Package recommendation method, device, equipment and storage medium

Abstract

This application discloses a package recommendation method, apparatus, device, and storage medium. The method includes: upon receiving a package change request from a target user, obtaining a set of reference packages; based on any reference package, inputting the user attribute information, historical package attribute information, historical usage information, and first product attribute information of the reference package corresponding to the target user into a first prediction model to obtain a first probability; inputting the user attribute information, historical package attribute information, historical usage information, and second product attribute information of the reference package into a second prediction model to obtain a second probability; calculating a target probability based on the first and second probabilities; and selecting and recommending a target package from the set of reference packages based on the target probabilities of each reference package. In recommending packages, this application breaks down the overall package into multiple basic products and calculates the overall package order probability based on the order probability of the basic products, making the package recommendation results more aligned with user needs.

Description

Technical Field

[0001] This application relates to, but is not limited to, the field of data processing technology, and in particular to a method, apparatus, device, and storage medium for recommending packages. Background Technology

[0002] Telecommunications operators regularly release new telecommunications packages to meet diverse user needs. When a user wants to change their current package, the operator will prioritize recommending new packages. Current package recommendation algorithms determine which packages in the new package set best suit the user's preferences based on their historical package history, and then recommend packages that meet those preferences. In other words, the current recommendation method considers the package as a whole. A package is typically composed of multiple different basic products (including a main product (PO) and multiple supplementary products (SO)). However, the appeal of a package usually comes from a core product (main or supplementary), and the remaining services are passively received by the user. Recommending packages to users using the current method can easily mask the user's preferences for specific services, resulting in recommendations that fail to meet user needs and a poor user experience. Summary of the Invention

[0003] This application provides a method, apparatus, device, and storage medium for recommending service packages, enabling the recommended packages to better meet user needs and improve user experience.

[0004] In a first aspect, embodiments of this application provide a method for recommending service packages, including:

[0005] When a target user's request to change their plan is received, a set of reference plans is obtained, wherein the set of reference plans includes multiple different reference plans, and each reference plan consists of a main product and at least one supplementary product;

[0006] Based on any of the reference packages, the user attribute information, historical package attribute information, historical usage information, and the first product attribute information of the reference package corresponding to the target user are input into a first prediction model to obtain a first probability. The user attribute information, the historical package attribute information, the historical usage information, and the second product attribute information of the reference package are input into a second prediction model to obtain a second probability. A target probability is calculated based on the first probability and the second probability. The first product attribute information is the product attribute information of the main product of the reference package, the second product attribute information is the product attribute information of the main product and the supplementary product of the reference package, the first probability is the probability that the target user orders the main product of the reference package, and the second probability is the probability that the target user orders the supplementary product if the main product of the reference package has already been ordered.

[0007] Based on the target probability of each of the reference packages, a target package is selected from the set of reference packages and recommended to the target user.

[0008] In some embodiments, obtaining the reference package set includes:

[0009] Obtain an initial set of packages, wherein each candidate package in the initial set of packages has a corresponding package type tag;

[0010] Based on the reference type tag of the target user's current package and the historical package attribute information, candidate tags are selected from all the package type tags;

[0011] The reference package set is formed based on the candidate packages corresponding to the candidate tags.

[0012] In some embodiments, selecting a target package from the set of reference packages based on the target probability of each of the reference packages includes:

[0013] Determine the preset probability threshold;

[0014] The reference packages in the reference package set whose target probability exceeds the preset probability threshold are identified as the target packages.

[0015] In some embodiments, there are multiple target packages, and recommending the target packages to the target user includes:

[0016] Based on the target probability corresponding to each target package, the target packages are reordered in descending order of their numerical values;

[0017] A predetermined number of top-ranked packages are selected from the sorted target packages to form a recommendation list;

[0018] The recommended list is sent to the target user, or the order of the target packages in the recommended list is adjusted based on preset popular package elements, and the adjusted recommended list is sent to the target user.

[0019] In some embodiments, adjusting the order of the target packages in the recommendation list based on preset popular package elements, and sending the adjusted recommendation list to the target user, includes:

[0020] Determine the attribute content of each product in each target package, and calculate the similarity between the popular package elements and the attribute content;

[0021] The target packages in the recommendation list are sorted in descending order of similarity, and the sorted recommendation list is sent to the target user.

[0022] In some embodiments, calculating the target probability based on the first probability and the second probability includes:

[0023] When the quantity of the additional product is 1, the first product of the first probability and the second probability is determined as the target probability;

[0024] When there are multiple additional products, calculate the second product of all the second probabilities, and determine the target probability as the product between the second product and the first probability.

[0025] In some embodiments, before inputting the user attribute information, historical package attribute information, historical usage information, and the first product attribute information of the candidate package corresponding to the target user into the first prediction model to obtain the first probability, the method further includes:

[0026] Obtain the preset data preprocessing algorithm;

[0027] The data preprocessing algorithm is used to preprocess the user attribute information, the historical package attribute information, the historical usage information, and the first product attribute information of the candidate package.

[0028] Secondly, embodiments of this application provide a control device, including at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, which, when executed by the at least one control processor, enable the at least one control processor to perform the package recommendation method as described in the first aspect.

[0029] Thirdly, embodiments of this application also provide an electronic device, including the control device of the second aspect.

[0030] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions for performing the package recommendation method as described in the first aspect.

[0031] This application provides a package recommendation method, apparatus, device, and storage medium. The method includes: upon receiving a package change request from a target user, obtaining a set of reference packages, wherein the set of reference packages includes multiple different reference packages, each of the reference packages consisting of a main product and at least one add-on product; based on any one of the reference packages, inputting user attribute information, historical package attribute information, historical usage information, and first product attribute information of the reference package corresponding to the target user into a first prediction model to obtain a first probability; inputting the user attribute information, the historical package attribute information, historical usage information, and second product attribute information of the reference package into a second prediction model to obtain a second probability; calculating a target probability based on the first probability and the second probability, wherein the first product attribute information is the product attribute information of the main product of the reference package, the second product attribute information is the product attribute information of the main product and the add-on product of the reference package, the first probability is the probability that the target user subscribes to the main product of the reference package, and the second probability is the probability that the target user subscribes to the add-on product if the main product of the reference package has already been subscribed to; selecting a target package from the set of reference packages based on the target probabilities of each reference package, and recommending the target package to the target user. According to the solution provided in the embodiments of this application, when recommending packages, the overall package is broken down into multiple basic products, and the order probability of the overall package is calculated based on the order probability of the basic products. This effectively avoids masking the user's preference for a certain product, making the package recommendation results more in line with the user's needs and improving the user experience. Attached Figure Description

[0032] Figure 1 This is a flowchart of the steps of a package recommendation method provided in one embodiment of this application;

[0033] Figure 2 This is a structural diagram of a control device provided in another embodiment of this application. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0035] It is understandable that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0036] Telecommunications operators regularly release new telecommunications packages to meet diverse user needs. When a user wants to change their current package, the operator will prioritize recommending new packages. Current package recommendation algorithms determine which packages in the new package set best suit the user's preferences based on their historical package history, and then recommend packages that meet those preferences. In other words, the current recommendation method considers the package as a whole. A package is typically composed of multiple different basic products (including a main product (PO) and multiple supplementary products (SO)). However, the appeal of a package usually comes from a core product (main or supplementary), and the remaining services are passively received by the user. Recommending packages to users using the current method can easily mask the user's preferences for specific services, resulting in recommendations that fail to meet user needs and a poor user experience.

[0037] To address the aforementioned problems, this application provides a method, apparatus, device, and storage medium for recommending service packages. The method includes: upon receiving a target user's request to change their service package, obtaining a set of reference packages, wherein the set of reference packages includes multiple different reference packages, each of the reference packages consisting of a main product and at least one supplementary product; based on any one of the reference packages, inputting the user attribute information, historical package attribute information, historical usage information, and the first product attribute information of the reference package corresponding to the target user into a first prediction model to obtain a first probability; and inputting the user attribute information, the historical package attribute information, the historical usage information, and the second product attribute information of the reference package into a second prediction model to obtain a first probability. Product attribute information is input into a second prediction model to obtain a second probability. A target probability is calculated based on the first probability and the second probability. The first product attribute information refers to the product attribute information of the main product of the reference package, and the second product attribute information refers to the product attribute information of both the main product and supplementary products of the reference package. The first probability is the probability that the target user will order the main product of the reference package, and the second probability is the probability that the target user will order the supplementary product if they have already ordered the main product of the reference package. Based on the target probabilities of each reference package, a target package is selected from the set of reference packages and recommended to the target user. According to the solution provided in this application embodiment, when recommending packages, the overall package is broken down into multiple basic products, and the order probability of the overall package is calculated based on the order probability of the basic products. This effectively avoids masking the user's preference for a particular product, making the package recommendation results more in line with user needs and improving user experience.

[0038] The embodiments of this application will be further described below with reference to the accompanying drawings.

[0039] refer to Figure 1 , Figure 1 This is a flowchart illustrating the steps of a package recommendation method provided in one embodiment of this application. This application provides a package recommendation method, which includes, but is not limited to, the following steps:

[0040] Step S10: When a target user's request to change their plan is received, a set of reference plans is obtained. The set of reference plans includes multiple different reference plans, each of which consists of a main product and at least one supplementary product.

[0041] Specifically, the package recommendation method in this embodiment is applied to the telecommunications user management system. The main product and the supplementary product are both package products and services preset by the telecommunications user management system, such as data traffic products or call charges.

[0042] In some embodiments, Figure 1 Step S10, obtaining the reference package set, includes, but is not limited to, the following steps:

[0043] Step S11: Obtain the initial package set. Each candidate package in the initial package set has a corresponding package type label.

[0044] Step S12: Based on the reference type label of the target user's current package and the historical package attribute information, select candidate labels from all package type labels;

[0045] Step S13: Form a reference package set based on the candidate packages corresponding to the candidate tags.

[0046] It is understandable that since the telecommunications user management system has hundreds or thousands of pre-set telecommunications packages, iterating through each pre-set package based on the characteristics of each target user who needs to change packages would consume a lot of system resources. The filtering method lacks specificity, affecting the efficiency of package recommendations and consequently impacting user experience. Therefore, this embodiment uses the reference type tags of the target user's current package and historical package attribute information. Upon receiving a target user's package change request, this embodiment first determines the target user's user profile in the system based on the reference type tags of the target user's current package and historical package attribute information. For example, it categorizes users by group (individual or family) and consumption behavior (low-demand or medium-to-high data usage). Since each candidate package in the system has a package type tag containing keywords related to the corresponding candidate package content, keyword matching is performed between the package type tags and the target user's current package reference type tags and historical package attribute information. Successfully matched tags are identified as candidate tags, and a reference package set is formed based on the candidate packages corresponding to these tags. This achieves rapid initial filtering and provides effective support for improving the efficiency of subsequent package recommendations.

[0047] Step S20: Based on any reference package, input the user attribute information, historical package attribute information, historical usage information, and the first product attribute information of the reference package corresponding to the target user into the first prediction model to obtain a first probability. Input the user attribute information, historical package attribute information, historical usage information, and the second product attribute information of the reference package into the second prediction model to obtain a second probability. Calculate the target probability based on the first probability and the second probability. The first product attribute information is the product attribute information of the main product of the reference package, the second product attribute information is the product attribute information of the main product and the supplementary product of the reference package, the first probability is the probability that the target user orders the main product of the reference package, and the second probability is the probability that the target user orders the supplementary product if the main product of the reference package has already been ordered.

[0048] Understandably, based on the product service composition of the reference package (e.g., consisting of a Product Owner (PO) and an Additional Product Owner (SO), both of which are basic product services), the first probability of a target user ordering the main product PO of the reference package and the second probability of a target user ordering the additional product SO if the main product PO of the reference package has already been ordered are calculated separately. Combining the first and second probabilities, the probability of the target user ordering the overall package is calculated. On the one hand, this can effectively avoid masking the user's preference for a particular product. On the other hand, it can avoid treating the combination of PO and SO as a whole, which would prevent the collection of training data for the overall package order probability prediction model, thus affecting the accuracy of the target probability. Therefore, this embodiment breaks down the overall package into multiple basic products and calculates the overall package order probability based on the order probability of the basic products. This makes the package recommendation results more in line with user needs and improves the user experience.

[0049] It should be noted that this embodiment transforms a holistic package recommendation into two sub-problems, which are solved using two models (a first prediction model and a second prediction model). The training data required to train these two prediction models is satisfied by the target user's current package credit score. The prediction models in this embodiment can use supervised algorithms such as machine learning or deep learning, without further restrictions. For example, the method for constructing the training data for the first prediction model P(user.po) is as follows: the user attribute information (such as age, gender, occupation, etc.), usage information (call duration, data usage, etc.), PO specification information, and other user and PO product-related information are used as model inputs, and the probability of the user subscribing to the PO is used as the model output. The method for constructing the training data for the second prediction model P(user.po.so) is as follows: the user attribute information (such as age, gender, occupation, etc.), usage information (call duration, data usage, etc.), PO and SO specification information, and other user and PO / SO product-related information are used as model inputs, and the probability of the target user subscribing to the supplementary product SO when the main product PO of the reference package has already been subscribed to is used as the model output.

[0050] It should be noted that this embodiment does not limit the specific quantity of the additional product SO. Figure 1 Step S20, which calculates the target probability based on the first and second probabilities, includes, but is not limited to, the following steps:

[0051] Step S21: When the quantity of the additional product is 1, the first product of the first probability and the second probability is determined as the target probability.

[0052] Step S22: When there are multiple additional products, calculate the second product of all the second probabilities, and determine the target probability as the product between the second product and the first probability.

[0053] Specifically, when the quantity of the additional product is 1, the first product of the first probability and the second probability is determined as the target probability, calculated using the following formula: P(user.po)*P(so|user.po); when the quantity of the additional product is multiple, the second product of all the second probabilities is calculated, and the product of the second product and the first probability is determined as the target probability, calculated using the following formula: P(user.po)*P(so1|user.po)*...*P(so n |user.po), where P(user.po) is the first probability, and P(so|user.po) is the second probability when the quantity of the additional product is 1; P(so1|user.po), ..., P(so n |user.po) represents the second probability when there are multiple additional products, and user represents the target user.

[0054] Additionally, in some embodiments, execution Figure 1 Before step S20, the package recommendation method of this application embodiment also includes, but is not limited to, the following steps:

[0055] Step S41: Obtain the preset data preprocessing algorithm;

[0056] Step S42: Based on the data preprocessing algorithm, perform data preprocessing on user attribute information, historical package attribute information, historical usage information, and the first product attribute information of candidate packages.

[0057] It is understandable that the initially acquired user attribute information, historical package attribute information, historical usage information, and candidate package first product attribute information may contain irrelevant information such as null values ​​or erroneous values. Therefore, this embodiment uses a preset data preprocessing algorithm to preprocess the user attribute information, historical package attribute information, historical usage information, and candidate package first product attribute information. This can restore useful and real information, enhance the detectability of relevant information, and simplify the data to the maximum extent, thereby improving the reliability of subsequent application to model processing and reducing the possibility of network model overfitting.

[0058] It should be noted that the data preprocessing algorithm in this embodiment may include: data cleaning, text data information extraction and recognition, formatting, etc., and no further limitations are imposed here.

[0059] Step S30: Select a target package from the set of reference packages based on the target probability of each reference package, and recommend the target package to the target user.

[0060] Specifically, in some embodiments, Figure 1Step S30, which involves selecting a target package from the reference package set based on the target probability of each reference package, includes, but is not limited to, the following steps:

[0061] Step S31: Determine the preset probability threshold;

[0062] Step S32: Select the reference packages in the reference package set whose target probability exceeds the preset probability threshold as the target packages.

[0063] Understandably, reference packages with a target probability exceeding a preset probability threshold have a higher probability of being ordered by the target user. Identifying these reference packages as target packages can effectively ensure that subsequent package recommendations meet user needs and effectively improve the user experience for the target user.

[0064] Specifically, in some embodiments, the number of target packages is multiple. Figure 1 Step S30, recommending the target package to the target user, includes, but is not limited to, the following steps:

[0065] Step S33: Based on the target probability corresponding to each target package, reorder the target packages in descending order of their values;

[0066] Step S34: Select a preset number of top-ranked packages from the sorted target packages to form a recommendation list;

[0067] Step S35: Send the recommendation list to the target user, or adjust the order of the target packages in the recommendation list based on preset popular package elements, and send the adjusted recommendation list to the target user.

[0068] Understandably, in this embodiment, based on the target probability corresponding to each target package, the reference packages are reordered in descending order of their numerical values. A preset number of packages at the top of the sorted list are then selected as target packages. The subscription probabilities of these target packages are then sorted from high to low to form a recommendation list, which is sent to the target user. Alternatively, the order of the target packages in the recommendation list can be adjusted based on preset popular package elements, and the adjusted recommendation list is sent to the target user. This ensures that the recommendation list sent to the target user better reflects the user's actual needs.

[0069] Specifically, in some embodiments, step S35 involves adjusting the order of target packages in the recommendation list based on preset popular package elements, and then sending the adjusted recommendation list to the target user. The method includes, but is not limited to, the following steps:

[0070] Step S351: Determine the attribute content of each product in each target package and calculate the similarity between popular package elements and attribute content;

[0071] Step S352: Adjust the order of the target packages in the recommendation list according to the similarity from high to low, and send the adjusted recommendation list to the target user.

[0072] It is understandable that individual user behavior data may lag behind market changes, while popular package elements implicitly contain group preferences and operator strategies. The unadjusted recommendation list already contains recommendations that match users' actual needs. Based on this, the attribute content of each product in each target package in the recommendation list is determined, the second similarity between popular package elements and attribute content is calculated, and the ranking of target packages in the recommendation list is adjusted according to the second similarity from high to low. The adjusted recommendation list is then sent to the target users. In other words, the recommendation list adjusted based on the current popular package elements can dynamically adapt to market trends and user group preferences, thus better optimizing the user experience.

[0073] like Figure 2 As shown, Figure 2 This is a structural diagram of a control device provided in one embodiment of this application. The present invention also provides a control device 200, comprising:

[0074] The processor 210 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0075] The memory 220 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 220 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 220 and is called and executed by the processor 210 using the package recommendation method of the embodiments of this application.

[0076] Input / output interface 230 is used to implement information input and output;

[0077] The communication interface 240 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0078] Bus 250 transmits information between various components of the device (e.g., processor 210, memory 220, input / output interface 230, and communication interface 240);

[0079] The processor 210, memory 220, input / output interface 230 and communication interface 240 are connected to each other within the device via bus 250.

[0080] In addition, this application also provides an electronic device, including the control device 200 described in the above embodiments.

[0081] In addition, this application embodiment also provides a storage medium, which is a computer-readable storage medium, storing a computer program that, when executed by a processor, implements the above-described package recommendation method.

[0082] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof. The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separate, and may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0083] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0084] The above provides a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A package recommendation method characterized by comprising: The method comprises the following steps: When receiving a package changing demand of a target user, a reference package set is obtained, wherein the reference package set comprises a plurality of different reference packages, and each reference package is composed of a main product and at least one additional product; Based on any reference package, user attribute information, historical package attribute information, historical usage information and first product attribute information of the reference package corresponding to the target user are input into a first prediction model to obtain a first probability, the user attribute information, the historical package attribute information, the historical usage information and second product attribute information of the reference package are input into a second prediction model to obtain a second probability, and a target probability is calculated based on the first probability and the second probability, wherein the first product attribute information is product attribute information of the main product of the reference package, the second product attribute information is product attribute information of the main product and the additional product of the reference package, the first probability is a probability of the target user subscribing to the main product of the reference package, and the second probability is a probability of the target user subscribing to the additional product in the case of having subscribed to the main product of the reference package; A target package is selected from the reference package set based on the target probability of each reference package, and the target package is recommended to the target user; The target probability is calculated based on the first probability and the second probability, which comprises: In the case that the number of additional products is one, a first product of the first probability and the second probability is determined as the target probability; In the case that the number of additional products is a plurality, a second product of all the second probabilities is calculated, and a product between the second product and the first probability is determined as the target probability. 2.The package recommendation method of claim 1, wherein, The reference package set is obtained, which comprises: An initial package set is obtained, and each candidate package in the initial package set corresponds to a package type label; Based on a reference type label of a current package of the target user and the historical package attribute information, a candidate label is selected from all the package type labels; The reference package set is formed based on the candidate package corresponding to the candidate label. 3.The package recommendation method of claim 1, wherein, The target package is selected from the reference package set based on the target probability of each reference package, which comprises: A preset probability threshold is determined; The reference package in the reference package set whose target probability exceeds the preset probability threshold is determined as the target package.

4. The package recommendation method according to claim 1 or 3, characterized by, The number of target packages is a plurality, and the target package is recommended to the target user, which comprises: Based on the target probability corresponding to each target package, the target packages are reordered in a descending order of numerical values; A preset number of packages in the front row in the reordered target packages are selected to form a recommendation list; The recommendation list is sent to the target user, or the ordering of the target package in the recommendation list is adjusted based on a preset popular package element, and the adjusted recommendation list is sent to the target user.

5. The package recommendation method of claim 4, wherein, adjusting the ranking of the target package in the recommendation list based on the preset popular package element, and sending the adjusted recommendation list to the target user, comprising: determining the attribute content of each product in each target package, and calculating the similarity between the popular package element and the attribute content; adjusting the ranking of the target package in the recommendation list according to the order from high to low of the similarity, and sending the adjusted recommendation list to the target user. 6.The package recommendation method of claim 1, wherein, Before inputting the user attribute information corresponding to the target user, the historical package attribute information, the historical usage information and the first product attribute information of the reference package into the first prediction model to obtain the first probability, the method further comprises: obtaining a preset data preprocessing algorithm; based on the data preprocessing algorithm, the user attribute information, the historical package attribute information, the historical usage information and the first product attribute information of the reference package are preprocessed.

7. A control device characterized by comprising: comprise at least one control processor and a memory connected in communication with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute the package recommendation method of any one of claims 1 to 6.

8. An electronic device, comprising: The control device of claim 7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions for causing a computer to execute the package recommendation method of any one of claims 1 to 6.

Images