Promotion product display method and device and electronic equipment

Abstract

The invention discloses a promotion product display method and device and electronic equipment. The method relates to the field of big data, and comprises the following steps: acquiring initial product information of a to-be-popularized product, and preprocessing the initial product information to obtain target product information; inputting the target product information into a first value prediction model to obtain first value data of the to-be-popularized product; determining a value interval to which the first value data belongs, and obtaining M initial promotion positions corresponding to the value interval; obtaining attribute information of the initial promotion position, and calculating M pieces of second value data of the initial promotion position according to the attribute information; and selecting a target promotion position from the M initial promotion positions according to the first value data and the M second value data, and displaying promotion information of the to-be-promoted product at the target promotion position. Through the method and the device, the problem of relatively low accuracy of manually determining the product promotion position in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of big data, and more specifically, to a method, device and electronic device for displaying promotional products. Background Art

[0002] With the continuous development of the Internet and big data, banks and other financial institutions have opened online business channels, such as mobile banking. Banks promote their products or services by placing advertisements in the promotional positions of online channels to attract customers to complete transactions and realize the value of their products.

[0003] The existing product promotion methods and promotion location selection are determined manually, but the promotion locations provided by online channels are limited. In addition, as the price and cost of promotion locations increase, the accuracy, efficiency and economic benefits of manually determining product promotion locations are relatively low.

[0004] With regard to the problem of low accuracy in manually determining product promotion locations in related technologies, no effective solution has been proposed so far. Summary of the invention

[0005] The main purpose of the present application is to provide a method, device and electronic device for displaying promotional products to solve the problem of low accuracy in manually determining the product promotion location in the related art.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for displaying promotional products is provided. The method includes: obtaining initial product information of the product to be promoted, and preprocessing the initial product information to obtain target product information; inputting the target product information into a first value prediction model to obtain first value data of the product to be promoted; determining the value interval to which the first value data belongs, and obtaining the promotion position corresponding to the value interval to obtain M initial promotion positions, where M is a positive integer; obtaining attribute information of each initial promotion position, and calculating the value data of each initial promotion position according to the attribute information to obtain M second value data; selecting a target promotion position from the M initial promotion positions according to the first value data and the M second value data, and displaying the promotion information of the product to be promoted at the target promotion position.

[0007] Optionally, preprocessing the initial product information to obtain target product information includes: obtaining data characteristic values ​​in the initial product information, and normalizing the data characteristic values ​​to obtain multiple first characteristic values; obtaining non-data characteristic values ​​in the initial product information, and converting each non-data characteristic value into a numerical value according to a preset corresponding relationship, and normalizing the numerical value to obtain multiple second characteristic values, wherein the preset corresponding relationship is used to characterize the correspondence between the non-data characteristic value and the numerical value; and determining the multiple first characteristic values ​​and the multiple second characteristic values ​​as the target product information.

[0008] Optionally, the first value prediction model is trained in the following manner: obtaining multiple historical promotion products, and obtaining historical product information and historical value information of each historical promotion product in turn; determining the historical product information and historical value information of each historical promotion product as a set of sample data, to obtain multiple sets of first sample data; training the initial prediction model with the multiple sets of first sample data, to obtain the first value prediction model.

[0009] Optionally, obtaining the historical value information of each historical promotion product includes: for each historical promotion product, obtaining the promotion effect information obtained after the promotion operation of the historical promotion product, wherein the promotion effect information includes multiple promotion effect data; obtaining the weight of each promotion effect data in the promotion effect information to obtain multiple first weights, and normalizing each promotion effect data to obtain multiple processed promotion effect data; performing a weighted sum operation on the multiple processed promotion effect data and the multiple first weights to obtain the historical value information of the historical promotion product.

[0010] Optionally, the value data of each initial promotion position is calculated according to the attribute information to obtain M second value data, including: for any initial promotion position, obtaining the attribute information of the initial promotion position, wherein the attribute information includes multiple third eigenvalues; obtaining the weight of each third eigenvalue to obtain multiple second weights, and performing weighted sum calculation on each third eigenvalue according to the multiple second weights to obtain the second value data of the initial promotion position.

[0011] Optionally, selecting a target promotion position from M initial promotion positions based on the first value data and M second value data includes: calculating the difference between each second value data and the first value data in turn to obtain M initial differences; obtaining the difference with the smallest value from the M initial differences to obtain multiple target differences; when the number of target differences is 1, determining the initial promotion position corresponding to the second value data to which the target difference belongs as the target promotion position; when the number of target differences is greater than 1, obtaining an evaluation value of the product to be promoted; when the evaluation value is greater than a preset value, obtaining multiple second value data corresponding to the target difference, and determining the initial promotion position corresponding to the second value data greater than the first value data as the target promotion position; when the evaluation value is less than or equal to the preset value, obtaining multiple second value data corresponding to the target difference, and determining the initial promotion position corresponding to the second value data less than the first value data as the target promotion position.

[0012] Optionally, selecting a target promotion position from M initial promotion positions based on the first value data and M second value data includes: obtaining a target product type of the product to be promoted; obtaining the number of historical products of the target product type promoted at each initial promotion position, respectively, to obtain M promotion times; updating the M second value data according to the M promotion times, to obtain M updated second value data; and determining the initial promotion position corresponding to the updated second value data having the smallest difference with the first value data among the M updated second value data as the target promotion position.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a display device for promoting products is provided. The device includes: a first acquisition unit, used to acquire the initial product information of the product to be promoted, and pre-process the initial product information to obtain the target product information; an input unit, used to input the target product information into the first value prediction model to obtain the first value data of the product to be promoted; a first determination unit, used to determine the value interval to which the first value data belongs, and acquire the promotion position corresponding to the value interval to obtain M initial promotion positions, where M is a positive integer; a second acquisition unit, used to acquire the attribute information of each initial promotion position, and calculate the value data of each initial promotion position according to the attribute information to obtain M second value data; a selection unit, used to select the target promotion position from the M initial promotion positions according to the first value data and the M second value data, and display the promotion information of the product to be promoted at the target promotion position.

[0014] In an embodiment of the present application, the initial product information of the product to be promoted is obtained, and the initial product information is preprocessed to obtain the target product information; the target product information is input into the first value prediction model to obtain the first value data of the product to be promoted; the value interval to which the first value data belongs is determined, and the promotion position corresponding to the value interval is obtained to obtain M initial promotion positions, where M is a positive integer; the attribute information of each initial promotion position is obtained, and the value data of each initial promotion position is calculated according to the attribute information to obtain M second value data; the target promotion position is selected from the M initial promotion positions according to the first value data and the M second value data, and the promotion information of the product to be promoted is displayed at the target promotion position. The first value data of the product to be promoted is obtained according to the target product information through the first value prediction model, and then its initial promotion position is determined. By obtaining the attribute information of the initial promotion position, the second value data of each initial promotion position is calculated, and then the target promotion position is selected according to the first value data and the second value data, and the promotion information of the product to be promoted is displayed, which solves the problem of low accuracy of manually determining the product promotion position in the related art, thereby achieving the technical effect of improving the efficiency and accuracy of determining the product promotion position. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a computer terminal for implementing a method for displaying promotional products is shown;

[0017] Figure 2 is a flow chart of a method for displaying promotional products provided in Example 1 of the present application;

[0018] Figure 3 is a schematic diagram of a display device for promoting products provided in Example 2 of the present application;

[0019] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] It should be noted that the display method, device and electronic device for promotional products determined in the present disclosure can be used in the field of big data, and can also be used in any field except the field of big data. The application field of the display method, device and electronic device for promotional products determined in the present disclosure is not limited.

[0024] It should be noted that the collected information, user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) used in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of the relevant regions, necessary confidentiality measures are taken, and public order and good customs are not violated. Corresponding operation entrances are provided for users to choose to authorize use or refuse use. If the user chooses to refuse, the expert decision-making process is entered. For example, an interface is set between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0025] The embodiments or examples of the present disclosure are not exhaustive, but are only illustrative of some embodiments or examples, and are not intended to be specific limitations on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment or example can be implemented as an independent example, and the steps can be combined arbitrarily. For example, the scheme after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be combined arbitrarily; in addition, the various embodiments or examples can be combined arbitrarily, for example, some or all steps of different embodiments or examples can be combined arbitrarily, and a certain embodiment or example can be combined arbitrarily with the optional methods or optional examples of other embodiments or examples.

[0026] Example 1

[0027] According to an embodiment of the present application, an embodiment of a method for displaying a promotional product is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a method for displaying promotional products. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0029] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the display method of the promotion product in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the display method of the promotion product mentioned above. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0033] Under the above operating environment, this application provides Figure 2 The method of displaying the promoted product shown. Figure 2 This is a flow chart of a method for displaying promotional products provided according to Example 1 of the present application.

[0034] Step S201, obtaining initial product information of a product to be promoted, and preprocessing the initial product information to obtain target product information.

[0035] Specifically, in the process of displaying promotional products, the initial product information of the products to be promoted can be obtained first, where the products to be promoted can be financial products or businesses that are promoted by banks or other financial institutions through online channels, such as loan services, points redemption activities, financial products, etc. The online channels can be mobile banking, etc. The initial product information obtained is the advertising information of the products to be promoted, which may include advertising ID, advertising type, promotion days, target customer group type, activity rewards invested, etc.

[0036] Furthermore, after collecting the initial product information of the product to be promoted, the initial product information can be pre-processed. Since the numerical range of the numerical information contained in the initial product information may vary greatly, for example, the number of promotion days in the initial product information is 30, and the activity reward invested is 100,000, the numerical information in the initial product information can be normalized first, and the numerical range of all numerical information can be unified to between 0 and 1, so as to eliminate the impact of differences in dimensions and value ranges between different types of information on data processing.

[0037] Furthermore, after the numerical information in the initial product information is normalized, since the initial product information also contains some text information, such as advertising type, customer group type, etc., which is not conducive to analysis and processing, the text information can be converted into numerical values ​​according to a preset correspondence. For example, a corresponding number can be set for each advertising type, such as setting the corresponding number for loan services to 001, the corresponding number for investment and financial management to 002, the corresponding number for points redemption to 003, etc. After the text information is converted into numerical values, it can also be normalized to unify the numerical range, and finally the pre-processed initial product information can be determined as the target product information.

[0038] Step S202: input the target product information into the first value prediction model to obtain the first value data of the product to be promoted.

[0039] Specifically, after obtaining the target product information, the target product information can be input into a pre-trained first value prediction model to predict the product value, wherein the first value prediction model can be a machine learning algorithm model such as linear regression and neural network. The first value data of the product to be promoted can be obtained through the output result of the first value prediction model, wherein the first value data is used to characterize the value of the product to be promoted, and its range can be 0-100.

[0040] It should be noted that in the process of training the first value prediction model, multiple historical promotion products can be obtained, as well as the historical product information and historical value information corresponding to each historical promotion product, and the historical product information and historical value information of each historical promotion product can be combined into a set of sample data. The sample data can be divided into training data and test data according to time. The machine learning algorithm model is trained with the training data, and the model can learn the mapping rules from product information to value information. After the training is completed, the accuracy of the model is tested with the test data. When the prediction accuracy of the model reaches the expected value, the first value prediction model can be obtained. Through the first value prediction model, the first value data of the product to be promoted can be determined according to the target product information.

[0041] Step S203, determining the value interval to which the first value data belongs, and obtaining the promotion positions corresponding to the value interval, to obtain M initial promotion positions, where M is a positive integer.

[0042] Specifically, after obtaining the first value data of the product to be promoted, we can first determine the value range to which the first value data belongs, and then determine the promotion position range that matches the product to be promoted based on the value range. A higher value range can match a more significant and important promotion position range. Finally, we can obtain all specific promotion positions within the promotion position range that matches the product to be promoted, and obtain M initial promotion positions.

[0043] For example, assuming that the range of the first value data is between 0 and 100 points, the value interval can be divided into: 80-100 points (high-value products), 50-79 points (medium-value products) and 0-49 points (low-value products). The promotion position range of high-value products can be selected in a prominent position on the homepage, the promotion position range of medium-value products can be in the middle of the special area or the classification page, etc., and the promotion position range of low-value products can be the bottom of the special area, the end of the activity page, etc. Suppose product A is to be promoted through advertising in mobile banking. The first value data of product A is 89 points, which is within the high-value product interval. Therefore, it can be determined that its promotion position range is in the top area or the popular recommendation area of ​​the mobile banking homepage. By obtaining the specific positions in these areas, multiple initial promotion positions of the product can be obtained.

[0044] Step S204, acquiring attribute information of each initial promotion position, and calculating value data of each initial promotion position according to the attribute information to obtain M second value data.

[0045] Specifically, after obtaining multiple initial promotion positions for the products to be promoted, the attribute information of each initial promotion position can be obtained. The attribute information includes multiple feature types, such as position, length, type, exposure rate, click-through rate, etc. Since the attribute information includes both numerical features and text features, the feature values ​​of the text features can be converted into numerical values ​​according to a preset corresponding relationship. For example, for the feature of promotion position type, assuming that its feature values ​​include banners, videos, pop-ups, etc., the banner can be set to 001, the video can be set to 002, the pop-up window can be set to 003, etc., and then all feature values ​​can be normalized to control the numerical range between 0-1, which is convenient for subsequent processing and calculation.

[0046] Further, the weight value of each feature type can be obtained according to a preset comparison table of feature types and weights, wherein the comparison table of feature types and weights contains all feature types in the promotion location attribute information and the weight value corresponding to each feature. The comparison table of feature types and weights can be shown in the following table:

[0047] Table 1

[0048] feature Weight Location 0.120 space 0.104 type 0.099 Exposure 0.140 Click-through rate 0.120 … …

[0049] Among them, the weight can reflect the importance of different feature types in the attribute information to the promotion location value.

[0050] Furthermore, after obtaining the weights corresponding to each feature type, the value data of each initial promotion position can be calculated using the following weighted average calculation formula:

[0051] V=f1*w1+f2*w2+…

[0052] Among them, V represents the second value data, f represents the characteristic value of the promotion position, and w represents the weight of the characteristic type corresponding to the characteristic value. Finally, the second value data of each initial promotion position can be obtained by calculating through the above formula.

[0053] Step S205: selecting a target promotion location from the M initial promotion locations according to the first value data and the M second value data, and displaying promotion information of the product to be promoted at the target promotion location.

[0054] Specifically, after obtaining the second value data of multiple initial promotion positions, the multiple second value data can be compared with the first value data of the product to be promoted obtained above, and the target promotion position can be determined from the multiple initial promotion positions. First, the first value data and the second value data can be normalized to unify the value ranges of the two value data. Then, by calculating the difference between each second value data and the first value data, the minimum difference can be determined as the target difference, and the initial promotion position corresponding to the second value data to which the target difference belongs can be determined as the target promotion position.

[0055] It should be noted that when the second value data corresponding to the target difference is not unique, the final target promotion position can be determined in combination with the evaluation value of the product to be promoted, where the evaluation value of the product is an attribute of the product itself, which can be obtained by evaluating the product before producing the product in combination with multiple factors such as product positioning, cost analysis, and profit forecast. The evaluation value can range from 0 to 100 points.

[0056] Furthermore, after obtaining the evaluation value of the product to be promoted, the evaluation value can be compared with a preset value, which can be 50 points. When the evaluation value is greater than the preset value, the initial promotion position corresponding to the second value data greater than the first value data among the multiple second value data to which the target difference belongs can be determined as the target promotion position. When the product evaluation value is less than the preset value, the initial promotion position corresponding to the second value data less than the first value data among the multiple second value data to which the target difference belongs can be determined as the target promotion position. After determining the target promotion position, the promotion information of the product to be promoted can be displayed at the target promotion position.

[0057] In an embodiment of the present application, the initial product information of the product to be promoted is obtained, and the initial product information is preprocessed to obtain the target product information; the target product information is input into the first value prediction model to obtain the first value data of the product to be promoted; the value interval to which the first value data belongs is determined, and the promotion position corresponding to the value interval is obtained to obtain M initial promotion positions, where M is a positive integer; the attribute information of each initial promotion position is obtained, and the value data of each initial promotion position is calculated according to the attribute information to obtain M second value data; the target promotion position is selected from the M initial promotion positions according to the first value data and the M second value data, and the promotion information of the product to be promoted is displayed at the target promotion position. The first value data of the product to be promoted is obtained according to the target product information through the first value prediction model, and then its initial promotion position is determined. By obtaining the attribute information of the initial promotion position, the second value data of each initial promotion position is calculated, and then the target promotion position is selected according to the first value data and the second value data, and the promotion information of the product to be promoted is displayed, which solves the problem of low accuracy of manually determining the product promotion position in the related art, thereby achieving the technical effect of improving the efficiency and accuracy of determining the product promotion position.

[0058] Optionally, in the promotional product display method provided in the embodiment of the present application, the initial product information is preprocessed to obtain the target product information, including: obtaining data feature values ​​in the initial product information, and normalizing the data feature values ​​to obtain multiple first feature values; obtaining non-data feature values ​​in the initial product information, and converting each non-data feature value into a numerical value according to a preset corresponding relationship, and normalizing the numerical value to obtain multiple second feature values, wherein the preset corresponding relationship is used to characterize the correspondence between the non-data feature value and the numerical value; and determining the multiple first feature values ​​and the multiple second feature values ​​as the target product information.

[0059] It should be noted that, in the process of displaying the promoted product, the initial product information of the product to be promoted can be obtained first, wherein the initial product information includes multiple feature types and feature values ​​corresponding to each feature type. For example, the feature types in the initial product information can be as follows:

[0060] Feature type: (advertising ID, advertising type, promotion days, target customer group type, activity rewards invested, etc.).

[0061] Corresponding characteristic values: (101, investment and financial management, 30, young customer group, 50,000, ...).

[0062] Furthermore, since the characteristic values ​​in the initial product information contain both numerical values ​​and text, the initial product information can be preprocessed. First, the data characteristic values ​​in the initial product information can be obtained, that is, (101, 30, 50000, ...) corresponding to (advertising ID, promotion days, activity rewards invested, ...) respectively, and then the data characteristic values ​​can be normalized to control the numerical range of each data characteristic value between 0-1, which is convenient for subsequent data processing and calculation. After the data characteristic values ​​are normalized, multiple first characteristic values ​​can be obtained.

[0063] Furthermore, the non-data feature values ​​in the initial product information can be obtained, that is, (investment management, youth customer group, ...) correspond to (advertising type, customer group type, ...) respectively, and then the non-data feature values ​​can be converted into numerical form according to the preset corresponding relationship, wherein the preset corresponding relationship includes a plurality of non-data feature types, and the non-data feature values ​​contained therein, and the numerical number corresponding to each non-data feature value. For example, for the customer group type feature, non-data feature values ​​such as youth customer group, young customer group, and elderly customer group can be included. The numerical number corresponding to the youth customer group can be set to 001, the numerical number corresponding to the young customer group can be set to 002, the numerical number corresponding to the elderly customer group can be set to 003, etc. After converting each non-data feature value into a numerical value, the numerical value can be normalized to obtain multiple second feature values, and finally the multiple first feature values ​​and the multiple second feature values ​​are determined as the target product information.

[0064] This embodiment obtains target product information by preprocessing initial product information, normalizing data feature values, converting non-data feature values ​​into numerical values ​​and then normalizing them, thereby predicting the value of the product to be promoted based on the target product information, thereby ensuring the accuracy of the prediction of the value of the product to be promoted.

[0065] Optionally, in the promotion product display method provided in the embodiment of the present application, the first value prediction model is trained in the following manner: obtaining multiple historical promotion products, and obtaining historical product information and historical value information of each historical promotion product in turn; determining the historical product information and historical value information of each historical promotion product as a set of sample data to obtain multiple sets of first sample data; training the initial prediction model through the multiple sets of first sample data to obtain the first value prediction model.

[0066] It should be noted that the first value prediction model is used to predict the value of the product to be promoted. It can be trained by using sample data to train machine learning algorithm models such as linear regression and neural networks. When the prediction accuracy of the model reaches the expected value, the first value prediction model can be obtained.

[0067] Specifically, in the process of training the machine learning algorithm model, historical data can be used as sample data for training. First, multiple historical promotion products can be obtained, and then the historical product information and historical value information of each historical promotion product can be obtained respectively to obtain multiple historical product information and historical value information. The historical product information and historical value information corresponding to each historical promotion product can be combined into a set of sample data, and finally multiple sets of first sample data can be obtained.

[0068] Furthermore, multiple groups of first sample data can be divided into training sample data and test sample data according to time. For example, assuming that the selected historical data time length is one year, the first sample data from January to October can be used as training sample data, and the first sample data from November and December can be used as test sample data. By using multiple groups of training sample data to train the model, the model continuously learns the mapping rules from product information to value information, and then uses the test sample data to test the prediction accuracy of the model. When the prediction accuracy of the model reaches the expected value, the model training process can be ended to obtain the first value prediction model. If the model prediction accuracy does not reach the expected value, sample data can continue to be collected to train the model until the model prediction accuracy reaches the expected value. Finally, the first value prediction model is obtained. Through the first value prediction model, the first value data of the product to be promoted can be determined according to the target product information.

[0069] This embodiment trains the model by acquiring historical product information and historical value information of historically promoted products, and finally obtains a first value prediction model, which can then predict the first value data of the product to be promoted, thereby ensuring the accuracy and efficiency of the first value data prediction.

[0070] Optionally, in the promotion product display method provided in the embodiment of the present application, obtaining the historical value information of each historical promotion product includes: for each historical promotion product, obtaining the promotion effect information obtained after the historical promotion product is promoted, wherein the promotion effect information includes multiple promotion effect data; obtaining the weight of each promotion effect data in the promotion effect information to obtain multiple first weights, and normalizing each promotion effect data to obtain multiple processed promotion effect data; performing a weighted sum operation on the multiple processed promotion effect data and the multiple first weights to obtain the historical value information of the historical promotion product.

[0071] It should be noted that in the process of obtaining the historical value information of each historical promotion product, you can first obtain the promotion effect information obtained after the historical promotion product is promoted, such as exposure rate, click volume, click rate, conversion rate, retention rate, etc., where the promotion effect information includes multiple promotion effect data. For example, after the promotion operation of product A, its promotion effect data is (50%, 2000000, 80%, 35%, 32%, ...) corresponding to (exposure rate, click volume, click rate, conversion rate, retention rate, ...) respectively.

[0072] Further, after obtaining the promotion effect information of multiple historical promotion products, the weights of each promotion effect data in the promotion effect information can be obtained according to the preset promotion effect and weight comparison table, wherein the promotion effect and weight comparison table contains different types of promotion effect information and their corresponding weight values, and the promotion effect and weight comparison table can be shown in the following Table 2:

[0073] Table 2

[0074] Promotion effect information Weight Exposure 0.120 Clicks 0.104 Click-through rate 0.099 Conversion Rate 0.140 Retention rate 0.120 … …

[0075] Furthermore, through the comparison table of promotion effect and weight, the weight of each promotion effect data of each historical promotion product can be obtained, and multiple first weights can be obtained. Then, each promotion effect data can be normalized to obtain multiple processed promotion effect data. By using the weighted average calculation formula, that is, performing a weighted sum operation on multiple processed promotion effect data and multiple first weights, the historical value information of the historical promotion product can be obtained, wherein the calculation formula of the historical value information is as follows:

[0076] V0=e1*w1+e2*w2+…

[0077] Among them, V0 represents the promotion position value, e represents the normalized promotion effect data, and w represents the first weight. Finally, through the above formula calculation, the historical value information of each historical promotion product can be obtained.

[0078] This embodiment obtains the promotion effect information and the corresponding first weight of each historical promotion product, and obtains the historical value information of the historical promotion product through weighted calculation, thereby ensuring the accuracy of the historical value information.

[0079] Optionally, in the method for displaying promotional products provided in an embodiment of the present application, the value data of each initial promotion position is calculated based on the attribute information to obtain M second value data, including: for any initial promotion position, obtaining the attribute information of the initial promotion position, wherein the attribute information includes multiple third eigenvalues; obtaining the weight of each third eigenvalue to obtain multiple second weights, and performing weighted sum calculation on each third eigenvalue according to the multiple second weights to obtain the second value data of the initial promotion position.

[0080] It should be noted that in the process of calculating the value data of each initial promotion position, it is possible to first obtain the attribute information of each initial promotion position based on the initial promotion positions obtained above, such as position, area, type, exposure rate, click-through rate, etc., wherein the attribute information includes multiple third characteristic values, that is, the characteristic value corresponding to each attribute feature. For example, the third characteristic value of the C promotion position is (top, 6, pop-up window, 30%, 22%, ...) corresponding to (position, area, type, exposure rate, click-through rate, ...) respectively.

[0081] Furthermore, since the third eigenvalue contains both numerical values ​​and text, the third eigenvalue of the text type can be converted into a numerical value according to a preset correspondence. For example, for the attribute of the promotion position type, assuming that its third eigenvalue can be a banner, video, pop-up window, etc., the preset correspondence can set the banner to 001, the video to 002, the pop-up window to 003, etc. After the third eigenvalue of the text type in the initial promotion position attribute information is converted into a numerical value, all the third eigenvalues ​​are normalized and the numerical range is controlled between 0-1 to facilitate subsequent processing and calculation.

[0082] Furthermore, after obtaining and processing the third eigenvalues ​​of each initial promotion position, the weights of each third eigenvalue can be obtained according to a preset comparison table of attribute information and weights, wherein the comparison table of attribute information and weights contains different types of attribute information, such as position, area, type, etc., and the weights corresponding to each attribute information. Through the comparison table of attribute information and weights, the weights of each third eigenvalue can be obtained to obtain multiple second weights, and then the second value data of the initial promotion position is finally obtained by performing weighted sum calculation on the multiple second weights and each third eigenvalue respectively.

[0083] This embodiment calculates the second value data of each initial promotion position according to the attribute information, so that the target promotion position of the product to be promoted can be determined according to the second value data, thereby ensuring the accuracy of the target promotion position.

[0084] Optionally, in the display method for promotional products provided in the embodiment of the present application, selecting a target promotion position from M initial promotion positions based on the first value data and M second value data includes: calculating the difference between each second value data and the first value data in turn to obtain M initial differences; obtaining the difference with the smallest value from the M initial differences to obtain multiple target differences; when the number of target differences is 1, determining the initial promotion position corresponding to the second value data to which the target difference belongs as the target promotion position; when the number of target differences is greater than 1, obtaining an evaluation value of the product to be promoted; when the evaluation value is greater than a preset value, obtaining multiple second value data corresponding to the target difference, and determining the initial promotion position corresponding to the second value data greater than the first value data as the target promotion position; when the evaluation value is less than or equal to the preset value, obtaining multiple second value data corresponding to the target difference, and determining the initial promotion position corresponding to the second value data less than the first value data as the target promotion position.

[0085] It should be noted that after obtaining the second value data of multiple initial promotion positions, the multiple second value data can be compared with the first value data of the product to be promoted obtained above, and the target promotion position can be determined from the multiple initial promotion positions. First, the first value data and the second value data can be normalized to unify the value ranges of the two value data, and then the difference between each second value data and the first value data can be calculated to obtain multiple initial differences.

[0086] Furthermore, the difference with the smallest value can be obtained from multiple initial differences to obtain multiple target differences. When the number of target differences is 1, the initial promotion position corresponding to the second value data to which the target difference belongs can be determined as the target promotion position.

[0087] It should be noted that when the number of target differences is greater than 1, the evaluation value of the product to be promoted can be obtained, where the evaluation value of the product is an attribute of the product itself. It can be an evaluation value obtained by evaluating the product before producing the product, combining multiple factors such as product positioning, cost analysis, and profit forecast. The evaluation value can range from 0 to 100 points.

[0088] Furthermore, after obtaining the evaluation value of the product to be promoted, the evaluation value can be compared with a preset value, which can be 50 points. When the evaluation value is greater than the preset value, multiple second value data belonging to the target difference can be obtained, and the initial promotion position corresponding to the second value data greater than the first value data can be determined as the target promotion position. When the evaluation value is less than or equal to the preset value, multiple second value data belonging to the target difference can be obtained, and the initial promotion position corresponding to the second value data less than the first value data can be determined as the target promotion position.

[0089] This embodiment determines the target promotion position of the product to be promoted by calculating the difference between the first value data and the second value data and combining the evaluation value of the product to be promoted, thereby improving the accuracy of determining the promotion position of the product to be promoted.

[0090] Optionally, in the method for displaying promotional products provided in the embodiment of the present application, selecting a target promotion position from M initial promotion positions based on the first value data and M second value data includes: obtaining the target product type of the product to be promoted; obtaining the number of historical products of the target product type promoted at each initial promotion position, respectively, to obtain M promotion times; updating the M second value data according to the M promotion times, to obtain M updated second value data; and determining the initial promotion position corresponding to the updated second value data having the smallest difference with the first value data among the M updated second value data as the target promotion position.

[0091] It should be noted that in the process of determining the target promotion position based on the first value data and multiple second value data, the aforementioned second value data can also be updated by the number of promotions, wherein the number of promotions is the number of times each initial promotion position promotes historical products of the same type as the target product.

[0092] Specifically, first, the target product type of the product to be promoted can be obtained, and then the number of historical products under the target product type promoted at each initial promotion position can be obtained to obtain multiple promotion times. Then, the number of promotion times and the weight of the second value data can be obtained according to a preset comparison table, and the updated second value data can be obtained through a weighted sum operation. Then, the difference between the updated second value data and the first value data can be calculated. When the number of differences is greater than 1, the target promotion position of the product to be promoted can be comprehensively determined in combination with the evaluation value of the product to be promoted.

[0093] This embodiment updates the second value data according to the number of promotions, thereby determining the target promotion position of the product to be promoted, thereby improving the accuracy of determining the promotion position of the product to be promoted.

[0094] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0095] Example 2

[0096] The embodiment of the present application also provides a display device for promotional products. It should be noted that the display device for promotional products in the embodiment of the present application can be used to execute the display method for promotional products provided in the above embodiment. The display device for promotional products provided in the embodiment of the present application is introduced below.

[0097] According to an embodiment of the present application, a device for implementing the above-mentioned method for displaying promotional products is also provided. Figure 3 is a schematic diagram of a display device for promoting products provided in Example 2 of the present application, such as Figure 3 As shown, the device comprises:

[0098] The first acquisition unit 31 is used to acquire initial product information of the product to be promoted, and pre-process the initial product information to obtain target product information.

[0099] The input unit 32 is used to input the target product information into the first value prediction model to obtain the first value data of the product to be promoted.

[0100] The first determination unit 33 is used to determine the value interval to which the first value data belongs, and obtain the promotion position corresponding to the value interval to obtain M initial promotion positions, where M is a positive integer.

[0101] The second acquisition unit 34 is used to acquire the attribute information of each initial promotion position, and calculate the value data of each initial promotion position according to the attribute information to obtain M second value data.

[0102] The selection unit 35 is used to select a target promotion position from the M initial promotion positions according to the first value data and the M second value data, and display the promotion information of the product to be promoted at the target promotion position.

[0103] The display device for promotional products provided in the embodiment of the present application obtains the initial product information of the product to be promoted through the first acquisition unit 31, and pre-processes the initial product information to obtain the target product information; the input unit 32 inputs the target product information into the first value prediction model to obtain the first value data of the product to be promoted; the first determination unit 33 determines the value interval to which the first value data belongs, and obtains the promotion position corresponding to the value interval to obtain M initial promotion positions, where M is a positive integer; the second acquisition unit 34 obtains the attribute information of each initial promotion position, and calculates the value data of each initial promotion position according to the attribute information to obtain M second value data; the selection unit 35 selects the target product information according to the first value prediction model, and obtains .... A target promotion position is selected from M initial promotion positions using one value data and M second value data, and the promotion information of the product to be promoted is displayed at the target promotion position. The first value data of the product to be promoted is obtained according to the target product information through the first value prediction model, and then its initial promotion position is determined. The second value data of each initial promotion position is calculated by acquiring the attribute information of the initial promotion position, and then the target promotion position is selected according to the first value data and the second value data, and the promotion information of the product to be promoted is displayed. The problem of low accuracy in manually determining the product promotion position in related technologies is solved, thereby achieving the technical effect of improving the efficiency and accuracy of determining the product promotion position.

[0104] Optionally, in the display device for promotional products provided in the embodiment of the present application, the first acquisition unit 31 includes: a first acquisition module, used to acquire data characteristic values ​​in the initial product information, and normalize the data characteristic values ​​to obtain multiple first characteristic values; a second acquisition module, used to acquire non-data characteristic values ​​in the initial product information, and convert each non-data characteristic value into a numerical value according to a preset corresponding relationship, and normalize the numerical value to obtain multiple second characteristic values, wherein the preset corresponding relationship is used to characterize the correspondence between the non-data characteristic value and the numerical value; a first determination module, used to determine multiple first characteristic values ​​and multiple second characteristic values ​​as target product information.

[0105] Optionally, the first value prediction model is trained in the following manner: a third acquisition unit is used to acquire multiple historical promotion products, and to acquire historical product information and historical value information of each historical promotion product in turn; a second determination unit is used to determine the historical product information and historical value information of each historical promotion product as a group of sample data, and to obtain multiple groups of first sample data; a training unit is used to train the initial prediction model using multiple groups of first sample data, and to obtain the first value prediction model.

[0106] Optionally, the third acquisition unit includes: a third acquisition module, used to obtain, for each historical promotion product, the promotion effect information obtained after the promotion operation of the historical promotion product, wherein the promotion effect information includes multiple promotion effect data; a fourth acquisition module, used to obtain the weights of each promotion effect data in the promotion effect information, obtain multiple first weights, and normalize each promotion effect data to obtain multiple processed promotion effect data; a weighting module, used to perform a weighted sum operation on the multiple processed promotion effect data and the multiple first weights to obtain the historical value information of the historical promotion product.

[0107] Optionally, the second acquisition unit 34 includes: a fifth acquisition module, used to obtain attribute information of the initial promotion position for any initial promotion position, wherein the attribute information includes multiple third eigenvalues; a sixth acquisition module, used to obtain weights of each third eigenvalue, obtain multiple second weights, and perform weighted sum calculations on each third eigenvalue according to the multiple second weights to obtain second value data of the initial promotion position.

[0108] Optionally, the selection unit 35 includes: a calculation module, which is used to calculate the difference between each second value data and the first value data in turn to obtain M initial differences; a seventh acquisition module, which is used to obtain the difference with the smallest value from the M initial differences to obtain multiple target differences; a second determination module, which is used to determine the initial promotion position corresponding to the second value data to which the target difference belongs as the target promotion position when the number of target differences is 1; an eighth acquisition module, which is used to obtain the evaluation value of the product to be promoted when the number of target differences is greater than 1; a ninth acquisition module, which is used to obtain multiple second value data corresponding to the target difference when the evaluation value is greater than a preset value, and determine the initial promotion position corresponding to the second value data greater than the first value data as the target promotion position; a tenth acquisition module, which is used to obtain multiple second value data corresponding to the target difference when the evaluation value is less than or equal to the preset value, and determine the initial promotion position corresponding to the second value data less than the first value data as the target promotion position.

[0109] Optionally, the selection unit 35 includes: an eleventh acquisition module, used to acquire the target product type of the product to be promoted; a twelfth acquisition module, used to respectively acquire the number of historical products under the target product type promoted at each initial promotion position, and obtain M promotion times; an update module, used to update M second value data according to the M promotion times, and obtain M updated second value data; a third determination module, used to determine the initial promotion position corresponding to the updated second value data having the smallest difference with the first value data among the M updated second value data as the target promotion position.

[0110] It should be noted that the above-mentioned first acquisition unit 31, input unit 32, first determination unit 33, second acquisition unit 34, and selection unit 35 correspond to steps S201 to S205 in Example 1, and the first acquisition unit 31, input unit 32, first determination unit 33, second acquisition unit 34, and selection unit 35 are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules can also be part of the device and can be run in the computer terminal 10 provided in Example 1.

[0111] Example 3

[0112] An embodiment of the present application may provide an electronic device, Figure 4 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0113] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0114] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the initial product information of the product to be promoted, and pre-process the initial product information to obtain the target product information; input the target product information into the first value prediction model to obtain the first value data of the product to be promoted; determine the value interval to which the first value data belongs, and obtain the promotion position corresponding to the value interval to obtain M initial promotion positions, where M is a positive integer; obtain the attribute information of each initial promotion position, and calculate the value data of each initial promotion position based on the attribute information to obtain M second value data; select the target promotion position from the M initial promotion positions based on the first value data and the M second value data, and display the promotion information of the product to be promoted at the target promotion position.

[0115] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the data characteristic values ​​in the initial product information, and normalize the data characteristic values ​​to obtain multiple first characteristic values; obtain the non-data characteristic values ​​in the initial product information, and convert each non-data characteristic value into a numerical value according to a preset corresponding relationship, and normalize the numerical value to obtain multiple second characteristic values, wherein the preset corresponding relationship is used to characterize the correspondence between the non-data characteristic value and the numerical value; determine the multiple first characteristic values ​​and the multiple second characteristic values ​​as the target product information.

[0116] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain multiple historical promotion products, and obtain the historical product information and historical value information of each historical promotion product in turn; determine the historical product information and historical value information of each historical promotion product as a set of sample data to obtain multiple sets of first sample data; train the initial prediction model through the multiple sets of first sample data to obtain a first value prediction model.

[0117] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: for each historical promotion product, obtain the promotion effect information obtained after the historical promotion product is promoted, wherein the promotion effect information includes multiple promotion effect data; obtain the weight of each promotion effect data in the promotion effect information to obtain multiple first weights, and normalize each promotion effect data to obtain multiple processed promotion effect data; perform weighted sum operation on the multiple processed promotion effect data and the multiple first weights to obtain the historical value information of the historical promotion product.

[0118] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: for any initial promotion position, obtain the attribute information of the initial promotion position, wherein the attribute information includes multiple third eigenvalues; obtain the weight of each third eigenvalue to obtain multiple second weights, and perform weighted sum calculation on each third eigenvalue according to the multiple second weights to obtain the second value data of the initial promotion position.

[0119] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: calculate the difference between each second value data and the first value data in turn to obtain M initial differences; obtain the difference with the smallest value from the M initial differences to obtain multiple target differences; when the number of target differences is 1, determine the initial promotion position corresponding to the second value data to which the target difference belongs as the target promotion position; when the number of target differences is greater than 1, obtain the evaluation value of the product to be promoted; when the evaluation value is greater than a preset value, obtain multiple second value data corresponding to the target difference, and determine the initial promotion position corresponding to the second value data greater than the first value data as the target promotion position; when the evaluation value is less than or equal to the preset value, obtain multiple second value data corresponding to the target difference, and determine the initial promotion position corresponding to the second value data less than the first value data as the target promotion position.

[0120] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the target product type of the product to be promoted; obtain the number of historical products under the target product type promoted at each initial promotion position respectively, and obtain M promotion times; update the M second value data according to the M promotion times, and obtain M updated second value data; determine the initial promotion position corresponding to the updated second value data with the smallest difference with the first value data among the M updated second value data as the target promotion position.

[0121] It can be understood by those skilled in the art that Figure 4 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 4 The structure of the electronic device is not limited. Figure 4 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 4 Different configurations shown.

[0122] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0123] Example 4

[0124] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for displaying promotional products provided in the first embodiment.

[0125] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0126] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the steps of the display method for promoting products.

[0127] The present application also provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the program controls the device where the computer-readable storage medium is located to execute the steps of the method for displaying promotion products.

[0128] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0129] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0131] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0133] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0134] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for displaying a promotional product, characterized in that: include: Acquire initial product information of the product to be promoted, and pre-process the initial product information to obtain target product information; Inputting the target product information into a first value prediction model to obtain first value data of the product to be promoted; Determine the value interval to which the first value data belongs, and obtain the promotion position corresponding to the value interval to obtain M initial promotion positions, where M is a positive integer; Acquire attribute information of each initial promotion position, and calculate value data of each initial promotion position according to the attribute information to obtain M second value data; A target promotion location is selected from the M initial promotion locations according to the first value data and the M second value data, and promotion information of the product to be promoted is displayed at the target promotion location.

2. The method according to claim 1, characterized in that The initial product information is preprocessed to obtain target product information including: Acquire data characteristic values ​​in the initial product information, and normalize the data characteristic values ​​to obtain a plurality of first characteristic values; Acquire non-data feature values ​​in the initial product information, convert each non-data feature value into a numerical value according to a preset corresponding relationship, and normalize the numerical value to obtain a plurality of second feature values, wherein the preset corresponding relationship is used to characterize the corresponding relationship between the non-data feature value and the numerical value; The plurality of first feature values ​​and the plurality of second feature values ​​are determined as the target product information.

3. The method according to claim 1, characterized in that The first value prediction model is trained in the following way: Acquire multiple historical promotion products, and sequentially acquire historical product information and historical value information of each historical promotion product; Determine the historical product information and historical value information of each historically promoted product as a set of sample data to obtain multiple sets of first sample data; The initial prediction model is trained using the multiple groups of first sample data to obtain the first value prediction model.

4. The method according to claim 3, characterized in that Obtaining historical value information of each historical promotion product includes: For each historical promotion product, obtaining promotion effect information of the historical promotion product after the promotion operation, wherein the promotion effect information includes a plurality of promotion effect data; Obtaining weights of each promotion effect data in the promotion effect information to obtain a plurality of first weights, and normalizing each promotion effect data to obtain a plurality of processed promotion effect data; The plurality of processed promotion effect data are weighted-summed with the plurality of first weights to obtain historical value information of the historically promoted product.

5. The method according to claim 1, characterized in that The value data of each initial promotion position is calculated according to the attribute information, and the M second value data are obtained, including: For any initial promotion position, acquiring attribute information of the initial promotion position, wherein the attribute information includes a plurality of third characteristic values; The weight of each third eigenvalue is obtained to obtain a plurality of second weights, and weighted sum calculation is performed on each third eigenvalue according to the plurality of second weights to obtain the second value data of the initial promotion position.

6. The method according to claim 1, characterized in that Selecting a target promotion location from the M initial promotion locations according to the first value data and the M second value data includes: Calculate the difference between each second value data and the first value data in turn to obtain M initial difference degrees; Obtaining the minimum difference from the M initial differences to obtain a plurality of target differences; When the number of the target difference is 1, the initial promotion position corresponding to the second value data to which the target difference belongs is determined as the target promotion position; When the number of the target differences is greater than 1, obtaining the evaluation value of the product to be promoted; When the evaluation value is greater than a preset value, a plurality of second value data corresponding to the target difference degree are obtained, and an initial promotion position corresponding to the second value data greater than the first value data is determined as the target promotion position; When the evaluation value is less than or equal to the preset value, a plurality of second value data corresponding to the target difference are obtained, and an initial promotion position corresponding to the second value data less than the first value data is determined as the target promotion position.

7. The method according to claim 1, characterized in that Selecting a target promotion location from the M initial promotion locations according to the first value data and the M second value data includes: Obtaining the target product type of the product to be promoted; Obtain the number of times each initial promotion position promotes a historical product of the target product type, and obtain M promotion times; The M second value data are updated according to the M promotion times to obtain M updated second value data; The initial promotion position corresponding to the updated second value data having the smallest difference with the first value data among the M updated second value data is determined as the target promotion position.

8. A display device for promoting products, characterized in that: include: A first acquisition unit is used to acquire initial product information of the product to be promoted, and pre-process the initial product information to obtain target product information; An input unit, used to input the target product information into a first value prediction model to obtain first value data of the product to be promoted; A first determining unit is used to determine the value interval to which the first value data belongs, and obtain a promotion position corresponding to the value interval to obtain M initial promotion positions, where M is a positive integer; A second acquisition unit is used to acquire attribute information of each initial promotion position, and calculate value data of each initial promotion position according to the attribute information to obtain M second value data; A selection unit is used to select a target promotion position from the M initial promotion positions according to the first value data and the M second value data, and display the promotion information of the product to be promoted at the target promotion position.

9. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the steps of the method for displaying promotional products described in any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the method for displaying promotional products as described in any one of claims 1 to 7.

Images