Resource pushing method and device, equipment, storage medium and program product

Abstract

The invention provides a resource pushing method which can be applied to the technical field of digital marketing, the technical field of computers, the technical field of big data and the technical field of artificial intelligence. The resource pushing method comprises the steps that recommendation demand evaluation is carried out on a to-be-recommended object according to multiple pieces of resource demand attribute data related to the to-be-recommended object, a recommendation demand index of the to-be-recommended object is obtained, and the resource demand attribute data comprise transaction logistics data; determining a target object from the plurality of to-be-recommended objects according to the recommendation demand index; generating a target resource according to the transaction logistics data of the target object; and pushing the target resource to the target object. The invention further provides a resource pushing device and equipment, a storage medium and a program product.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of digital marketing, the technical field of computer, the technical field of big data and the technical field of artificial intelligence, and more particularly, to a resource pushing method and device, equipment, storage medium and program product. BACKGROUND

[0002] In a marketing scenario, in order to improve the user subscription rate, resource information is usually pushed to a large number of users, and then feedback from the users is used to develop a marketing strategy to promote user subscription.

[0003] In the process of implementing the present disclosure, the inventors have found that at least the following problems exist in the related art: the matching degree of the pushed resource information and the user is low, the number of invalid pushes is large, and the resource pushing cost is high. SUMMARY

[0004] Therefore, the present disclosure provides a resource pushing method and device, equipment, storage medium and program product.

[0005] One aspect of the present disclosure provides a resource pushing method, comprising: performing recommendation demand evaluation on a to-be-recommended object according to a plurality of resource demand attribute data related to the to-be-recommended object to obtain a recommendation demand index of the to-be-recommended object, the resource demand attribute data including transaction logistics data; determining a target object from the plurality of to-be-recommended objects according to the recommendation demand index; generating a target resource according to transaction logistics data of the target object; and pushing the target resource to the target object.

[0006] According to an embodiment of the present disclosure, the recommendation demand index includes a plurality of recommendation demand indexes, and the plurality of recommendation demand indexes have different index types.

[0007] According to an embodiment of the present disclosure, performing recommendation demand evaluation on a to-be-recommended object according to a plurality of resource demand attribute data related to the to-be-recommended object to obtain a recommendation demand index of the to-be-recommended object includes: performing feature extraction on the plurality of resource demand attribute data related to the to-be-recommended object to obtain resource demand attribute features; inputting the resource demand attribute features into a demand index prediction network corresponding to each of the plurality of index types respectively to output a plurality of recommendation demand indexes of the to-be-recommended object.

[0008] According to an embodiment of the present disclosure, the demand index prediction network includes a baseline feature extraction layer, a shared feature extraction layer and a demand index prediction layer, and at least two of the plurality of demand index prediction networks have the same shared feature extraction layer.

[0009] According to an embodiment of the present disclosure, the resource demand attribute features are respectively input into demand index prediction networks corresponding to the plurality of index types, and the plurality of recommended demand indexes are output by: inputting the resource demand attribute features into a baseline feature extraction layer to output baseline attribute features; inputting the resource demand attribute features into a shared feature extraction layer to output shared attribute features; fusing the baseline recommended features and the shared recommended features based on an attention mechanism to obtain recommended demand fusion features corresponding to the index types; and inputting the recommended demand fusion features into a demand index prediction layer to output recommended demand indexes corresponding to the index types.

[0010] According to an embodiment of the present disclosure, the transaction logistics data includes a transaction item type and a number of shipping orders related to a transaction item.

[0011] According to an embodiment of the present disclosure, generating the target resource according to the transaction logistics data of the target object includes: determining a target transaction item type from a plurality of transaction item types according to a number of shipping orders corresponding to each of the plurality of transaction item types; determining first logistics service information according to the target transaction item type; and generating the target resource according to the first logistics service information.

[0012] According to an embodiment of the present disclosure, the transaction logistics data includes shipping order area information and a number of shipping orders related to a transaction item.

[0013] According to an embodiment of the present disclosure, generating the target resource according to the transaction logistics data of the target object includes: determining second logistics service information according to the number of shipping orders corresponding to the shipping order area information; and generating the target resource according to the second logistics service information.

[0014] According to an embodiment of the present disclosure, the target resource includes a feedback information box corresponding to the logistics service information, and the logistics service information includes the first logistics service information or the second logistics service information.

[0015] According to an embodiment of the present disclosure, the method further includes: obtaining a resource feedback request from a client corresponding to the target object; and determining the feedback information according to the resource feedback request, wherein the feedback information is generated by the target object in response to an interactive operation of the feedback information box.

[0016] According to an embodiment of the present disclosure, pushing the target resource to the target object includes: pushing the target resource to the target object at a push time period corresponding to the target object.

[0017] According to an embodiment of the present disclosure, the method further includes: determining a delivery time attribute related to a transaction item of the target object according to the transaction logistics data; and determining a push time period corresponding to the target object according to the delivery time attribute.

[0018] According to an embodiment of the present disclosure, the recommendation demand index comprises at least one of the following: a click rate index, a conversion rate index.

[0019] Another aspect of the present disclosure provides a resource pushing apparatus, comprising: a recommendation demand evaluation module configured to evaluate recommendation demands of to-be-recommended objects according to a plurality of resource demand attribute data related to the to-be-recommended objects, and obtain a recommendation demand index of the to-be-recommended objects, wherein the resource demand attribute data comprises transaction logistics data; a target object determination module configured to determine a target object from the to-be-recommended objects according to the recommendation demand index; a target resource generation module configured to generate a target resource according to transaction logistics data of the target object; and a target resource pushing module configured to push the target resource to the target object.

[0020] Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory configured to store 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 as described above.

[0021] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the instructions, when executed, implement the method as described above.

[0022] Another aspect of the present disclosure provides a computer program product comprising computer-executable instructions, wherein the instructions, when executed, implement the method as described above.

[0023] According to an embodiment of the present disclosure, the recommendation demand evaluation is performed on the plurality of resource demand attribute data comprising transaction logistics data, so that the demand degree of the to-be-recommended objects for service resources such as logistics services, marketing services, and data analysis services can be evaluated by fusing the transaction logistics data, the target object with a higher demand degree for resources can be determined according to the recommendation demand index, the target resource that matches the demand of the target object can be generated according to the transaction logistics data of the target object, the personalized resource customization for the demand of the target object can be implemented to make the target resource further satisfy the actual demand of the target object, the number of incorrect pushing of the target resource can be reduced, the pushing amount of the target resource can be reduced by combining the screening of the target object, the communication resource occupation and the communication bandwidth redundancy of the communication device can be reduced, and the resource pushing cost can be reduced. BRIEF DESCRIPTION OF DRAWINGS

[0024] The above and other objects, features and advantages of the present disclosure will become more apparent from the following description when taken in conjunction with the accompanying drawings, in which:

[0025] Figure 1An exemplary system architecture of a resource pushing method, apparatus, device, storage medium and program product according to an embodiment of the present disclosure is schematically shown;

[0026] Figure 2 A flowchart of a resource pushing method according to an embodiment of the present disclosure is schematically shown;

[0027] Figure 3 A schematic diagram of a demand index prediction network according to an embodiment of the present disclosure is schematically shown;

[0028] Figure 4 A schematic diagram of a demand index prediction network according to another embodiment of the present disclosure is schematically shown;

[0029] Figure 5 An application scenario diagram of a resource pushing method according to an embodiment of the present disclosure is schematically shown;

[0030] Figure 6 A block diagram of a resource pushing apparatus according to an embodiment of the present disclosure is schematically shown; and

[0031] Figure 7 A block diagram of an electronic device suitable for implementing a resource pushing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0032] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood, however, that the description which follows is merely exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description of embodiments of the present disclosure, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it would be apparent to one skilled in the art that one or more embodiments of the present disclosure can be practiced without these specific details. In other instances, descriptions of well-known structures and techniques have been omitted in order to avoid obscuring the concepts of the present disclosure.

[0033] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. As used herein, the term "includes" and tautological expressions thereof, such as "including," "includes," "include," "contains," "containing," and so on, mean the presence of stated features, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0034] All terms used herein (including technical and scientific terms) have the meanings commonly understood by one of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings that are consistent with the context of the specification, and should not be interpreted in an idealized or overly formal manner.

[0035] In the case of using expressions similar to "at least one of A, B, and C, etc.", it is generally interpreted in the meaning that the skilled person in the art usually understands the expression (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, a system having B alone, a system having C alone, a system having both A and B, a system having both A and C, a system having both B and C, and / or a system having A, B, and C, etc.).

[0036] In embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) comply with relevant laws and regulations, are used for legal purposes, and do not violate public order and good customs. In particular, necessary measures have been taken to prevent illegal access to user personal information data, to maintain user personal information security, network security and national security.

[0037] In embodiments of the present disclosure, the authorization or consent of the user is obtained before the user's personal information is acquired or collected.

[0038] In the marketing scenario, in order to improve the user subscription rate, a large number of users are usually pushed with resource information such as short message messages and client notification messages, so that the user can browse the resource information content related to the demand in time, thereby meeting the actual needs of the user. In some scenarios, the user can also fill in the related demand content in the pushed resource information, so as to provide corresponding services according to the demand content of the user in the future.

[0039] For example, in the marketing scenario, in order to promote user subscription and increase business income, potential users can be found from a large number of users based on industry information, registered capital or sales experience, etc., and then information collection is performed on the potential users through short message, etc. and users with logistics cooperation intention are identified through outbound call, and are incubated into hot leads. For users with high cooperation intention, sales personnel are issued, so as to reduce the human cost of sales, and promote customer subscription.

[0040] However, at least the following problems exist in the related art: the matching degree of the pushed resource information and the user demand is low, the number of invalid pushes is large, and the resource pushing cost is high.

[0041] To solve the above problems, embodiments of the present disclosure provide a resource pushing method, comprising: performing recommendation demand evaluation on a to-be-recommended object according to a plurality of resource demand attribute data related to the to-be-recommended object, obtaining a recommendation demand index of the to-be-recommended object, and the resource demand attribute data comprising transaction logistics data; determining a target object from a plurality of to-be-recommended objects according to the recommendation demand index; generating a target resource according to the transaction logistics data of the target object; and pushing the target resource to the target object.

[0042] Figure 1 An example system architecture to which the resource pushing method, apparatus, device, storage medium, and program product according to embodiments of the present disclosure can be applied is schematically shown. It should be noted that, Figure 1 The shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0043] As Figure 1 shown, the system architecture 100 according to the embodiment can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired and / or wireless communication links, etc.

[0044] The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (only as examples).

[0045] The terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0046] The server 105 can be a server providing various services, such as a background management server providing support for websites browsed by users using the terminal devices 101, 102, 103 (only as an example). The background management server can analyze and process received user requests and other data, and feed back the processing results (such as web pages, information, or data, etc. obtained or generated according to user requests) to the terminal devices.

[0047] It should be noted that the resource pushing method provided by the embodiments of the present disclosure can generally be executed by the server 105. Correspondingly, the resource pushing system provided by the embodiments of the present disclosure can generally be arranged in the server 105. The resource pushing method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105. Correspondingly, the resource pushing system provided by the embodiments of the present disclosure can also be arranged in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105. Alternatively, the resource pushing method provided by the embodiments of the present disclosure can also be executed by the terminal devices 101, 102, or 103, or by other terminal devices different from the terminal devices 101, 102, or 103. Correspondingly, the resource pushing system provided by the embodiments of the present disclosure can also be arranged in the terminal devices 101, 102, or 103, or in other terminal devices different from the terminal devices 101, 102, or 103.

[0048] For example, the plurality of resource demand attribute data related to the to-be-recommended object can be originally stored in any one of the terminal devices 101, 102, or 103 (for example, the terminal device 101, but not limited thereto), or stored on an external storage device and imported into the terminal device 101. Then, the terminal device 101 can execute the resource pushing method provided by the embodiments of the present disclosure locally, or send the plurality of resource demand attribute data related to the to-be-recommended object to other terminal devices, servers, or server clusters, and execute the resource pushing method provided by the embodiments of the present disclosure by the other terminal devices, servers, or server clusters receiving the plurality of resource demand attribute data related to the to-be-recommended object.

[0049] It should be understood that Figure 1 The number of terminal devices, networks, and servers in the system shown in FIG. 1 is only illustrative. According to the needs of implementation, there can be any number of terminal devices, networks, and servers.

[0050] Figure 2 A flowchart of a resource pushing method according to an embodiment of the present disclosure is schematically shown.

[0051] As Figure 2 shown, the method includes operations S210-S240.

[0052] In operation S210, a recommendation demand evaluation is performed on the to-be-recommended object according to the plurality of resource demand attribute data related to the to-be-recommended object, and a recommendation demand index of the to-be-recommended object is obtained, wherein the resource demand attribute data includes transaction flow data.

[0053] According to an embodiment of the present disclosure, the to-be-recommended object can include an object sales object, for example, can be a sales party in an e-commerce platform; can also include an object purchase object, for example, can be a purchase party in need of object purchase. It should be understood that the to-be-recommended object can receive or send messages through a terminal device such as a smart phone, and can also authorize the acquisition of data (including but not limited to resource demand attribute data) through the terminal device to improve the resource quality of the received resources.

[0054] According to an embodiment of the present disclosure, the authorization or consent of the user is obtained before the resource demand attribute data is obtained. The resource demand attribute data can include basic data, transaction data, and historical order information of the to-be-recommended object. The basic data can include geographic location, user type, industry, business scope, user age, occupation, etc.; the transaction data can include order address, annual order address volume, order address volume in the last 90 days, purchasing power, target category, maximum first-level category of order volume in the last 90 days, and average order value; and the transaction logistics data can include historical order information of the to-be-recommended object, which can include consigned goods, first-level commodity category, second-level commodity category, third-level commodity category, order volume, and order quarter.

[0055] According to an embodiment of the present disclosure, the recommendation demand index can include any index used to evaluate the resource demand of the to-be-recommended object, for example, at least one of a click rate index, a conversion rate index, and a click and conversion rate index.

[0056] According to an embodiment of the present disclosure, the transaction logistics data can include historical order data of the object sales party, for example, can include order volume, order address, consigned goods category, order time, etc.

[0057] According to an embodiment of the present disclosure, the recommendation demand index of the to-be-recommended object can be obtained through a neural network model. For example, multiple resource demand attribute data can be processed based on a convolutional neural network model to obtain the recommendation demand index. However, it is not limited to this, and other types of models can also be used to process multiple resource demand attribute data, for example, a multilayer perceptron model, etc., and the embodiments of the present disclosure do not limit this.

[0058] In operation S220, a target object is determined from the multiple to-be-recommended objects according to the recommendation demand index.

[0059] According to an embodiment of the present disclosure, one or more target objects can be determined from the multiple to-be-recommended objects according to the recommendation demand index and a preset rule. The preset rule can include: determining a to-be-recommended object whose recommendation demand index is greater than or equal to a first predetermined threshold as a target object.

[0060] According to an embodiment of the present disclosure, the preset rule can also include: sorting the to-be-recommended objects according to the numerical value of the recommendation demand index, and selecting a predetermined number of to-be-recommended objects as target objects.

[0061] In operation S230, a target resource is generated according to the transaction logistics data of the target object.

[0062] According to an embodiment of the present disclosure, the target resource can be generated according to the historical shipping order data of the target object. For example, the target resource that matches the personalized demand of the target object can be generated based on the shipping order data such as the number of historical shipping orders, the type of mail items, the weight of mail items, etc. The target resource can include a service item list, preferential information, or any type of information, and the embodiments of the present disclosure are not limited thereto.

[0063] According to an embodiment of the present disclosure, the historical shipping order data of the target object can be processed according to a neural network algorithm to predict the demand of the target object, such as the demand for transaction item type, the demand for geographical span, the demand for logistics time limit, etc., and the target resource that matches the demand can be generated according to the actual demand of the target object.

[0064] In operation S240, the target resource is pushed to the target object.

[0065] According to an embodiment of the present disclosure, the recommendation demand evaluation is performed on the multiple resource demand attribute data containing transaction logistics data, so that the to-be-recommended resource can be accurately evaluated in terms of resource demand by fusing the transaction logistics data, so as to determine the target object with strong resource demand according to the recommendation demand index, generate the target resource that matches the resource demand of the target object according to the transaction logistics data of the target object, and accurately configure the resource that matches the target object according to the actual transaction and the mailing data of the transaction items, so as to realize the personalized resource customization of the resource demand of the target object, so that the target resource can further meet the actual demand of the target object, reduce the number of incorrect pushing of the target resource, and reduce the pushing amount of the target resource in combination with the screening of the target object, reduce the communication resource occupation and communication bandwidth redundancy of the communication device, and reduce the resource pushing cost.

[0066] According to an embodiment of the present disclosure, the recommendation demand index includes at least one of the following: a click rate index, a conversion rate index.

[0067] According to an embodiment of the present disclosure, the purpose of resource pushing is not only to retain users, but also to obtain more user information and user cooperation intention in the case of user authorization, and ultimately to achieve user subscription. Therefore, at least one of the click rate index and the conversion rate is taken as a target in the embodiment of the present disclosure.

[0068] According to an embodiment of the present disclosure, the recommendation demand index can include multiple, and the multiple recommendation demand indexes have different index types.

[0069] According to an embodiment of the present disclosure, the recommendation demand index can include a click rate index and a conversion rate index.

[0070] According to an embodiment of the present disclosure, the recommendation demand index of the to-be-recommended object is obtained by performing recommendation demand evaluation on the to-be-recommended object according to the multiple resource demand attribute data related to the to-be-recommended object, including: performing feature extraction on the multiple resource demand attribute data related to the to-be-recommended object to obtain resource demand attribute features; inputting the resource demand attribute features into the demand index prediction network corresponding to each of the multiple index types respectively, and outputting multiple recommendation demand indexes of the to-be-recommended object.

[0071] According to an embodiment of the present disclosure, the resource demand attribute data involved in the embodiment of the present disclosure includes but is not limited to basic data of the user, and specifically can include geographic location, user type, industry to which the user belongs, business scope, etc. For non-numeric features, and among them, there are character type features of long text, such as business scope, etc., a word embedding model can be used to map them to a low-dimensional vector. For short character category features that do not have a size relationship, features with less feature value can be mapped by one-hot encoding. And for features with too many feature values, to avoid the sparsity of the feature matrix and the too high dimension of the features, a feature hashing method can be used to convert them to low-dimensional features without losing the original features.

[0072] According to an embodiment of the present disclosure, the resource demand attribute data involved in the embodiment of the present disclosure includes but is not limited to age, single price, etc. For such numeric type features, which are unevenly distributed or have a large magnitude span, can be processed by bucketing.

[0073] According to an embodiment of the present disclosure, the resource demand attribute data involved in the embodiment of the present disclosure includes but is not limited to consignments, commodity categories, etc. For such long character type features, Chinese word segmentation can be performed, and a statistical method can be used to convert them to feature vectors based on word frequency. Considering that the dimension of the vector can be too high, therefore, the low-dimensional feature vector can be obtained by feature extraction according to the importance.

[0074] Figure 3 The schematic diagram of the principle of the demand index prediction network according to an embodiment of the present disclosure is shown.

[0075] As shown in Figure 3 The demand index prediction network 300 can include two sub-networks, i.e., a first sub-network 310 and a second sub-network 320. The first sub-network 310 can include a first embedding layer 311, a first pooling layer 312, a first full connection layer 313, and a first demand index prediction layer 314. The second sub-network 320 can include a second embedding layer 321, a second pooling layer 322, a second full connection layer 323, and a second demand index prediction layer 324. The first embedding layer 311 and the second embedding layer 321 can share parameters. The first demand index prediction layer 314 and the second demand index prediction layer 324 can be constructed based on a multilayer perception algorithm, or can be constructed based on a multi-scale convolutional neural network, and the embodiments of the present disclosure do not make any limitation in this regard. According to the embodiments of the present disclosure, the first embedding layer 311 is configured to perform low-dimensional embedding mapping processing on resource demand attribute features to obtain a feature matrix; the first pooling layer 312 is configured to sum all entity embedding vectors of the same type to obtain a vector corresponding to the current type; the first full connection layer 313 is configured to splice vectors of all types; and the first demand index prediction layer 314 is configured to process the spliced vectors to obtain a first recommended demand index.

[0076] According to the embodiments of the present disclosure, the click rate index and the conversion rate index can also be fused as the recommended demand index, i.e., the click and conversion rate 304 of the potential customer is considered, which is the probability of signing a contract by the potential customer under the condition of pushing resource exposure. The conversion indexes of each stage are comprehensively considered to avoid the situation that the capital retention rate is high but the signing rate is low, or the signing rate is high but the capital retention rate is low, which affects the overall investment return rate.

[0077] According to the embodiments of the present disclosure, the first demand index can be a conversion rate index, and the second demand index can be a click rate index. When the conversion rate task and the click rate task are trained separately, the conversion rate task selects samples after capital retention, but the entire sample space needs to be predicted, which leads to different sample distributions and a large deviation between the two tasks, which has a great challenge to the generalization ability of the model. In addition, the proportion of the capital retention samples is relatively small, and there is a problem of sample sparsity. The embodiments of the present disclosure fuse the two indexes, learn the conversion rate implicitly through an explicit learning task, and train and predict the click rate and the click and conversion rate in the full sample space.

[0078] According to the embodiments of the present disclosure, the product of the click rate and the conversion rate can be used to calculate the loss during training, and the embedding layer data of the two tasks is shared. When back propagation is performed, the parameters of the two tasks are updated simultaneously. Therefore, both the click rate and the conversion rate are aware of the fusion target, and the estimated results of the click rate, the conversion rate, and the conversion rate after clicking can be finally obtained.

[0079] According to an embodiment of the present disclosure, the demand index prediction network can overcome the problem of sampling bias by implicitly learning through auxiliary tasks, and provide generalization capability of the demand index prediction network; and can overcome the problem of data sparsity through shared embedding layer data, and improve the fitting capability of the demand index prediction network.

[0080] According to an embodiment of the present disclosure, the demand index prediction network comprises a benchmark feature extraction layer, a shared feature extraction layer and a demand index prediction layer, and at least two of the plurality of demand index prediction networks have the same shared feature extraction layer.

[0081] Figure 4 A schematic diagram of a demand index prediction network according to another embodiment of the present disclosure is shown.

[0082] As shown in Figure 4 , the multi-task prediction network 400 can comprise three feature extraction layers, a first benchmark feature extraction layer 411, a second benchmark feature extraction layer 412 and a shared feature extraction layer 413. The first benchmark feature extraction layer 411 and the second benchmark feature extraction layer 412 correspond to the first recommended demand index 402 and the second recommended demand index 403 respectively. The feature extraction layer can be constructed based on a neural network algorithm, for example, can be constructed based on a multi-scale convolutional neural network, or can also be constructed based on a multi-layer perceptron algorithm, and the embodiments of the present disclosure do not limit this.

[0083] According to an embodiment of the present disclosure, the resource demand attribute features are respectively input into the demand index prediction networks corresponding to the respective index types, and the plurality of recommended demand indexes are output by: inputting the resource demand attribute features into the benchmark feature extraction layer to output benchmark attribute features; inputting the resource demand attribute features into the shared feature extraction layer to output shared attribute features; fusing the benchmark recommended features and the shared recommended features based on an attention mechanism to obtain recommended demand fusion features corresponding to the index types; and inputting the recommended demand fusion features into the demand index prediction layer to output the recommended demand indexes corresponding to the index types.

[0084] As shown in Figure 4As shown, the resource demand attribute features 401 can be respectively input to the first reference feature extraction layer 411, the second reference feature extraction layer 412, and the shared feature extraction layer 413, so that the three feature extraction layers respectively extract the encoding sequence attribute features in the resource demand attribute features 401, and output the first reference feature, the second reference feature, and the shared reference feature. The first reference feature and the shared reference feature can be input to the first gating layer 421 to realize fusion of the first reference feature and the shared reference feature based on the attention mechanism, and output the first recommendation demand fusion feature corresponding to the first recommendation demand indicator 402. The second reference feature and the shared reference feature can be input to the second gating layer 422 to realize fusion of the second reference feature and the shared reference feature based on the attention mechanism, and output the second recommendation demand fusion feature corresponding to the second recommendation demand indicator 403. Fusion of the shared reference feature with the first reference feature and the second reference feature based on the attention mechanism can enable the first recommendation demand fusion feature and the second recommendation demand fusion feature to respectively learn attribute features for recommendation demand indicators of different indicator types.

[0085] It should be noted that the first gating layer 421 and the second gating layer 422 of the embodiments of the present disclosure can each include a plurality of gating sub-layers, which can be constructed based on a gating recurrent neural network to improve learning of the multi-task prediction network to a deep level of attribute expression.

[0086] As shown, Figure 4 The first recommendation demand fusion feature and the second recommendation demand fusion feature are respectively input to the first recommendation demand indicator prediction layer 431 and the second recommendation demand indicator UI side layer 432, and the first recommendation demand indicator 402 and the second recommendation demand indicator 403 are output.

[0087] According to an embodiment of the present disclosure, the transaction logistics data includes a transaction item type and a number of shipping orders related to a transaction item.

[0088] According to an embodiment of the present disclosure, the transaction item type can include cold-chain logistics, hour-arrival logistics, large-item logistics, and single-order logistics.

[0089] According to an embodiment of the present disclosure, generating the target resource according to the transaction logistics data of the target object includes: determining a target transaction item type from a plurality of transaction item types according to a number of shipping orders corresponding to each of the plurality of transaction item types; determining first logistics service information according to the target transaction item type; and generating the target resource according to the first logistics service information.

[0090] According to an embodiment of the present disclosure, determining the target transaction item type from the plurality of transaction item types can include: screening a transaction item type with a number of shipping orders exceeding a second predetermined threshold as the target transaction item type.

[0091] According to an embodiment of the present disclosure, the first logistics service information can include a target transaction item type and preferential information corresponding to the target transaction item type. The preferential information corresponding to the target transaction item type can be related to the corresponding number of waybills.

[0092] According to an embodiment of the present disclosure, screening the target transaction item type according to the number of waybills can reduce the number of resource pushes. Determining the first logistics service information according to the target transaction item type can further meet the actual needs of the target object.

[0093] According to an embodiment of the present disclosure, the transaction logistics data includes waybill area information and the number of waybills related to transaction items.

[0094] According to an embodiment of the present disclosure, the waybill area information can include sender area information, recipient area information, and pick-up area span.

[0095] According to an embodiment of the present disclosure, generating the target resource according to the transaction logistics data of the target object includes: determining second logistics service information according to the number of waybills corresponding to the waybill area information; and generating the target resource according to the second logistics service information.

[0096] According to an embodiment of the present disclosure, the second logistics service information can include waybill area information and preferential information corresponding to the waybill area information. The preferential information corresponding to the waybill area information can be related to the corresponding number of waybills.

[0097] According to an embodiment of the present disclosure, the second logistics service information determined according to the number of waybills corresponding to the waybill area information is more in line with the actual needs of the target object.

[0098] According to an embodiment of the present disclosure, the transaction logistics data can include transaction item types and the number of waybills related to transaction items, and waybill area information and the number of waybills related to transaction items.

[0099] According to an embodiment of the present disclosure, generating the target resource according to the transaction logistics data of the target object includes: determining a target transaction item type from a plurality of transaction item types according to the number of waybills corresponding to each of the plurality of transaction item types; determining first logistics service information according to the target transaction item type; determining second logistics service information according to the number of waybills corresponding to the waybill area information; and generating the target resource according to the first logistics service information and the second logistics service information.

[0100] According to the embodiment of the present disclosure, the first logistics service information related to the target transaction item type and the second logistics service information related to the waybill area can be combined, and the target resource generated based thereon can further meet the actual needs of the target object, reduce the number of target resource error push, and reduce the resource push cost.

[0101] According to the embodiment of the present disclosure, the target resource includes a feedback information box corresponding to the logistics service information, and the logistics service information includes the first logistics service information or the second logistics service information.

[0102] According to the embodiment of the present disclosure, the feedback information box can include a user name, a transaction logistics platform, logistics service information, user demand information, and the like.

[0103] According to the embodiment of the present disclosure, the method further includes: obtaining a resource feedback request from a client corresponding to the target object; and determining feedback information according to the resource feedback request, wherein the feedback information is generated by the target object for the interactive operation of the feedback information box.

[0104] According to the embodiment of the present disclosure, the resource feedback request can be a subscription demand of the target object, a preferential demand of the target object, a transaction item type demand of the target object, a waybill area demand of the target object, and the like.

[0105] According to the embodiment of the present disclosure, by using the resource feedback request of the target object, the subscription intention and the actual demand of the target object can be further obtained, thereby providing a basis for subsequent marketing strategy.

[0106] According to the embodiment of the present disclosure, the target resource pushed to the target object includes: pushing the target resource to the target object in a push time period corresponding to the target object.

[0107] According to the embodiment of the present disclosure, for different target objects, the click rate of resource information pushed in different working days and different time periods is different. The same or similar type of target objects can be randomly divided, and the target objects can be reached in different working days and different time periods, so as to determine the push time period. For example, the click rate of the target resource in the time period of 7:00 to 8:00 on Thursday and Friday is relatively high, so the two time periods are finally selected to push the target resource to the target object.

[0108] According to the embodiment of the present disclosure, the target resource is pushed in the push time period corresponding to the target object, thereby improving the click rate of the target resource and the subscription rate of the target object.

[0109] According to an embodiment of the present disclosure, the method further includes: determining, according to the transaction logistics data, a delivery time attribute related to the transaction item of the target object; and determining, according to the delivery time attribute, a push time period corresponding to the target object.

[0110] According to an embodiment of the present disclosure, the delivery time attribute can include an item delivery start time of the target object, an item delivery time period, etc. Determining the push time period corresponding to the target object according to the delivery time attribute can include determining, according to the delivery time attribute and waybill data corresponding to the delivery time attribute, such as the number of waybills and the number of item mailings, a concentrated shipping time period in which the target object is likely to mail items in large quantities in the future, and then determining the push time period as a time period before the concentrated shipping time period or a start time of the concentrated shipping time period, so as to facilitate pushing of personalized target resources to the target object before the target object conducts large-scale item transactions and concentrated shipping, so as to timely meet the actual needs of the target object, improve the click rate or conversion rate of the target object for the target resources, avoid information interference caused by receiving service resources in the case that the target object does not need to conduct logistics services or has determined logistics services, improve the accuracy of resource pushing, and improve the degree of pushing refinement, thereby reducing the amount of resource pushing, reducing the frequency of resource pushing, reducing the information throughput of the communication device, and reducing the communication bandwidth occupation. According to an embodiment of the present disclosure, the delivery time attribute is determined through transaction logistics data, and the push time period is determined based on the delivery time attribute, so that the determination of the push time period is more convenient and accurate.

[0111] Figure 5 An application scenario diagram of the resource pushing method according to an embodiment of the present disclosure is schematically shown.

[0112] As shown in Figure 5 , the resource pushing method can be stored in a resource pushing model 520. The resource pushing model 520 can include a target object determination layer 521, a target resource generation layer 522, and a push time period determination layer 523.

[0113] As shown in Figure 5As shown, the first resource requirement attribute data 511 and the second resource requirement attribute data 512 can be input into the resource pushing model 520. The target object determination layer 521 can process the resource requirement attribute data 510 through a multi-target recommendation algorithm model to obtain a recommended demand index, and determine a target object from a plurality of to-be-recommended objects according to the recommended demand index, so as to more accurately identify high-quality potential customers. The target resource generation layer 522 can distinguish different types of potential customers (target objects), and configure different pushing information and personalized forms (target resources) for potential customers with different characteristics. The pushing time period determination layer 523 can select a time period with relatively high click rate or conversion rate for resource pushing according to the sensitivity of potential customers to resource pushing information at different times.

[0114] According to an embodiment of the present disclosure, the retained capital customer information 531 can be combined to artificially call and cultivate 532 the retained capital potential customers, explore other information of the potential customers, and identify the cooperation intention of the potential customers.

[0115] According to an embodiment of the present disclosure, the high-intention and high-quality potential customers can be issued to sales personnel, and the retained capital customer information 531 and other gain information 541 are attached to help sales personnel promote signing.

[0116] According to an embodiment of the present disclosure, compared with a scheme of performing mass screening and resource pushing based on a single rule and sales experience, the embodiment of the present disclosure improves the stage conversion rate and the final signing rate of the to-be-recommended objects, wherein the exposure rate of retained capital is increased by 0.02%, the signing rate of retained capital is increased by 0.15%, the signing cost of a single customer is reduced by 10.3%, the number of incorrect target resource pushing and the pushing amount of target resources are reduced, the communication resource occupation and communication bandwidth redundancy of the communication device are reduced, and the resource pushing cost is reduced.

[0117] Figure 6 A block diagram of a resource pushing apparatus according to an embodiment of the present disclosure is schematically shown.

[0118] As Figure 6 shown, the resource pushing apparatus 600 includes a recommended demand evaluation module 610, a target object determination module 620, a target resource generation module 630, and a target resource pushing module 640.

[0119] The recommended demand evaluation module 610 is configured to perform recommended demand evaluation on the to-be-recommended objects according to a plurality of resource requirement attribute data related to the to-be-recommended objects, and obtain a recommended demand index of the to-be-recommended objects, wherein the resource requirement attribute data includes transaction logistics data.

[0120] The target object determination module 620 is configured to determine a target object from a plurality of to-be-recommended objects according to the recommended demand index.

[0121] The target resource generation module 630 is configured to generate the target resource according to transaction logistics data of the target object.

[0122] The target resource pushing module 640 is configured to push the target resource to the target object.

[0123] According to an embodiment of the present disclosure, the recommendation demand evaluation module 610 includes a feature extraction sub-module and a recommendation demand index output sub-module. The feature extraction sub-module is configured to perform feature extraction on a plurality of resource demand attribute data related to the object to be recommended, to obtain resource demand attribute features. The recommendation demand index output sub-module is configured to input the resource demand attribute features into a demand index prediction network corresponding to each of a plurality of index types, respectively, to output a plurality of recommendation demand indexes of the object to be recommended.

[0124] According to an embodiment of the present disclosure, the recommendation demand index output sub-module includes a benchmark attribute feature output unit, a shared attribute feature output unit, a fusion unit, and a recommendation demand index output unit. The benchmark attribute feature output unit is configured to input the resource demand attribute features into a benchmark feature extraction layer, to output benchmark attribute features. The shared attribute feature output unit is configured to input the resource demand attribute features into a shared feature extraction layer, to output shared attribute features. The fusion unit is configured to fuse the benchmark recommendation features and the shared recommendation features based on an attention mechanism, to obtain recommendation demand fusion features corresponding to the index types. The recommendation demand index output unit is configured to input the recommendation demand fusion features into a demand index prediction layer, to output the recommendation demand indexes corresponding to the index types.

[0125] According to an embodiment of the present disclosure, the target resource generation module 630 includes a target transaction item type determination sub-module, a first logistics service information determination sub-module, and a first target resource generation sub-module. The target transaction item type determination sub-module is configured to determine a target transaction item type from a plurality of transaction item types according to a number of waybills corresponding to each of the plurality of transaction item types of the target object. The first logistics service information determination sub-module is configured to determine first logistics service information according to the target transaction item type. The first target resource generation sub-module is configured to generate the target resource according to the first logistics service information.

[0126] According to an embodiment of the present disclosure, the target resource generation module 630 includes a second logistics service information determination sub-module and a second target resource generation sub-module. The second logistics service information determination sub-module is configured to determine second logistics service information according to a number of waybills corresponding to waybill area information. The second target resource generation sub-module is configured to generate the target resource according to the second logistics service information.

[0127] According to an embodiment of the present disclosure, the resource push device 600 further includes a resource feedback request acquisition module and a feedback information determination module. The resource feedback request acquisition module is configured to acquire a resource feedback request from a client corresponding to a target object; and the feedback information determination module is configured to determine feedback information based on the resource feedback request, wherein the feedback information is generated by the target object's interactive operation with respect to the feedback information box.

[0128] According to an embodiment of the present disclosure, the target resource push module 640 includes a target resource push submodule configured to push the target resource to the target object during a push time period corresponding to the target object.

[0129] According to an embodiment of the present disclosure, the target resource push module 640 further includes a delivery time attribute determination submodule and a push time period determination submodule. The delivery time attribute determination submodule is configured to determine the delivery time attribute associated with the target transaction item based on the transaction logistics data, and the push time period determination submodule is configured to determine the push time period corresponding to the target item based on the delivery time attribute.

[0130] According to the modules, submodules, units, and subunits of the embodiments of the present invention, any multiple or at least part of the functions of any multiple thereof can be implemented in one module. According to the modules, submodules, units, and subunits of the embodiments of the present invention, any one or more thereof can be split into multiple modules for implementation. According to the modules, submodules, units, and subunits of the embodiments of the present invention, any one or more thereof can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware of any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware, and firmware or in an appropriate combination of any of them. Alternatively, according to the modules, submodules, units, and subunits of the embodiments of the present invention, one or more thereof can be at least partially implemented as a computer program module, which can perform the corresponding function when the computer program module is run.

[0131] For example, any multiple of the recommendation demand evaluation module 610, the target object determination module 620, the target resource generation module 630 and the target resource pushing module 640 can be combined in one module / unit / sub-unit for implementation, or any one of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of the modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units, and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the recommendation demand evaluation module 610, the target object determination module 620, the target resource generation module 630 and the target resource pushing module 640 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or any other reasonable manner of integrating or packaging a circuit, etc. hardware or firmware, or in any one of software, hardware and firmware implementation or in a proper combination of any of them. Alternatively, at least one of the recommendation demand evaluation module 610, the target object determination module 620, the target resource generation module 630 and the target resource pushing module 640 can be at least partially implemented as a computer program module which can perform corresponding functions when the computer program module is run.

[0132] It should be noted that the resource pushing system part in the embodiments of the present disclosure corresponds to the resource pushing method part in the embodiments of the present disclosure, and the description of the resource pushing system part is specifically referred to the resource pushing method part, which will not be repeated here.

[0133] Figure 7 A block diagram of an electronic device suitable for implementing the resource pushing method according to an embodiment of the present disclosure is schematically shown. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and use range of the embodiments of the present disclosure.

[0134] As Figure 7As shown, the electronic device 700 according to embodiments of the present disclosure includes a processor 701 that can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 702 or loaded into a random access memory (RAM) 703 from a storage section 708. The processor 701 can include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor, and / or a related chipset and / or a dedicated microprocessor (e.g., an application specific integrated circuit (ASIC)), and so on. The processor 701 can also include an on-board memory for cache use. The processor 701 can include a single processing unit or multiple processing units for executing different actions of the method processes according to embodiments of the present disclosure.

[0135] In the RAM 703, various programs and data required for the operation of the electronic device 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. The processor 701 performs various operations of the method processes according to embodiments of the present disclosure by executing the programs in the ROM 702 and / or the RAM 703. Note that the programs described above can also be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 can also perform various operations of the method processes according to embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0136] According to embodiments of the present disclosure, the electronic device 700 can also include an input / output (I / O) interface 705 that is also connected to the bus 704. The system 700 can further include one or more of the following components connected to the input / output (I / O) interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as necessary. A removable medium 711 such as a magnetic disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 710 as necessary, so that a computer program read out therefrom is installed into the storage section 708 as necessary.

[0137] According to an embodiment of the present disclosure, the method flow according to the embodiments of the present disclosure can be implemented as a computer software program. For example, the embodiments of the present disclosure include a computer program product comprising a computer program carrying out the program codes for executing the method shown in the flow chart. In such embodiments, the computer program can be downloaded and installed from a network through the communication part 709, and / or installed from the detachable medium 711. When the computer program is executed by the processor 701, the above-mentioned functions defined in the system / apparatus according to the embodiments of the present disclosure are executed. According to an embodiment of the present disclosure, the system, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0138] The present disclosure also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments, or exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, which when executed, implement the method according to the embodiments of the present disclosure.

[0139] According to an embodiment of the present disclosure, the computer readable storage medium can be a non-volatile computer readable storage medium. For example, it can include but not limited to portable computer diskette, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), portable compact disc read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0140] For example, according to an embodiment of the present disclosure, the computer readable storage medium can include the ROM 702 and / or the RAM 703 described above and / or one or more memories other than the ROM 702 and the RAM 703.

[0141] The embodiments of the present disclosure also include a computer program product comprising a computer program containing program codes for executing the method provided by the embodiments of the present disclosure, which program codes are used to make the electronic device implement the resource pushing method provided by the embodiments of the present disclosure when the computer program product is running on the electronic device.

[0142] When the computer program is executed by the processor 701, the above-mentioned functions defined in the system / apparatus according to the embodiments of the present disclosure are executed. According to an embodiment of the present disclosure, the system, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0143] In one embodiment, the computer program can be embodied on a tangible memory device, such as a magnetic storage device, an optical storage device, etc. In another embodiment, the computer program can be transmitted in a signal over a network, distributed across networks, downloaded and installed, and / or installed from a removable memory media 711. The computer program comprising the program code can be transmitted using any suitable network medium, including, but not limited to wireless, wired, etc., or any suitable combination of the foregoing.

[0144] According to an embodiment of the disclosure, program code for execution by a computer program can be written in any combination of one or more programming languages, and can specifically be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, Java, C++, python, "C", or similar programming languages. Program code can execute entirely on a user's computing device, partly on a user's device, partly on a remote computing device, or entirely on a remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0145] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes may occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, as well as the combination of boxes in the block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or may be implemented using a combination of dedicated hardware and computer instructions. It will be understood by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or coupled in various ways, and all such combinations and / or couplings fall within the scope of the present disclosure.

[0146] The embodiments of the present disclosure are described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be used in combination to advantage. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A resource pushing method, comprising: performing recommendation demand evaluation on a to-be-recommended object according to a plurality of resource demand attribute data related to the to-be-recommended object, to obtain a recommendation demand index of the to-be-recommended object, wherein the resource demand attribute data comprises transaction logistics data; determining a target object from a plurality of the to-be-recommended objects according to the recommendation demand index; generating a target resource according to transaction logistics data of the target object; and pushing the target resource to the target object. The recommendation demand index comprises a plurality of recommendation demand indexes having different index types.

2. The method of claim 1, wherein, The performing recommendation demand evaluation on a to-be-recommended object according to a plurality of resource demand attribute data related to the to-be-recommended object, to obtain a recommendation demand index of the to-be-recommended object comprises: performing feature extraction on a plurality of resource demand attribute data related to the to-be-recommended object to obtain resource demand attribute features; inputting the resource demand attribute features into a demand index prediction network corresponding to each of the index types respectively, to output a plurality of the recommendation demand indexes of the to-be-recommended object. The demand index prediction network comprises a baseline feature extraction layer, a shared feature extraction layer, and a demand index prediction layer, and at least two of the plurality of demand index prediction networks have the same shared feature extraction layer.

3. The method of claim 2, wherein, The inputting the resource demand attribute features into a demand index prediction network corresponding to each of the index types respectively, to output a plurality of the recommendation demand indexes comprises: inputting the resource demand attribute features into the baseline feature extraction layer to output baseline attribute features; inputting the resource demand attribute features into the shared feature extraction layer to output shared attribute features; fusing the baseline recommendation features and the shared recommendation features based on an attention mechanism to obtain recommendation demand fusion features corresponding to the index types; and inputting the recommendation demand fusion features into the demand index prediction layer to output recommendation demand indexes corresponding to the index types. The transaction logistics data comprises transaction item types and the number of shipping orders related to transaction items.

4. The method of claim 1, wherein, The generating a target resource according to transaction logistics data of the target object comprises: determining a target transaction item type from a plurality of the transaction item types according to the number of shipping orders corresponding to each of the transaction item types of the target object; determining first logistics service information according to the target transaction item type; and generating the target resource according to the first logistics service information. The transaction logistics data comprises shipping order area information and the number of shipping orders related to transaction items.

5. The method of claim 1, wherein, The generating a target resource according to transaction logistics data of the target object comprises: determining second logistics service information according to the number of shipping orders corresponding to the shipping order area information; and generating the target resource according to the second logistics service information. The target resource comprises a feedback information box corresponding to logistics service information, wherein the logistics service information comprises the first logistics service information or the second logistics service information.

6. The method of claim 4 or 5, wherein, The method further comprises: ​ obtaining a resource feedback request from a client corresponding to the target object; and determining feedback information according to the resource feedback request, wherein the feedback information is generated by the target object in response to an interaction operation of the feedback information box.

7. The method of claim 1, wherein, The pushing of the target resource to the target object comprises: pushing the target resource to the target object at a push time period corresponding to the target object.

8. The method of claim 7, further comprising: determining a delivery time attribute related to a transaction item of the target object according to the transaction logistics data; and determining the push time period corresponding to the target object according to the delivery time attribute. The recommendation demand indicator comprises at least one of:

9. The method of any one of claims 1 to 8, wherein, a click rate indicator and a conversion rate indicator.

10. A resource pushing apparatus, comprising: a recommendation demand evaluation module configured to evaluate a recommendation demand of a target object according to a plurality of resource demand attribute data related to the target object, and obtain a recommendation demand indicator of the target object, wherein the resource demand attribute data comprises transaction logistics data; a target object determination module configured to determine the target object from a plurality of target objects according to the recommendation demand indicator; a target resource generation module configured to generate a target resource according to transaction logistics data of the target object; and a target resource pushing module configured to push the target resource to the target object.

11. An electronic device, comprising: one or more processors; a memory configured to store 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 of any one of claims 1 to 9.

12. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement the method of any one of claims 1 to 9.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1 to 9. ​ ​

Images