Package recommendation method, control device and storage medium

Abstract

The invention discloses a package recommendation method, a control device and a storage medium. The method comprises the following steps: constructing a first user vector based on a first consumption amount of a target user for each product service; based on the second historical usage information of each neighbor user, the second historical package price and all the product services, determining a second consumption amount of each product service by the neighbor user, and constructing a second user vector; updating the first user vector based on the second user vector and the communication times to obtain a target user vector; and recommending the target package to the target user based on the first similarity between the target user vector and each reference vector in the reference package set. According to the method, after the first user vector is obtained based on the quota of the target user for each product service, the first user vector is updated based on the second user vector, the similarity with each reference package is calculated to perform recommendation of the target package, the package usage and the social relation are comprehensively considered, and the accuracy of the recommendation result is improved.

Description

Technical Field

[0001] The present application relates to, but is not limited to, the field of data processing technology, and in particular to a package recommendation method, a control device, and a storage medium. Background Art

[0002] Telecom operators regularly release new telecom packages to meet diverse user needs. When a user wants to upgrade their current package, the operator prioritizes recommending a new package. Existing package recommendation methods only consider the user's usage requirements and the specifications of their previous packages. They then measure the similarity between each candidate package in the new package set and the user's usage requirements and the specifications of their previous packages, and then recommend packages with high similarity. However, user package selection is often influenced by their social circles (such as recommendations between family, friends, and colleagues). Recommendations based solely on historical package usage or similarity in package specifications fail to capture these socially driven selection patterns, resulting in package recommendations that deviate from actual needs and a poor user experience. Summary of the Invention

[0003] The embodiments of the present application provide a package recommendation method, a control device, and a storage medium, so that the package recommendation results can better meet the user's actual needs and improve the user experience.

[0004] In a first aspect, an embodiment of the present application provides a package recommendation method, which is applied to a telecommunications user management system, wherein the telecommunications user management system is preset with multiple product services, and the method includes:

[0005] When receiving a package change request from a target user, a reference package set is obtained, wherein the reference package set includes multiple different reference packages, each of which corresponds to a reference vector, and the reference vector is composed of multiple credits, the number of which is the same as the number of the product services, and each credit is the amount spent on the corresponding product service based on the package specifications of the corresponding reference package;

[0006] Determining the first consumption amount of the target user for each of the product services based on the first historical usage information of the target user, the first historical package price, and all of the product services, and constructing a first user vector of the target user based on each of the first consumption amounts, wherein a higher value corresponds to the first consumption amount, and a higher preference value of the target user for the product service corresponding to the corresponding product service;

[0007] Determining a second consumption amount of each neighbor user for each of the products and services based on the second historical usage information, second historical package prices, and all of the products and services of each neighbor user having a communication relationship with the target user, and constructing a second user vector for the neighbor user based on each of the second consumption amounts;

[0008] Iteratively updating the first user vector based on the second user vector and the corresponding number of communications to obtain a target user vector;

[0009] A first similarity between the target user vector and each of the reference vectors is calculated, a target package is selected from the reference package set based on the first similarity of each of the reference packages, and the target package is recommended to the target user.

[0010] In some embodiments, iteratively updating the first user vector based on the second user vector and the corresponding number of communications to obtain a target user vector includes:

[0011] Calculating a weight of each neighbor user based on the number of neighbor users and the number of communications between each neighbor user and the target user;

[0012] The first user vector is iteratively updated based on the first user vector, all the second user vectors, and the corresponding weights until an absolute value of a difference between a user vector obtained at a previous iteration and a user vector corresponding to a current iteration is less than a preset value, and the user vector corresponding to the current iteration is determined as the target user vector.

[0013] In some embodiments, the weight of each neighbor user is calculated based on the number of neighbor users and the number of communications between each neighbor user and the target user, and is obtained according to the following formula:

[0014]

[0015] Among them, w k is the weight, k is the sequence number of the neighbor user, Count k is the number of communications between the neighbor user corresponding to sequence number k and the target user, and M is the number of the neighbor users corresponding to the target user.

[0016] In some embodiments, the first user vector is iteratively updated based on the first user vector, all the second user vectors, and the corresponding weights, and is obtained according to the following formula:

[0017]

[0018] Among them, Vu n+1 is the updated first user vector corresponding to the target user, Vu n is the first user vector before updating, when n=1, Vu1 is the first user vector, k is the sequence number of the neighbor user, Count kis the number of communications between the neighbor user corresponding to sequence number k and the target user, M is the number of neighbor users corresponding to the target user, and λ is the learning rate hyperparameter.

[0019] In some embodiments, obtaining a reference package set includes:

[0020] Obtaining an initial package set, wherein each candidate package in the initial package set corresponds to a package type label;

[0021] Based on the reference type tag of the target user's current package and the historical package attribute information, selecting a candidate tag from all the package type tags, wherein the candidate tag is a tag that matches the reference type tag of the target user's current package and a keyword associated with the historical package attribute information;

[0022] The reference package set is formed based on the candidate packages corresponding to the candidate tags.

[0023] In some embodiments, the first similarity between the target user vector and each of the reference vectors is calculated according to the following formula:

[0024] Simi(user,plan)=μ*Simi(Vu last ,V Plan )+(1-μ)*Simi(Spec user ,Spec plan );

[0025] Among them, Simi(user,plan) is the first similarity, μ is the preset hyperparameter, Vu last is the target user vector, V Plan For any of the reference vectors, Spec user Spec is the package specification of the current package of the target user. plan is the package specification of any reference package, and Simi(x, y) is used to calculate the similarity between x and y.

[0026] In some embodiments, there are multiple target packages, and selecting a target package from the reference package set based on the first similarity of each reference package, and recommending the target package to the target user includes:

[0027] reordering the reference packages in descending order of values ​​based on the first similarities corresponding to the respective reference packages;

[0028] Selecting a preset number of top-ranked packages from the sorted reference packages as target packages, and forming a recommendation list based on all the target packages;

[0029] The recommendation list is sent to the target user, or the order of the target packages in the recommendation list is adjusted based on preset popular package elements, and the recommendation list after the order adjustment is sent to the target user.

[0030] In some embodiments, adjusting the order of the target package in the recommendation list based on preset popular package elements, and sending the adjusted recommendation list to the target user, includes:

[0031] Determining the attribute content of each product in each of the target packages, and calculating a second similarity between the popular package elements and the attribute content;

[0032] The order of the target packages in the recommendation list is adjusted in descending order according to the second similarity, and the recommendation list after the adjustment is sent to the target user.

[0033] In a second aspect, an embodiment of the present application provides a control device comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed 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 as described in the first aspect.

[0034] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the package recommendation method as described in the first aspect.

[0035] The embodiment of the present application provides a package recommendation method, a control device and a storage medium, the method comprising: when receiving a package change request from a target user, obtaining a reference package set, wherein the reference package set includes a plurality of different reference packages, each of the reference packages corresponds to a reference vector, the reference vector is composed of a plurality of quotas, the number of the quotas is the same as the number of the product services, and each quota is the amount spent on the corresponding product service in the package specification of the corresponding reference package; based on the first historical usage information of the target user, the first historical package price and all the product services, determining the first consumption amount of the target user for each of the product services, and constructing the first user vector of the target user based on each of the first consumption amounts, wherein the numerical value The higher the first consumption amount, the higher the preference value of the target user corresponding to the product or service; based on the second historical usage information, second historical package price and all the products and services of each neighbor user with a communication relationship with the target user, the second consumption amount of each product or service of the neighbor user is determined, and the second user vector of the neighbor user is constructed based on each second consumption amount; the first user vector is iteratively updated based on the second user vector and the corresponding number of communications to obtain a target user vector; the first similarity between the target user vector and each reference vector is calculated, and the target package is selected from the reference package set based on the first similarity of each reference package, and the target package is recommended to the target user. According to the solution provided in the embodiment of the present application, the amount for each product or service is determined based on the historical package information of the target user to form a first user vector, and then the first user vector is updated based on the second user vector of the neighbor user with a communication relationship with the target user, and the target package is recommended to the target user based on the similarity between the updated first user vector and each reference package in the reference package set. In this way, the historical package usage can be comprehensively considered while also considering the influence of social relationship driving on the user's package selection, so that the package recommendation result can better meet the user's real needs and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flowchart of the steps of a package recommendation method provided by an embodiment of the present application;

[0037] Figure 2 This is a structural diagram of a control device provided in another embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0039] It is understood that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and the like in the specification, claims, or accompanying drawings are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0040] Telecom operators regularly release new telecom packages to meet diverse user needs. When a user wants to upgrade their current package, the operator prioritizes recommending a new package. Existing package recommendation methods only consider the user's usage requirements and the specifications of their previous packages. They then measure the similarity between each candidate package in the new package set and the user's usage requirements and the specifications of their previous packages, and then recommend packages with high similarity. However, user package selection is often influenced by their social circles (such as recommendations between family, friends, and colleagues). Recommendations based solely on historical package usage or similarity in package specifications fail to capture these socially driven selection patterns, resulting in package recommendations that deviate from actual needs and a poor user experience.

[0041] To solve the above-mentioned problems, the embodiments of the present application provide a package recommendation method, a control device, and a storage medium. The method includes: when receiving a package change request from a target user, obtaining a reference package set, wherein the reference package set includes multiple different reference packages, each of the reference packages corresponds to a reference vector, and the reference vector is composed of multiple quotas, the number of the quotas is the same as the number of the product services, and each quota is the amount spent on the corresponding product service according to the package specifications of the corresponding reference package; based on the first historical usage information of the target user, the first historical package price, and all the product services, determining the first consumption amount of the target user for each of the product services, and constructing the first user vector of the target user based on each of the first consumption amounts. , wherein the higher the value, the higher the preference value of the target user for the product or service corresponding to the first consumption amount; based on the second historical usage information, second historical package prices, and all the products and services of each neighbor user with whom the target user has a communication relationship, the second consumption amount of each product or service of the neighbor user is determined, and the second user vector of the neighbor user is constructed based on each second consumption amount; based on the second user vector and the corresponding number of communications, the first user vector is iteratively updated to obtain a target user vector; the first similarity between the target user vector and each reference vector is calculated, and a target package is selected from the reference package set based on the first similarity of each reference package, and the target package is recommended to the target user. According to the solution provided in the embodiment of the present application, the amount for each product or service is determined based on the historical package information of the target user to form a first user vector, and then the first user vector is updated based on the second user vector of the neighbor user with whom the target user has a communication relationship, and the target package is recommended to the target user based on the similarity between the updated first user vector and each reference package in the reference package set. In this way, the historical package usage and the influence of social relationship driving on the user's package selection can be comprehensively considered, so that the package recommendation result can better meet the user's real needs and improve the user experience.

[0042] The embodiments of the present application are further described below with reference to the accompanying drawings.

[0043] refer to Figure 1 , Figure 1 This is a flowchart of the steps of a package recommendation method provided by an embodiment of the present application. The embodiment of the present application provides a package recommendation method, which is applied to a telecommunications user management system. The telecommunications user management system is preset with multiple product services. The method includes but is not limited to the following steps:

[0044] Step S10: When receiving the package change request of the target user, obtain a reference package set, wherein the reference package set includes multiple different reference packages, each reference package corresponds to a reference vector, and the reference vector is composed of multiple quotas. The number of quotas is the same as the number of product services, and each quota is the amount spent on the corresponding product service of the package specification of the corresponding reference package.

[0045] Specifically, the reference package set in this embodiment is a set of reference packages selected by the telecommunications user management system based on the user attributes of the target user.

[0046] Specifically, in some embodiments, Figure 1 Acquiring the reference package set in step S10 includes but is not limited to the following steps:

[0047] Step S11, obtaining an initial package set, wherein each candidate package in the initial package set corresponds to a package type label;

[0048] Step S12, based on the reference type tag of the target user's current package and the historical package attribute information, selecting a candidate tag from all the package type tags, wherein the candidate tag is a tag that matches the reference type tag of the target user's current package and the keyword associated with the historical package attribute information;

[0049] Step S13: forming a reference package set based on the candidate packages corresponding to the candidate tags.

[0050] It is understandable that since hundreds or even thousands of telecom packages are pre-set in the telecom user management system, if each target user who wishes to change their package were to traverse and screen each pre-set telecom package based on the characteristics of the target user, a large amount of system resources would be consumed, the screening method would be non-targeted, and the efficiency of package recommendations would be affected, thereby affecting the user experience. Based on this, this embodiment uses the reference type tag of the target user's current package and historical package attribute information. Based on this, after receiving the target user's package change request, this embodiment first determines the target user's user profile in the system based on the reference type tag of the target user's current package and historical package attribute information. For example, based on user group classification, whether it is an individual user or a family user, and consumption behavior, whether it is a low-demand user or a medium-to-high-volume user, etc. Since each candidate package in the system has a package type tag, which contains the corresponding candidate package content keywords, keyword matching is performed based on the package type tag with the reference type tag of the target user's current package and historical package attribute information. The tags that successfully match are determined as candidate tags, and a reference package set is formed based on the candidate packages corresponding to the candidate tags, achieving rapid preliminary screening and providing effective support for subsequently improving the efficiency of package recommendations.

[0051] Step S20: Determine the first consumption amount of the target user for each product service based on the target user's first historical usage information, the first historical package price, and all products and services, and construct the first user vector of the target user based on each first consumption amount. The higher the value, the higher the preference value of the target user for the product service corresponding to the corresponding first consumption amount.

[0052] Step S30: Determine the second consumption amount of each product and service of each neighbor user who has a communication relationship with the target user based on the second historical usage information, second historical package prices, and all products and services, and construct a second user vector of the neighbor user based on each second consumption amount.

[0053] It can be understood that this embodiment constructs the first user vector of the target user and the second user vector of each neighbor user having a communication relationship with the target user, wherein the first user vector Vu = (offer1, offer2, ..., offerN) corresponds to the target user's consumption amount for all products and services in the system, offer1 ... offerN is the consumption amount of the target user's current package corresponding to each different product and service, the first user vector is positively correlated with the target user's usage of all products and services in the system, and the second user vector Vu k =(offer1, offer2, …, offerN) corresponds to the consumption amount of all products and services in the system by neighbor users. The second user vector is positively correlated with the consumption of all products and services in the system by neighbor users. In this way, the correlation between the consumption of all products and services by the target user and its neighbor users is determined.

[0054] Step S40: Iteratively update the first user vector based on the second user vector and the corresponding number of communications to obtain a target user vector.

[0055] It can be understood that, referring to the description of the above embodiment, after obtaining the first user vector and the second user vector, this embodiment iteratively updates the first user vector based on the second user vector and the corresponding number of communications to obtain the target user vector. The obtained target user vector can comprehensively judge the user's preference for different products based on the target user's usage behavior of system products and services and the target user's social relationships, that is, it can comprehensively consider the historical package usage while also considering the impact of social relationship-driven package selection on the user, providing an effective data basis for subsequent package recommendation results that meet user needs.

[0056] Specifically, in some embodiments, Figure 1 Step S40 includes but is not limited to the following steps:

[0057] Step S41, calculating the weight of each neighbor user based on the number of neighbor users and the number of communications between each neighbor user and the target user;

[0058] Step S42: Iteratively update the first user vector based on the first user vector, all second user vectors, and corresponding weights until the absolute value of the difference between the user vector obtained at the previous iteration and the user vector corresponding to the current iteration is less than a preset value, and determine the user vector corresponding to the current iteration as the target user vector.

[0059] It should be noted that in this embodiment, the weight of each neighbor user is calculated based on the number of neighbor users and the number of communications between each neighbor user and the target user, and is obtained according to the following formula:

[0060]

[0061] Among them, w k is the weight, k is the sequence number of the neighbor user, Count k is the number of communications between the neighbor user corresponding to sequence number k and the target user, and M is the number of neighbor users corresponding to the target user.

[0062] It should be noted that, in this embodiment, the first user vector is iteratively updated based on the first user vector, all second user vectors, and corresponding weights, and is obtained according to the following formula:

[0063]

[0064] Among them, Vu n+1 is the first user vector corresponding to the updated target user, Vu n is the first user vector before update, when n=1, Vu1 is the first user vector, k is the sequence number of the neighbor user, Count k is the number of communications between the neighbor user corresponding to sequence number k and the target user, M is the number of neighbor users corresponding to the target user, and λ is the learning rate hyperparameter.

[0065] It should be noted that the iterative termination condition of the iterative update operation of this embodiment is as shown in the following formula:

[0066] |Vu n+1 -Vu n |<ε;

[0067] Among them, ε is a preset value.

[0068] It can be understood that the preset value of this embodiment is an extremely small value. That is, during the iterative update of the first user vector based on the second user vector and the corresponding number of communications, the communication relationship between the neighbor user and the target user can be used to transmit preference information to obtain a target user vector that comprehensively considers historical package usage while also considering the package preference of the target user driven by social relationships. Until the absolute value of the difference between the first user vectors before and after the update is less than the preset value (without limiting the specific size of the preset value, it can be determined by those skilled in the art based on actual conditions), it indicates that the influence of the second user vector of the current neighbor user on the first user vector of the target user has reached a balanced state. Determining the first user vector at this time as the target user vector can ensure the stability of the target user vector and thereby ensure the accuracy of the subsequent determination of the target package.

[0069] Step S50 , calculating a first similarity between the target user vector and each reference vector, selecting a target package from the reference package set based on the first similarity of each reference package, and recommending the target package to the target user.

[0070] Specifically, in some embodiments, Figure 1 Step S50 of selecting a target package from the reference package set based on the first similarity of each reference package and recommending the target package to the target user includes but is not limited to the following steps:

[0071] Step S51, based on the first similarity corresponding to each reference package, reorder the reference packages in descending order of value;

[0072] Step S52: Select a preset number of top-ranked packages from the ranked reference packages and determine them as target packages, and form a recommendation list based on all the target packages;

[0073] Step S53: Send the recommendation list to the target user, or adjust the order of the target package in the recommendation list based on the preset popular package elements, and send the adjusted recommendation list to the target user.

[0074] It should be noted that, in this embodiment, the first similarity is calculated according to the following method:

[0075] Simi(user,plan)=μ*Simi(Vu last ,V Plan )+(1-μ)*Simi(Spec user ,Spec plan );

[0076] Among them, Simi(user,plan) is the first similarity, μ is the preset hyperparameter, Vu lastis the target user vector, V Plan For any reference vector, Spec user The package specifications of the target user's current package (such as traffic size, call duration and other basic attributes), Spec plan is the package specification of any reference package, Simi(x, y) is used to calculate the similarity between x and y. It should be noted that the embodiment of the present application does not limit the specific method of calculating the similarity Simi(x, y), which can be expressed by calculating the cosine distance or Euclidean distance between the reference vector and the target user vector.

[0077] Among them, Spec user The target user vector is normalized and the result is multiplied by the target user's latest average monthly consumption amount, which is used to indicate the allocation of the total package price of the target user's current package among different product services. Similarly, Spec plan Includes the quota of all products and services of any reference package (used to indicate the quota allocation of the total package price of any reference package among different products and services), that is, Simi (Spec user ,Spec plan ), μ represents the package preference similarity Simi(Vu last ,V Plan ) and the similarity between the package specifications Simi(Spec user ,Spec plan That is, the first similarity of this embodiment takes into account the similarity of package preferences and the similarity of package specifications, and the similarity result is reliable, effectively ensuring the reliability of subsequent selection of the target package.

[0078] It is understandable that in this embodiment, based on the first similarity corresponding to each reference package, the reference packages are reordered in descending numerical order, and a preset number of packages ranked at the top of the sorted reference packages are selected to determine as target packages. In this way, the determined target packages are closer to the target user's vector preferences and package specifications. A recommendation list is formed based on all target packages and sent to the target user. Alternatively, the sorting of the target packages in the recommendation list is adjusted based on preset popular package elements, and the adjusted recommendation list is sent to the target user. In this way, the recommendation list sent to the target user can better meet the user's actual needs.

[0079] Specifically, in some embodiments, step S53 of adjusting the order of the target package in the recommendation list based on the preset popular package elements and sending the adjusted recommendation list to the target user includes but is not limited to the following steps:

[0080] Step S531, determining the attribute content of each product in each target package, and calculating the second similarity between the popular package elements and the attribute content;

[0081] Step S532: Adjust the order of the target packages in the recommendation list in descending order of the second similarity, and send the adjusted recommendation list to the target user.

[0082] Specifically, the popular package elements in this embodiment are keywords of products and services in the package that are highly accepted by current users.

[0083] It is understandable that individual user behavior data may lag behind market changes, while popular package elements imply group preferences and operator strategies. The recommendation list before adjustment already contains recommendation results that meet the user's real needs. On this basis, the attribute content of each product in each target package in the recommendation list is determined, and the second similarity between the popular package elements and the attribute content is calculated. The order of the target packages in the recommendation list is adjusted in descending order according to the second similarity, and the adjusted recommendation list is sent to the target user. That is, the recommendation list adjusted based on the current popular package elements can dynamically adapt to market trends and user group preferences, and better optimize the user experience.

[0084] like Figure 2 As shown, Figure 2 : is a structural diagram of a control device provided in one embodiment of the present application. The present invention also provides a control device 200, comprising:

[0085] The processor 210 may be implemented as a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0086] The memory 220 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 220 can store an operating system and other application programs. 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 by the processor 210 to execute the package recommendation method of the embodiments of this application.

[0087] Input / output interface 230, used to implement information input and output;

[0088] Communication interface 240, used to implement communication interaction between the apparatus and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0089] bus 250 , which transmits information between the various components of the device (e.g., processor 210 , memory 220 , input / output interface 230 , and communication interface 240 );

[0090] The processor 210 , the memory 220 , the input / output interface 230 and the communication interface 240 are connected to each other in communication within the device via the bus 250 .

[0091] In addition, an embodiment of the present application further provides a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the above-mentioned package recommendation method is implemented.

[0092] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory optionally includes a memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of the above-mentioned networks include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and are located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0093] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data) and is volatile and non-volatile, removable, and non-removable. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0094] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above implementation. Those skilled in the art can also make various equivalent modifications or substitutions under the shared conditions that do not violate the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A package recommendation method, characterized in that: Applied to a telecommunications user management system, the telecommunications user management system is preset with multiple product services, the method includes: When receiving a package change request from a target user, a reference package set is obtained, wherein the reference package set includes multiple different reference packages, each of which corresponds to a reference vector, and the reference vector is composed of multiple credits, the number of which is the same as the number of the product services, and each credit is the amount spent on the corresponding product service based on the package specifications of the corresponding reference package; Determining the first consumption amount of the target user for each of the product services based on the first historical usage information of the target user, the first historical package price, and all of the product services, and constructing a first user vector of the target user based on each of the first consumption amounts, wherein a higher value corresponds to the first consumption amount, and a higher preference value of the target user for the product service corresponding to the corresponding product service; Determining a second consumption amount of each neighbor user for each of the products and services based on the second historical usage information, second historical package prices, and all of the products and services of each neighbor user having a communication relationship with the target user, and constructing a second user vector for the neighbor user based on each of the second consumption amounts; Iteratively updating the first user vector based on the second user vector and the corresponding number of communications to obtain a target user vector; A first similarity between the target user vector and each of the reference vectors is calculated, a target package is selected from the reference package set based on the first similarity of each of the reference packages, and the target package is recommended to the target user.

2. The method for recommending a package according to claim 1, wherein: Iteratively updating the first user vector based on the second user vector and the corresponding number of communications to obtain a target user vector includes: Calculating a weight of each neighbor user based on the number of neighbor users and the number of communications between each neighbor user and the target user; The first user vector is iteratively updated based on the first user vector, all the second user vectors, and the corresponding weights until an absolute value of a difference between a user vector obtained at a previous iteration and a user vector corresponding to a current iteration is less than a preset value, and the user vector corresponding to the current iteration is determined as the target user vector.

3. The method for recommending a meal plan according to claim 2, wherein: The weight of each neighbor user is calculated based on the number of neighbor users and the number of communications between each neighbor user and the target user, and is obtained according to the following formula: Among them, w k is the weight, k is the sequence number of the neighbor user, Count k is the number of communications between the neighbor user corresponding to sequence number k and the target user, and M is the number of neighbor users corresponding to the target user.

4. The method for recommending a meal plan according to claim 2, wherein: The first user vector is iteratively updated based on the first user vector, all the second user vectors, and the corresponding weights, and is obtained according to the following formula: Among them, Vu n+1 is the updated first user vector corresponding to the target user, Vu n is the first user vector before updating, when n=1, Vu1 is the first user vector, k is the sequence number of the neighbor user, Count k is the number of communications between the neighbor user corresponding to sequence number k and the target user, M is the number of neighbor users corresponding to the target user, and λ is the learning rate hyperparameter.

5. The method for recommending a meal plan according to claim 1, wherein: The obtaining of the reference package set includes: Obtaining an initial package set, wherein each candidate package in the initial package set corresponds to a package type label; Based on the reference type tag of the target user's current package and the historical package attribute information, selecting a candidate tag from all the package type tags, wherein the candidate tag is a tag that matches the reference type tag of the target user's current package and a keyword associated with the historical package attribute information; The reference package set is formed based on the candidate packages corresponding to the candidate tags.

6. The method for recommending a meal plan according to claim 1, wherein: Calculate the first similarity between the target user vector and each of the reference vectors, and obtain it according to the following formula: Simi(user,plan)=μ*Simi(Vu last ,In Plan )+(1-μ)*Simi(Spec user ,Spec plan ); Among them, Simi(user,plan) is the first similarity, μ is the preset hyperparameter, Vu last is the target user vector, V Plan For any of the reference vectors, Spec user Spec is the package specification of the current package of the target user. plan is the package specification of any reference package, and Simi(x, y) is used to calculate the similarity between x and y.

7. The method for recommending a meal plan according to claim 1, wherein: Selecting a target package from the reference package set based on the first similarity of each of the reference packages, and recommending the target package to the target user, comprising: reordering the reference packages in descending order of values ​​based on the first similarities corresponding to the respective reference packages; Selecting a preset number of top-ranked packages from the sorted reference packages as target packages, and forming a recommendation list based on all the target packages; The recommendation list is sent to the target user, or the order of the target packages in the recommendation list is adjusted based on preset popular package elements, and the recommendation list after the order adjustment is sent to the target user.

8. The method for recommending a meal plan according to claim 7, wherein: Adjusting the order of the target package in the recommendation list based on preset popular package elements, and sending the adjusted recommendation list to the target user, includes: Determining the attribute content of each product in each of the target packages, and calculating a second similarity between the popular package elements and the attribute content; The order of the target packages in the recommendation list is adjusted in descending order according to the second similarity, and the recommendation list after the adjustment is sent to the target user.

9. A control device, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed 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 as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the package recommendation method according to any one of claims 1 to 8.

Images