Information push method, device, medium and electronic device

Abstract

The present invention provides an information push method, including: obtaining the attributes of a first-category object and the attributes of a second-category object, the second-category object is used to replace the first-category object; determining a candidate object set from the second-category object according to the attributes of the first-category object and the attributes of the second-category object; calculating the data of each candidate object in the candidate object set; determining the candidate object used to replace the first-category object according to the data of each candidate object, and then pushing the candidate object used to replace the first-category object to the user, so that the accuracy of recommending goods can be improved and the influence caused by the subjective decision of business personnel and suppliers can be effectively reduced. The present invention also provides an information push device, a medium and an electronic device.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an information pushing method, device, medium and electronic device. Background Art

[0002] With the rapid development of the Internet, users can purchase goods offline or online. At present, online platforms or offline retail companies often meet the diverse needs of consumers through a variety of products, but this often results in some products not being replenished in time. In this case, when certain products are out of stock, they need to be replaced with similar products to meet customer needs. The product replacement method in related technologies is generally based on personal experience and judgment, looking for similar products based on some attributes of the replaced products, and then determining the order quantity of the replacement products based on the sales of the replaced products.

[0003] However, when the inventor was implementing the inventive concept of the present invention, the inventor discovered the following technical problems in the related art: in the related art, the entire process of determining product replacement relies on the personal experience and judgment of business personnel, which is subjective and lacks scalability. At the same time, the product positioning and sales suggestions given by the supplier may contain subjective factors. The product replacement selection, sales forecast and ordering plan made based on this may have the risk of unsalable or out-of-stock during procurement, affecting customer experience.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide an information push method, device, medium and electronic device, which can at least improve the accuracy of recommending products to a certain extent and effectively reduce the impact of subjective decisions of business personnel and suppliers.

[0006] Other features and advantages of the present invention will become apparent from the following detailed description, or may be learned in part by practice of the present invention.

[0007] According to a first aspect of an embodiment of the present invention, there is provided an information push method, comprising: acquiring attributes of a first category of objects and attributes of a second category of objects, the second category of objects being used to replace the first category of objects; determining a set of candidate objects from the second category of objects according to the attributes of the first category of objects and the attributes of the second category of objects; calculating data of each candidate object in the set of candidate objects; determining a candidate object for replacing the first category of objects according to the data of each candidate object; and pushing the candidate object for replacing the first category of objects.

[0008] In some embodiments of the present invention, determining a set of candidate objects from the second category of objects based on the attributes of the first category of objects and the attributes of the second category of objects includes: calculating the similarity between the attributes of the first category of objects and the attributes of the second category of objects; and determining the set of candidate objects from the second category of objects based on the similarity.

[0009] In some embodiments of the present invention, the method further includes: obtaining historical data of the first category of objects; removing abnormal values ​​in the historical data and obtaining normal data in the historical data; and establishing a preset model based on the normal data in the historical data.

[0010] In some embodiments of the present invention, calculating the data of each candidate object in the candidate object set includes: generating a feature vector of each candidate object based on the object data of the category to which the first category of objects belongs and the attributes of each candidate object; and determining the data of each candidate object according to the feature vector of each candidate object.

[0011] In some embodiments of the present invention, determining the data of each candidate object according to the feature vector of each candidate object includes: processing the feature vector of each candidate object by the gradient boosting regression tree algorithm in the preset model to obtain the data of each candidate object.

[0012] In some embodiments of the present invention, determining the candidate object for replacing the first category of objects according to the data of each candidate object includes: sorting the data of each candidate object; and determining the candidate object for replacing the first category of objects according to the sorting result.

[0013] In some embodiments of the present invention, the attributes of the first category of objects include any one or more of the following: continuity attributes of the first category of objects, discrete attributes of the first category of objects, and text information attributes of the first category of objects; the attributes of the second category of objects include any one or more of the following: continuity attributes of the second category of objects, discrete attributes of the second category of objects, and text information attributes of the second category of objects.

[0014] According to a second aspect of an embodiment of the present invention, there is provided an information recommendation device, comprising: a first acquisition module, configured to acquire attributes of a first category of objects and attributes of a second category of objects, wherein the second category of objects is used to replace the first category of objects; a first determination module, configured to determine a set of candidate objects from the second category of objects according to the attributes of the first category of objects and the attributes of the second category of objects; a first calculation module, configured to calculate data of each candidate object in the set of candidate objects; a second determination module, configured to determine a candidate object for replacing the first category of objects according to the data of each candidate object; and a push module, configured to push the candidate object for replacing the first category of objects.

[0015] In some embodiments of the present invention, the above-mentioned first determination module includes: a second calculation module, used to calculate the similarity between the attributes of the first category of objects and the attributes of the second category of objects; a submodule of the first determination module, used to determine the candidate object set from the second category of objects based on the similarity.

[0016] In some embodiments of the present invention, the device also includes: a second acquisition module, used to acquire historical data of the first category of objects; a removal module, used to remove abnormal values ​​in the historical data and acquire normal data in the historical data; and an establishment module, used to establish the preset model based on the normal data in the historical data.

[0017] In some embodiments of the present invention, the above-mentioned first calculation module includes: a generation module, which generates a feature vector of each candidate object based on the object data of the category to which the first category of objects belongs and the attributes of each candidate object; and a third determination module, which is used to determine the data of each candidate object according to the feature vector of each candidate object.

[0018] In some embodiments of the present invention, the third determination module is configured to: process the feature vector of each candidate object by using the gradient boosting regression tree algorithm in the preset model to obtain the data of each candidate object.

[0019] In some embodiments of the present invention, the second determination module includes: a sorting module for sorting the data of each candidate object; and a submodule of the second determination module for determining the candidate object for replacing the first category of objects according to the sorting result.

[0020] In some embodiments of the present invention, the attributes of the first category of objects include any one or more of the following: continuity attributes of the first category of objects, discrete attributes of the first category of objects, and text information attributes of the first category of objects; the attributes of the second category of objects include any one or more of the following: continuity attributes of the second category of objects, discrete attributes of the second category of objects, and text information attributes of the second category of objects.

[0021] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the information push method as described in the first aspect of the above embodiment.

[0022] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the information push method as described in the first aspect of the above embodiment is implemented.

[0023] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0024] In the technical solutions provided in some embodiments of the present invention, attributes of a first category of objects and attributes of a second category of objects are obtained, and the second category of objects are used to replace the first category of objects. A set of candidate objects is determined from the second category of objects based on the attributes of the first category of objects and the attributes of the second category of objects. Then, data of each candidate object in the candidate object set is calculated, and a candidate object for replacing the first category of objects is determined based on the data of each candidate object. The candidate object for replacing the first category of objects is pushed to the user. In this way, the accuracy of recommending products can be improved, and the impact of subjective decisions of business personnel and suppliers can be effectively reduced.

[0025] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0027] Figure 1 A schematic diagram showing an exemplary system architecture to which the information push method or information push device according to an embodiment of the present invention can be applied;

[0028] Figure 2 A flowchart of an information push method according to an embodiment of the present invention is schematically shown;

[0029] Figure 3 A flowchart of an information push method according to another embodiment of the present invention is schematically shown;

[0030] Figure 4 A flowchart of an information push method according to another embodiment of the present invention is schematically shown;

[0031] Figure 5 A flowchart of an information push method according to another embodiment of the present invention is schematically shown;

[0032] Figure 6 A flowchart of an information push method according to another embodiment of the present invention is schematically shown;

[0033] Figure 7A block diagram schematically shows an information push device according to an embodiment of the present invention;

[0034] Figure 8 A block diagram schematically shows an information push device according to another embodiment of the present invention;

[0035] Fig. 9 A block diagram schematically shows an information push device according to another embodiment of the present invention;

[0036] Fig.10 A block diagram schematically shows an information push device according to another embodiment of the present invention;

[0037] Fig.11 A block diagram schematically shows an information push device according to another embodiment of the present invention;

[0038] Fig.12 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0039] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present invention will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0040] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, those skilled in the art will appreciate that the technical solution of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present invention.

[0041] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0042] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0043] Figure 1 A schematic diagram showing an exemplary system architecture to which the information push method or information push device according to an embodiment of the present invention can be applied.

[0044] like Figure 1 As shown, the system architecture 100 may include one or more of 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.

[0045] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. According to the implementation requirements, there may be any number of terminal devices, networks and servers. For example, the server 105 may be a server cluster composed of multiple servers.

[0046] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, portable computers, desktop computers, etc.

[0047] The server 105 may be a server that provides various services. For example, when a user uploads the attributes of a first-category object and a second-category object to the server 105 using the terminal device 103 (or the terminal device 101 or 102), the server 105 may determine a candidate object set from the second-category object based on the attributes of the first-category object and the attributes of the second-category object, calculate the data of each candidate object in the candidate object set, determine a candidate object for replacing the first-category object based on the data of each candidate object, and push the candidate object for replacing the first-category object to the user, thereby improving the accuracy of recommending products and effectively reducing the impact of subjective decisions of business personnel and suppliers.

[0048] In some embodiments, the information push method provided in the embodiments of the present invention is generally executed by the server 105, and accordingly, the information push device is generally arranged in the server 105. In other embodiments, some terminals may have functions similar to those of the server to execute the method. Therefore, the information push method provided in the embodiments of the present invention is not limited to being executed on the server side.

[0049] Figure 2 The flowchart of the information push method according to an embodiment of the present invention is schematically shown.

[0050] like Figure 2 As shown, the information push method may include steps S210 to S250.

[0051] In step S210, attributes of a first type of object and attributes of a second type of object are obtained, and the second type of object is used to replace the first type of object.

[0052] In step S220, a set of candidate objects is determined from the second category of objects according to the attributes of the first category of objects and the attributes of the second category of objects.

[0053] In step S230 , data of each candidate object in the candidate object set is calculated.

[0054] In step S240, a candidate object for replacing the first category of objects is determined according to the data of each candidate object.

[0055] In step S250, candidate objects for replacing the first category of objects are pushed.

[0056] The method can obtain attributes of a first category of objects and attributes of a second category of objects, wherein the second category of objects are used to replace the first category of objects, determine a set of candidate objects from the second category of objects based on the attributes of the first category of objects and the attributes of the second category of objects, calculate data for each candidate object in the candidate object set, determine a candidate object for replacing the first category of objects based on the data of each candidate object, and push the candidate object for replacing the first category of objects to the user, thereby improving the accuracy of recommending products and effectively reducing the impact of subjective decisions of business personnel and suppliers.

[0057] In one embodiment of the present invention, the first category object may be a first category commodity, such as a replaced commodity. The second category object may be a second category commodity, a commodity used to replace the first category commodity, such as a replacement. In this embodiment, the replaced commodity may be a commodity that is out of stock online or offline. The commodity used to replace the first category commodity may be a commodity similar to the first category commodity.

[0058] In one embodiment of the present invention, the attributes of the first category objects include any one or more of the following: continuity attributes of the first category objects, discrete attributes of the first category objects, and text information attributes of the first category objects. Based on the above embodiments, the continuity attributes of the first category goods may include but are not limited to the selling price of the first category goods and the sales volume of the first category goods over a period of time. The discrete attributes of the first category goods may include but are not limited to the commodity type of the first category goods and the origin of the first category goods. The text information attributes of the first category goods may include but are not limited to the flavor of the first category goods and the commodity characteristics of the first category goods.

[0059] In one embodiment of the present invention, the attributes of the second category objects include any one or more of the following: continuity attributes of the second category objects, discrete attributes of the second category objects, and text information attributes of the second category objects. Based on the above embodiments, the continuity attributes of the second category goods may include but are not limited to the selling price of the second category goods and the sales volume of the second category goods over a period of time. The discrete attributes of the second category goods may include but are not limited to the commodity type of the second category goods and the origin of the second category goods. The text information attributes of the second category goods may include but are not limited to the flavor of the second category goods and the commodity characteristics of the second category goods.

[0060] In one embodiment of the present invention, a candidate object set can be determined from the second category objects according to the attributes of the first category objects and the attributes of the second category objects. For example, which second category commodities can be classified into the candidate commodity set can be determined according to the similarity between the continuity attribute of the first category commodities and the continuity attribute of the second category commodities, the similarity between the discrete attribute of the first category commodities and the discrete attribute of the second category commodities, and the similarity between the text information attribute of the first category commodities and the text information attribute of the second category commodities. In this embodiment, commodities in the candidate commodity set can be commodities with a high similarity to the first category commodities.

[0061] In one embodiment of the present invention, the data of each candidate object in the candidate object set is calculated. In this embodiment, the data of each candidate object can be obtained by the algorithm in the preset model. Among them, the data of each candidate object can be the sales data of each candidate commodity. The preset model can be obtained by training the historical sales data of the first category of commodities. For example, the attributes of each candidate commodity in the candidate commodity set are input into the preset model, and the sales data of each candidate commodity can be calculated by the algorithm of the preset model. According to the sales data of each candidate commodity, the candidate commodity for replacing the first category of commodities can be determined. Determining the commodity to replace the first category of commodities in this way can improve the accuracy of recommending commodities and effectively reduce the impact caused by the subjective decisions of business personnel and suppliers.

[0062] Figure 3The following schematically shows a flow chart of an information push method according to another embodiment of the present invention.

[0063] like Figure 3 As shown, the above step S220 may specifically include steps S221 and S222.

[0064] In step S221, the similarity between the attributes of the first category of objects and the attributes of the second category of objects is calculated.

[0065] In step S222, the candidate object set is determined from the second category of objects according to the similarity.

[0066] This method can calculate the similarity between the attributes of the first category of objects and the attributes of the second category of objects, and then determine a set of candidate objects from the second category of objects based on the similarity. In this way, candidate products that replace the first category of products can be preliminarily determined from the second category of products, thereby reducing the amount of calculation required to obtain sales data for candidate products through the preset model, thereby improving the calculation speed of the preset model.

[0067] In one embodiment of the present invention, calculating the similarity between the attributes of the first category of objects and the attributes of the second category of objects may specifically include calculating the similarity between the continuous attributes of the first category of goods and the continuous attributes of the second category of goods, calculating the similarity between the discrete attributes of the first category of goods and the discrete attributes of the second category of goods, and calculating the similarity between the text information attributes of the first category of goods and the text information attributes of the second category of goods, and then determining the similarity between the first category of goods and the second category of goods based on the similarities of the three.

[0068] Based on the above embodiment, the similarity between the continuity attribute of the first category of goods and the continuity attribute of the second category of goods is calculated. For example, the continuity attribute of the first category of goods and the continuity attribute of the second category of goods are respectively represented by vectors, and then the similarity sim is calculated by the cosine formula. 连续。 The cosine formula (1) is as follows:

[0069]

[0070] Among them, the continuity attribute of the first category of goods is A, the continuity attribute of the second category of goods is B, and the similarity is sim 连续。

[0071] Based on the above embodiment, the similarity between the discrete attributes of the first category of goods and the discrete attributes of the second category of goods is calculated. For example, specifically, let the discrete attribute of the first category of goods be S1, and the discrete attribute of the second category of goods be S2, and the similarity is calculated by the following formula: 离散 The similarity formula (2) is as follows:

[0072]

[0073] The attribute set with the same attribute values ​​of S1 and S2 can be a combination of discrete attributes with the same attribute values ​​of S1 and S2. i can be a discrete attribute of the set. j can be the sum of the number of attributes of S1 and S2. Sim(S1, S2) is sim 离散 .

[0074] Based on the above embodiment, the similarity between the text information attribute of the first category of goods and the text information attribute of the second category of goods is calculated. For example, the text information attribute of the first category of goods and the text information attribute of the second category of goods are processed by TF-IDF respectively to obtain the corresponding vectors. Then the similarity between the vectors is calculated by the above cosine formula (1): 文本 .

[0075] TF-IDF (term frequency–inverse document frequency) is a commonly used weighted technique for information retrieval and data mining. A dictionary is constructed by counting keywords, and then the term frequency (TF) and inverse document frequency (IDF) are calculated. Then the product of TF and IDF, i.e. the value of TF-IDF, is calculated to find the keywords of each product and finally construct a vector.

[0076] In one embodiment of the present invention, the sim can be calculated by the above formula: 连续 ,sim 离散 ,sim 文本 Then the final similarity is calculated by formula (3), which is as follows:

[0077] Sim=a*sim 连续 +b*sim 离散 +c*sim 文本 (3)

[0078] Among them, a+b+c=1, and the values ​​of a, b, and c can be configured by business personnel according to specific scenarios. For example, when business personnel believe that the description of the second category of goods should be as consistent as possible with the first category of goods, the values ​​of a, b, and c can be 0.15, 0.15, and 0.7 respectively to achieve this.

[0079] The above formula can be used to calculate the similarity sim between the attributes of the first category of goods and the attributes of the second category of goods. In this case, according to a certain threshold threshold, the goods with sim>threshold are selected as candidate goods. The value range of Threshold can be 0 to 1, and business personnel can adjust the value according to their own needs.

[0080] Figure 4 The following schematically shows a flow chart of an information push method according to another embodiment of the present invention.

[0081] Before step S230, the above method may further include steps S310 to S330. Figure 4 shown.

[0082] In step S310, historical data of the first category of objects is obtained.

[0083] In step S320, outliers in the historical data are removed to obtain normal data in the historical data.

[0084] In step S330, the preset model is established based on the normal data in the historical data.

[0085] This method can obtain historical data of the first category of objects, remove outliers in the historical data, obtain normal data in the historical data, and then establish the preset model based on the normal data in the historical data. The preset model established in this way is more accurate in calculating the sales data of candidate products.

[0086] In one embodiment of the present invention, the historical data of the first category of objects may be historical sales data of the first category of commodities.

[0087] Based on the above embodiment, the historical sales data of the first category of goods may be the sales of the first category of goods in the past period of time, for example, the historical sales of the first category of goods in the past period of time is 5000. In this embodiment, the historical sales data of the first category of goods may belong to the continuity attribute of the first category of goods.

[0088] Based on the above-mentioned embodiment, outliers in the historical sales data are removed, which can improve the credibility of the results learned by the model, thereby avoiding affecting the accuracy of the sales data of the candidate products obtained through the preset model.

[0089] Based on the above embodiments, combined with business logic, a label database is established for whether the historical sales data is abnormal. The implementation of this step will use rough grouping of multiple factors + density detection of sales distribution within the group as the initial value, and combine business judgment to perform multiple iterations to obtain a relatively accurate outlier training database. The detected outliers are removed from the historical sales and replaced with, for example, the sample mean of the leaf node at the end of the tree. Then, feature engineering is performed based on the historical sales data (i.e., normal data) after removing the outliers, and finally the above-mentioned preset model is established based on the historical sales data of feature engineering. For example, the model algorithm uses GBM (gradient boosting regression tree). The input training data (xold, yold), xold is the vector obtained by feature engineering of the attributes of the first category of goods, and yold is the historical sales data after removing outliers. The model is trained so that F = (xold) is approximately equal to yell.

[0090] Figure 5 The following schematically shows a flow chart of an information push method according to another embodiment of the present invention.

[0091] like Figure 5 As shown, the above step S230 may specifically include step S231 and step S232.

[0092] In step S231, a feature vector of each candidate object is generated based on the object data of the category to which the first category of objects belongs and the attributes of each candidate object.

[0093] In step S232, the sales data of each candidate object is determined according to the feature vector of each candidate object.

[0094] The method can generate a feature vector for each candidate object based on the object data of the category to which the first category of objects belongs and the attributes of each candidate object, and determine the data of each candidate object according to the feature vector of each candidate object. The data of each candidate object obtained in this way is more accurate.

[0095] In one embodiment of the present invention, the object data of the category to which the first category of objects belongs may be the sales data of commodities of the category to which the first category of commodities belongs.

[0096] Based on the above embodiments, the sales data of the products in the category of the first category of products and the attributes of each candidate product can be processed in the following ways to obtain the feature vector of each candidate product. For example, the above methods can be: (1) basic transformation of a single variable, such as squaring, root taking, log transformation, etc. of a single variable. (2) Variables are derived by adding a time dimension, such as 3 months of transaction data, 6 months of transaction data, etc. (3) Multi-variable operations, such as adding or multiplying two variables or calculating a ratio between variables to obtain a new variable. (4) Introducing exogenous variables such as historical and future weather, holiday effects, promotions and other factors.

[0097] Based on the above embodiment, determining the data of each candidate object according to the feature vector of each candidate object includes: processing the feature vector of each candidate commodity by the gradient boosting regression tree algorithm in the above preset model to obtain the sales data of each candidate commodity. For example, the feature vector xnew of each candidate commodity is input into the above preset model, and then the sales data ynew of each candidate commodity can be obtained by the gradient boosting regression tree algorithm F(x) in the preset model.

[0098] Figure 6 The following schematically shows a flow chart of an information push method according to another embodiment of the present invention.

[0099] like Figure 6 As shown, the above step 240 may include step S241 and step S242.

[0100] In step S241 , the data of each candidate object is sorted.

[0101] In step S242, candidate objects for replacing the first category of objects are determined according to the sorting result.

[0102] The method can sort the data of each candidate object and determine the candidate commodity for replacing the first category of objects according to the sorting result. In this way, the candidate commodity for replacing the first category of commodities can be quickly and accurately determined from the candidate commodity set.

[0103] In one embodiment of the present invention, the data of each candidate object may be the sales data of each candidate commodity.

[0104] Based on the above embodiments, the above method can assist business personnel in benchmarking similar products when determining candidate products for replacing the first category of products, providing a scientific basis for selecting replacement products. The objective prediction of the sales status of the replacement products provides a basis for business personnel to negotiate with suppliers on purchase prices and other resource support, and can also serve as an auxiliary support for the first order quantity, reducing the risk of over-ordering or under-ordering of products due to information asymmetry, and effectively reducing the risk of unsalable or out-of-stock products.

[0105] Figure 7 The block diagram of the information pushing device according to the embodiment of the present invention is schematically shown.

[0106] like Figure 7 As shown, the information pushing device 300 includes a first acquisition module 310 , a first determination module 320 , a first calculation module 330 , a second determination module 340 and a pushing module 350 .

[0107] Specifically, the first acquisition module 310 is used to acquire properties of a first type of object and properties of a second type of object, where the second type of object is used to replace the first type of object.

[0108] The first determining module 320 is configured to determine a set of candidate objects from the second category of objects according to attributes of the first category of objects and attributes of the second category of objects.

[0109] The first calculation module 330 is used to calculate the data of each candidate object in the candidate object set.

[0110] The second determination module 340 is configured to determine a candidate object for replacing the first category of objects according to the data of each candidate object.

[0111] The pushing module 350 is configured to push candidate objects for replacing the first category of objects.

[0112] The information push device 300 can obtain the attributes of the first category of objects and the attributes of the second category of objects, the second category of objects are used to replace the first category of objects, determine a set of candidate objects from the second category of objects according to the attributes of the first category of objects and the attributes of the second category of objects, calculate the data of each candidate object in the candidate object set, determine the candidate object for replacing the first category of objects according to the data of each candidate object, and push the candidate object for replacing the first category of objects to the user, so that the accuracy of recommending goods can be improved and the impact of subjective decisions of business personnel and suppliers can be effectively reduced.

[0113] According to an embodiment of the present invention, the information push device 300 can be used to implement Figure 2 The information push method described in the embodiment.

[0114] Figure 8 A block diagram of an information pushing device according to another embodiment of the present invention is schematically shown.

[0115] like Figure 8 As shown, the first determination module 320 may specifically include a second calculation module 321 and a submodule 322 of the first determination module.

[0116] Specifically, the second calculation module 321 is used to calculate the similarity between the attributes of the first category of objects and the attributes of the second category of objects.

[0117] The submodule 322 of the first determination module is configured to determine the candidate object set from the second category of objects according to the similarity.

[0118] The first determination module 320 can calculate the similarity between the attributes of the first category of objects and the attributes of the second category of objects, and then determine a set of candidate objects from the second category of objects based on the similarity. In this way, candidate products that replace the first category of products can be preliminarily determined from the second category of products, thereby reducing the amount of calculation required to subsequently obtain sales data for the candidate products through a preset model, thereby improving the calculation speed of the preset model.

[0119] According to an embodiment of the present invention, the first determination module 320 can be used to implement Figure 3 The information push method described in the embodiment.

[0120] Fig. 9 A block diagram of an information pushing device according to another embodiment of the present invention is schematically shown.

[0121] like Fig. 9 As shown, the information pushing device 300 includes a second acquisition module 360 ​​, a removal module 370 and a creation module 380 .

[0122] Specifically, the second acquisition module 360 ​​is used to acquire the historical data of the first category of objects.

[0123] The removal module 370 is used to remove abnormal values ​​in the historical data and obtain normal data in the historical data.

[0124] The establishment module 380 establishes the preset model based on the normal data in the historical data.

[0125] The information push device 300 can obtain historical data of the first category of objects, remove outliers in the historical data, obtain normal data in the historical data, and then establish the preset model based on the normal data in the historical data. The preset model established in this way is more accurate in calculating the sales data of candidate products.

[0126] According to an embodiment of the present invention, the information push device 300 can be used to implement Figure 4 The information push method described in the embodiment.

[0127] Fig.10 A block diagram of an information pushing device according to another embodiment of the present invention is schematically shown.

[0128] like Fig.10As shown, the first calculation module 330 may specifically include a generation module 331 and a third determination module 332 .

[0129] Specifically, the generating module 331 generates a feature vector for each candidate object based on the object data of the category to which the first category of objects belongs and the attributes of each candidate object.

[0130] The third determination module 332 is used to determine the data of each candidate object according to the feature vector of each candidate object.

[0131] The first calculation module 330 can generate a feature vector for each candidate object based on the object data of the category to which the first category of objects belongs and the attributes of each candidate object, and determine the data of each candidate object according to the feature vector of each candidate object. The data of each candidate object obtained in this way is more accurate.

[0132] According to an embodiment of the present invention, the first calculation module 330 can be used to implement Figure 5 The information push method described in the embodiment.

[0133] In some embodiments of the present invention, the third determination module 332 is configured to: process the feature vector of each candidate product by using a gradient boosting regression tree algorithm to obtain sales data of each candidate product.

[0134] Fig.11 A block diagram of an information pushing device according to another embodiment of the present invention is schematically shown.

[0135] like Fig.11 As shown, the second determination module 340 includes a sorting module 341 and a submodule 342 of the second determination module.

[0136] Specifically, the sorting module 341 is used to sort the data of each candidate object.

[0137] The submodule 342 of the second determination module is used to determine candidate objects for replacing the first category of objects according to the sorting result.

[0138] The second determination module 340 can sort the data of each candidate object and determine the candidate commodity for replacing the first category of objects according to the sorting result, so as to quickly and accurately determine the candidate commodity for replacing the first category of commodities from the candidate commodity set.

[0139] According to an embodiment of the present invention, the second determination module 340 can be used to implement Figure 6 The information push method described in the embodiment.

[0140] Since each module of the information push device 300 of the exemplary embodiment of the present invention can be used to implement the above 2~ Figure 6 The steps of the exemplary embodiment of the information push method are described, so for details not disclosed in the embodiment of the device of the present invention, please refer to the above-mentioned embodiment of the information push method of the present invention.

[0141] It is understandable that the first acquisition module 310, the first determination module 320, the second calculation module 321, the submodule 322 of the first determination module, the first calculation module 330, the generation module 331, the third determination module 332, the second determination module 340, the sorting module 341, the submodule 342 of the second determination module, the push module 350, the third acquisition module 360, the removal module 370, and the establishment module 380 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present invention, at least one of the first acquisition module 310, the first determination module 320, the second calculation module 321, the sub-module 322 of the first determination module, the first calculation module 330, the generation module 331, the third determination module 332, the second determination module 340, the sorting module 341, the sub-module 342 of the second determination module, the push module 350, the third acquisition module 360, the removal module 370, and the establishment module 380 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 in hardware or firmware such as any other reasonable way of integrating or packaging circuits, or in an appropriate combination of software, hardware and firmware. Alternatively, at least one of the first acquisition module 310, the first determination module 320, the second calculation module 321, the sub-module 322 of the first determination module, the first calculation module 330, the generation module 331, the third determination module 332, the second determination module 340, the sorting module 341, the sub-module 342 of the second determination module, the push module 350, the third acquisition module 360, the removal module 370, and the establishment module 380 can be at least partially implemented as a computer program module, and when the program is run by a computer, the functions of the corresponding module can be executed.

[0142] Reference below Fig.12 , which shows a schematic diagram of the structure of a computer system 400 of an electronic device suitable for implementing an embodiment of the present invention. Fig.12 The computer system 400 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0143] like Fig.12 As shown, computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage part 408 into a random access memory (RAM) 403. Various programs and data required for system operation are also stored in RAM 403. CPU 401, ROM 402 and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to bus 404.

[0144] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

[0145] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention 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 a network through a communication section 409, and / or installed from a removable medium 411. When the computer program is executed by a central processing unit (CPU) 401, the above-mentioned functions defined in the system of the present application are executed.

[0146] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may 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 storage media may include, but are not limited to: an electrical connection with one or more wires, 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 invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, 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. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or 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.

[0147] 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 invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a 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 box can also occur in a different order from the order marked in the accompanying drawings. For example, two 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 box in the block diagram or flow chart, and the combination of the boxes in the block diagram 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.

[0148] The units involved in the embodiments of the present invention may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, limit the units themselves.

[0149] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the information push method described in the above embodiment.

[0150] For example, the electronic device can implement Figure 2 As shown in: In step S210, the attributes of the first category object and the attributes of the second category object are obtained, and the second category object is used to replace the first category object. In step S220, a candidate object set is determined from the second category object according to the attributes of the first category object and the attributes of the second category object. In step S230, the data of each candidate object in the candidate object set is calculated. In step S240, the candidate object for replacing the first category object is determined according to the data of each candidate object. In step S250, the candidate object for replacing the first category object is pushed.

[0151] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0152] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present invention.

[0153] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0154] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. An information push method, characterized in that: include: Obtaining properties of a first type of object and properties of a second type of object, where the second type of object is used to replace the first type of object; Determine a set of candidate objects from the second category of objects according to the attributes of the first category of objects and the attributes of the second category of objects; Calculating data of each candidate object in the candidate object set, wherein the data of the candidate object includes sales data of the candidate object; Determine a candidate object for replacing the first category of objects according to the data of each candidate object; Pushing the candidate object for replacing the first category of objects; The step of calculating the data of each candidate object in the candidate object set includes: generating a feature vector of each candidate object based on the object data of the category to which the first category of objects belongs and the attributes of each candidate object; processing the feature vector of each candidate object through a preset model to obtain sales data of each candidate object; Determining the candidate object for replacing the first category of objects according to the data of each candidate object includes: sorting the sales data of each candidate object; and determining the candidate object for replacing the first category of objects according to the sorting result.

2. The method according to claim 1, characterized in that Determining a set of candidate objects from the second category of objects according to the attributes of the first category of objects and the attributes of the second category of objects includes: Calculating the similarity between the attributes of the first category of objects and the attributes of the second category of objects; The candidate object set is determined from the second category of objects according to the similarity.

3. The method according to claim 1, characterized in that: The method further includes: Obtaining historical data of the first category of objects; Removing abnormal values ​​from the historical data to obtain normal data from the historical data; The preset model is established based on normal data in the historical data.

4. The method according to any one of claims 1 to 3, characterized in that: The attributes of the first category of objects include any one or more of the following: continuity attributes of the first category of objects, discrete attributes of the first category of objects, and text information attributes of the first category of objects; The attributes of the second category objects include any one or more of the following: a continuity attribute of the second category objects, a discrete attribute of the second category objects, and a text information attribute of the second category objects.

5. An information push device, characterized in that: include: A first acquisition module, used to acquire properties of a first type of object and properties of a second type of object, wherein the second type of object is used to replace the first type of object; A first determining module, configured to determine a set of candidate objects from the second category of objects according to attributes of the first category of objects and attributes of the second category of objects; A second acquisition module is used to calculate the data of each candidate object in the candidate object set, wherein the data of the candidate object includes the sales data of the candidate object; A second determination module, configured to determine a candidate object for replacing the first category of objects according to the data of each candidate object; A pushing module, used for pushing the candidate objects for replacing the first category of objects; The second acquisition module is configured to generate a feature vector of each candidate object based on the object data of the category to which the first category of objects belongs and the attributes of each candidate object; the feature vector of each candidate object is processed by a preset model to obtain sales data of each candidate object; The second determination module is configured to sort the sales data of each candidate object; and determine the candidate object for replacing the first category of objects according to the sorting result.

6. An electronic device comprising: one or more processors; as well as A storage device, used for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the method according to any one of claims 1 to 3.

7. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images