiment, the specific processing of the acquisition unit 501, the determination unit 502, the generation unit 503, and the push unit 504 of the device 500 for pushing information can be referred to. Figure 2 This corresponds to step 201, step 202, step 203 and step 204 in the embodiment.

[0069] In some optional implementations of this embodiment, it is further configured to: determine the vectorized representation of the information of the second-hand goods as the characteristic information of the second-hand goods, wherein the information of the second-hand goods includes at least one of the following: price information, size information, color information, and quality score information.

[0070] In some optional implementations of this embodiment, the determination unit is further configured to: query associated user information based on account information; determine the vectorized representation of the user information as user feature information, wherein the user information includes at least one of the following: gender information, age information, location information, membership information, purchasing power information, information on the model of mobile phones used, network information used, weather information, product sales information in the user's area, product preference information, category preference information, brand preference information, price preference information, and store preference information.

[0071] In some optional implementations of the present embodiment, the generation unit is further configured to: perform a merging operation on feature information of second-hand goods and feature information of user feature information that has a pre-set association relationship, the merging operation comprising at least one of the following: cosine calculation, inner product calculation, square root calculation, absolute difference calculation; concatenate the results of the merging operation to obtain an input vector of the classification model; input the input vector into the classification model to generate probability values ​​of each alternative solution for disposing of the second-hand goods being selected.

[0072] In some optional implementations of this embodiment, the classification model includes: a convolutional neural network layer and a deep neural network layer.

[0073] In some optional implementations of this embodiment, the device further includes an alternative solution determining unit configured to: determine value information of the second-hand commodity based on the information of the second-hand commodity; and determine an alternative solution based on the value information.

[0074] In some optional implementations of this embodiment, the alternative solutions include an auction solution; and the alternative solution determination unit is further configured to: determine an estimated transaction price of the auction solution based on the value information.

[0075] In some optional implementations of this embodiment, the alternative plans include replacement plans; and the alternative plan determination unit is further configured to: determine the value difference between the second-hand goods and the new goods of the same category based on the value information; or determine the goods to be replaced or the combination of goods to be replaced that matches the value information based on the value information.

[0076] The device provided by the above-mentioned embodiments of the present application obtains information about second-hand goods and account information for uploading information about second-hand goods; determines characteristic information of the second-hand goods based on the information about the second-hand goods, and determines user characteristic information based on the account information; generates probability values ​​of various alternative plans for disposing of second-hand goods being selected based on the characteristic information of the second-hand goods, the user characteristic information and a pre-trained classification model; selects an alternative plan from various alternative plans based on the generated probability values ​​and pushes it to the terminal with the logged-in account information, thereby improving the efficiency of information push.

[0077] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 suitable for implementing an electronic device of an embodiment of the present application. Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0078] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0079] The following components can be connected to the I / O interface 605: an input section 606 including such as a keyboard, a mouse, etc.; an output section 607 including such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0080] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium described in the present application can be a computer-readable signal medium or a computer-readable medium or any combination of the above two. The computer-readable medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0081] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0082] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0083] The units involved in the embodiments described in the present application may be implemented by software or by hardware. The described units may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, a determination unit, a generation unit, and a push unit. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the acquisition unit may also be described as "a unit configured to obtain information about second-hand goods and account information for uploading information about second-hand goods."

[0084] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the device, the device: obtains information about second-hand goods and account information for uploading information about second-hand goods; determines feature information of second-hand goods based on the information about second-hand goods, and determines user feature information based on account information; generates probability values ​​of various alternative solutions for disposing of second-hand goods being selected based on the feature information of second-hand goods, user feature information and a pre-trained classification model; and selects an alternative solution from various alternative solutions based on the generated probability values ​​and pushes it to the terminal with logged-in account information.

[0085] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for pushing information, comprising: Obtaining information about second-hand goods and account information for uploading the information about the second-hand goods; Determining characteristic information of the second-hand commodity according to the information of the second-hand commodity, and determining characteristic information of the user according to the account information; Based on the feature information of the second-hand goods, the feature information of the user and the pre-trained classification model, a probability value of each alternative solution for disposing the second-hand goods being selected is generated, wherein each alternative solution is pre-determined according to a preset rule; According to the generated probability value, selecting an alternative plan from the various alternative plans and pushing it to the terminal where the account information is logged; The generating of the probability values ​​of each alternative solution for disposing the second-hand goods being selected based on the feature information of the second-hand goods, the feature information of the user and the pre-trained classification model includes: Performing a merging operation on the feature information of the second-hand commodity and the feature information of the user that has a preset association relationship; Concatenating the results of the merging operation to obtain an input vector of the classification model; The input vector is input into the classification model to generate probability values ​​of each alternative solution for disposing of the second-hand commodity being selected.

2. The method according to claim 1, wherein: The determining the characteristic information of the second-hand commodity according to the information of the second-hand commodity includes: The vectorized representation of the information of the second-hand commodity is determined as the feature information of the second-hand commodity, wherein the information of the second-hand commodity includes at least one of the following: price information, size information, color information, and quality score information.

3. The method according to claim 1, wherein: The determining of user characteristic information according to the account information includes: Querying associated user information according to the account information; The vectorized representation of the user information is determined as the user characteristic information, wherein the user information includes at least one of the following: gender information, age information, location information, membership information, purchasing power information, information on the model of mobile phone used, information on the network used, weather information, product sales information in the user's area, product preference information, category preference information, brand preference information, price preference information, and store preference information.

4. The method according to claim 1, wherein: The merging operation includes at least one of the following: cosine calculation, inner product calculation, square root calculation, and absolute difference calculation.

5. The method according to claim 1, wherein: The classification model comprises: Convolutional neural network layers and deep neural network layers.

6. The method according to any one of claims 1 to 5, wherein: The alternatives include those determined by the following steps: Determining the value information of the second-hand commodity according to the information of the second-hand commodity; The alternative plan is determined according to the value information.

7. The method according to claim 6, wherein: The alternatives include auction options; as well as Determining the alternative plan according to the value information includes: An estimated transaction price of the auction solution is determined based on the value information.

8. The method according to claim 6, wherein: The alternatives include replacement options; as well as Determining the alternative plan according to the value information includes: Determine the value difference between the second-hand product and a new product of the same category based on the value information; or The commodity to be replaced or the commodity combination to be replaced that matches the value information is determined according to the value information.

9. A device for pushing information, characterized in that: The device comprises: an acquisition unit configured to acquire information about the second-hand goods and account information for uploading the information about the second-hand goods; a determining unit configured to determine characteristic information of the second-hand commodity according to the information of the second-hand commodity, and to determine user characteristic information according to the account information; A generating unit configured to generate a probability value of each alternative solution for disposing the second-hand commodity being selected based on the feature information of the second-hand commodity, the feature information of the user and a pre-trained classification model, wherein each alternative solution is predetermined according to a preset rule; A push unit is configured to select an alternative solution from the various alternative solutions according to the generated probability value and push it to the terminal where the account information is logged in; The generating of the probability values ​​of each alternative solution for disposing the second-hand goods being selected based on the feature information of the second-hand goods, the feature information of the user and the pre-trained classification model includes: Performing a merging operation on the feature information of the second-hand commodity and the feature information of the user that has a preset association relationship; Concatenating the results of the merging operation to obtain an input vector of the classification model; The input vector is input into the classification model to generate probability values ​​of each alternative solution for disposing of the second-hand commodity being selected.

10. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images