Recommendation method, system and computer device for cold start based on login operation

Abstract

The present application relates to a recommendation method, system, computer device and computer-readable storage medium for cold start based on login operation, wherein the recommendation method includes: a data acquisition step for acquiring known user information and login operation information of new users; a login information relationship tree establishment step for establishing a login information relationship tree by analyzing the data of the known user information; wherein the login information relationship tree includes known user information and its corresponding recommended information type; a new user login recommendation step for comparing and searching in the operation branch of the login information relationship tree based on the login operation information of the new user, obtaining the information type that matches the login operation information of the new user and using it as the recommended information type for the new user login. The corresponding recommended information type is automatically matched based on the user's login operation information, without the user selecting an interest tag, so as to achieve accurate and personalized information recommendation while improving the user experience.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a method, system, computer device and computer-readable storage medium for recommending cold start based on a login operation. Background Art

[0002] Since entering the Internet era, with the continuous expansion of e-commerce, the amount of information has grown exponentially, and users are always faced with the problem of information overload. The recommendation system can provide users with personalized decision support and information services based on their interests and behaviors. This requires the accumulation of a large amount of user data. However, we usually know very little about the interests and behaviors of new users, and it is difficult to accurately recommend information of interest to new users. If you cannot leave a good impression on new users, it will be difficult to retain new users, and user growth will stagnate. The Internet economy is built on the basis of large-scale users. Only the healthy growth of total users can avoid being eliminated by the environment.

[0003] In order to provide new users with information of interest, the industry currently mainly performs cold start based on the content of the hot list or the tag selection operation when logging in for the first time. Among them, according to the hot list content, the content or products are ranked according to the popularity of the existing data, and hot content is recommended to new users. When the user data gradually becomes larger, personalized recommendations are made; according to the first login tag selection, new users are required to select one or more tags when logging in, and the user's interests are collected and sorted according to the selection, and highly relevant content and products are recommended.

[0004] However, the content of the popular list is often related to real-time information, combined with many complex channels, representing the public's focus at the time, and is unified. It is difficult to achieve accuracy and personalization for a single user, which can easily make users feel tired of using it. According to the selection of tags at the first login, the tags provided by the official are often fixed, and in order to hit more interests, the tags are relatively general. The range of recommendations after selection is wide, and it is difficult to achieve accurate recommendations. If there are too many tags, it is cumbersome to choose, which makes new users feel bored and quickly abandon it.

[0005] More and more products put recommendation business at the core, or at the core of the entire product. Therefore, new users must face the problem of cold start. For new users, recommending appropriate information to them to satisfy them can achieve user growth. Due to its complexity and uncertainty, it is often impossible to achieve accuracy and personalization for a single user, which can easily make users feel tired.

[0006] In summary, currently there is no effective solution for recommending information based on the precise personality of users in cold start. Summary of the invention

[0007] The embodiments of the present application provide a recommendation method, system, computer device and computer-readable storage medium for cold start based on login operation, which automatically matches the corresponding recommended information type based on the user's login operation information without the user selecting interest tags, thereby achieving accurate and personalized information recommendations while improving user experience.

[0008] In a first aspect, an embodiment of the present application provides a recommendation method for cold start based on a login operation, comprising at least:

[0009] Data acquisition step, used to obtain known user information and new user login operation information;

[0010] A login information relationship tree establishment step, for establishing a login information relationship tree by analyzing the data of the known user information; wherein the login information relationship tree includes the known user information and its corresponding recommended information type;

[0011] The new user login recommendation step is used to compare and search in the operation branch of the login information relationship tree based on the login operation information of the new user, obtain the information type that matches the login operation information of the new user and use it as the new user login recommendation information type.

[0012] Through the above steps, during the cold start process, the login operation information of the new user is associated with the recommended information type preferred by the user by establishing a login information relationship tree, and accurate and personalized information recommendations are made to the user by comparing the login information relationship tree, thereby improving matching efficiency and accuracy. At the same time, the above recommendation method is not likely to cause user fatigue, which helps to improve user experience.

[0013] In some embodiments, the step of establishing the login information relationship tree further includes:

[0014] A login operation classification step is used to classify the login information in the known user information to obtain a login information relationship tree. Specifically, the classification operation is based on a classification algorithm model, such as a CART classification decision tree (Classification And Regression Tree, referred to as CART);

[0015] A recommended information filling step is used to perform data mining based on the known user information to obtain characteristic attributes matching the login information, summarize the characteristic attributes to obtain recommended information types, fill the recommended information types into the login information relationship tree, and obtain the recommended information types corresponding to each operation branch;

[0016] Among them, the characteristic attributes are used to specifically represent the behavioral trajectory of the user's interests and hobbies. Based on this, under the premise that it is difficult to obtain user information and behavior, the recommended information type that the user likes is analyzed based on the login information of known users, thereby realizing personalized recommendations under the premise of incomplete user information.

[0017] In some of the embodiments, in the recommendation information filling step, when the recommendation information types corresponding to multiple identical login information are different, the matching degree between the login information and the recommendation information type is calculated and the matching degrees are sorted to obtain the recommendation information type with a high matching degree, thereby improving the matching efficiency and matching accuracy of the recommendation information type of this method.

[0018] In some embodiments, the login information in the known user information and the login operation information of the new user at least include: user registration information, user operation information and user login information; by way of example and not limitation, data analysis is performed on the user's login date, login time, login email, user name setting, and registered mobile phone number, such as: determining whether the user's login date is a weekday, determining whether the user's login time period is early, noon, or late, determining whether the user's login email suffix is ​​a mainstream email, an uncommon email, or a company email, determining whether the user's username is a name, number, letter combination, or other complex text, determining the difficulty of the user's password, determining the network to which the user's registered mobile phone number belongs and whether it is a good number, determining whether the user chooses to enable notifications, determining whether the user chooses to obtain positioning, etc.

[0019] In a second aspect, an embodiment of the present application provides a recommendation system for cold start based on a login operation, comprising at least:

[0020] Data acquisition module, used to obtain known user information and new user login operation information;

[0021] A login information relationship tree establishment module, used to establish a login information relationship tree by analyzing the data of the known user information; wherein the login information relationship tree includes the known user information and its corresponding recommended information type;

[0022] The new user login recommendation module is used to compare and search in the operation branch of the login information relationship tree based on the login operation information of the new user, obtain the information type that matches the login operation information of the new user and use it as the new user login recommendation information type.

[0023] Based on the above modules, during the cold start process, the login operation information of the new user is associated with the recommended information type preferred by the user by establishing a login information relationship tree, and accurate and personalized information recommendations are made to the user by comparing the login information relationship tree, thereby improving matching efficiency and accuracy. At the same time, the use of the above recommendation system is not likely to cause user fatigue, which helps to improve user experience.

[0024] In some embodiments, the login information relationship tree building module further includes:

[0025] A login operation classification module, used for classifying the login information in the known user information to obtain a login information relationship tree;

[0026] A recommended information filling module is used to perform data mining based on the known user information to obtain characteristic attributes matching the login information, summarize the characteristic attributes to obtain recommended information types, fill the recommended information types into the login information relationship tree, and obtain the recommended information types corresponding to each operation branch;

[0027] Among them, the characteristic attributes are used to specifically represent the behavioral trajectory of the user's interests and hobbies. Based on this, under the premise that it is difficult to obtain user information and behavior, the recommended information type that the user likes is analyzed based on the login information of known users, thereby realizing personalized recommendations under the premise of incomplete user information.

[0028] In some of the embodiments, in the recommended information filling module, when multiple identical login information corresponds to different recommended information types, the matching degree between the login information and the recommended information type is calculated and the matching degrees are sorted to obtain the recommended information type with a high matching degree, thereby improving the matching efficiency and matching accuracy of the recommended information type of the system.

[0029] In some embodiments, the login information in the known user information and the login operation information of the new user at least include: user registration information, user operation information and user login information.

[0030] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the recommended method for cold start based on a login operation as described in the first aspect above is implemented.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the recommended method for cold start based on a login operation as described in the first aspect above.

[0032] Compared with the related art, the recommendation method, system, computer device and computer-readable storage medium for cold start based on login operation provided in the embodiments of the present application, through the above steps and structure, during the cold start process, the login operation information of the new user is associated with the recommended information type preferred by the user by establishing a login information relationship tree, and accurate and personalized information recommendations are made to the user by comparing the login information relationship tree, thereby improving matching efficiency and accuracy. At the same time, the use of the above recommendation method is not likely to cause user fatigue, which helps to improve user experience. Under the premise that it is difficult to obtain user information and behavior, the embodiments of the present application locate the recommended information type preferred by the user based on the analysis of the login information of known users, thereby realizing personalized recommendations under the premise of incomplete user information.

[0033] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0035] Figure 1 is a flowchart of a recommended method for cold starting based on a login operation according to an embodiment of the present application;

[0036] Figure 2 It is a schematic diagram of the principle of a recommended method for cold starting based on a login operation according to an embodiment of the present application;

[0037] Figure 3 It is a structural block diagram of a recommendation system for cold start based on a login operation according to an embodiment of the present application. Description of the drawings:

[0039] 1. Recommendation system; 11. Data acquisition module; 12. Login information relationship tree establishment module;

[0040] 13. New user login recommendation module;

[0041] 121. Login operation classification module; 122. Recommended information filling module. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0043] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0044] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0045] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0046] This embodiment provides a recommended method for cold starting based on a login operation. Figure 1 is a flowchart of a recommended method for cold starting based on a login operation according to an embodiment of the present application, with reference to Figure 1 As shown, the process includes the following steps:

[0047] The data acquisition step S1 is used to acquire known user information and new user login operation information.

[0048] The login information relationship tree establishment step S2 is used to establish a login information relationship tree by analyzing the data of known user information; wherein the login information relationship tree includes known user information and its corresponding recommended information type.

[0049] The new user login recommendation step S3 is used to compare and search in the operation branch of the login information relationship tree based on the login operation information of the new user, obtain the information type that matches the login operation information of the new user and use it as the new user login recommendation information type.

[0050] Through the above steps S1 to S3, during the cold start process, the login operation information of the new user is associated with the recommended information type preferred by the user by establishing a login information relationship tree, and accurate and personalized information recommendations are made to the user by comparing the login information relationship tree, thereby improving matching efficiency and accuracy. At the same time, the use of the above recommendation method is not likely to cause user fatigue, which helps to improve user experience.

[0051] In some embodiments, the step of establishing the login information relationship tree further includes:

[0052] The login operation classification step S201 is used to classify the login information in the known user information to obtain a login information relationship tree. Specifically, the classification operation is based on a classification algorithm model, such as a CART classification decision tree (Classification And Regression Tree, referred to as CART);

[0053] The recommended information filling step S202 is used to perform data mining based on known user information to obtain feature attributes that match their login information, and to summarize the feature attributes to obtain recommended information types, and to fill the recommended information types into the login information relationship tree to obtain the recommended information types corresponding to each operation branch. It is worth noting that when the recommended information types corresponding to multiple identical login information are different, the matching degree between the login information and the recommended information type is calculated and the matching degree is sorted to obtain the recommended information type with a high matching degree; the login information in the above-mentioned known user information and the login operation information of the new user at least include: user registration information, user operation information and user login information; by way of example and not limitation, data analysis is performed on the user's login date, login time, login email, user name setting, and registered mobile phone number, such as: determining whether the user's login date is a weekday, determining whether the user's login time period is early, midday, or late, determining whether the user's login email suffix is ​​a mainstream email, an uncommon email, or a company email, determining whether the user's username is a name, number, letter combination, or other complex text, determining the difficulty of the user's password, determining the network to which the user's registered mobile phone number belongs and whether it is a good number, determining whether the user chooses to enable notifications, determining whether the user chooses to obtain positioning, etc. Among them, characteristic attributes are used to specifically represent the behavioral trajectory of the user's interests and hobbies. Based on this, under the premise that it is difficult to obtain user information and behavior, the recommended information type that the user likes is analyzed based on the login information of known users, thereby achieving personalized recommendations under the premise of incomplete user information.

[0054] This embodiment also provides a recommendation system for cold starting based on a login operation. Figure 3 is a structural block diagram of a recommendation system for cold start based on login operation according to an embodiment of the present application. Figure 3As shown, the recommendation system includes: a data acquisition module, a login information relationship tree establishment module, a new user login recommendation module, etc. As used below, the terms "module", "unit", "subunit", etc. can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0055] Combine the following Figure 3 A detailed introduction to the various components of the recommendation system 1 is given below:

[0056] The data acquisition module 11 is used to acquire the known user information and the login operation information of the new user;

[0057] A login information relationship tree establishment module 12 is used to establish a login information relationship tree by analyzing the data of known user information; wherein the login information relationship tree includes known user information and its corresponding recommended information type;

[0058] The new user login recommendation module 13 is used to compare and search in the operation branch of the login information relationship tree based on the login operation information of the new user, obtain the information type that matches the login operation information of the new user and use it as the new user login recommendation information type.

[0059] The login information relationship tree establishing module 12 further includes:

[0060] A login operation classification module 121, used for classifying the login information in the known user information to obtain a login information relationship tree;

[0061] The recommended information filling module 122 is used to perform data mining based on known user information to obtain characteristic attributes that match their login information, and to summarize the characteristic attributes to obtain recommended information types, and to fill the recommended information types into the login information relationship tree to obtain the recommended information types corresponding to each operation branch; it is worth noting that in order to improve the matching efficiency and matching accuracy of the recommended information types of this system, when the recommended information types corresponding to multiple identical login information are different, the matching degree between the login information and the recommended information type is calculated and the matching degree is sorted to obtain the recommended information type with a high matching degree.

[0062] Based on the above modules, during the cold start process, the login operation information of the new user is associated with the recommended information type preferred by the user by establishing a login information relationship tree, and accurate and personalized information recommendations are made to the user by comparing the login information relationship tree, thereby improving matching efficiency and accuracy. At the same time, the use of the above recommendation system is not likely to cause user fatigue, which helps to improve user experience.

[0063] The login information in the known user information and the login operation information of the new user at least include: user registration information, user operation information and user login information; by way of example but not limitation, data analysis is performed on the user's login date, login time, login email, user name setting, and registered mobile phone number, such as: determining whether the user's login date is a weekday, determining whether the user's login time period is early, mid-day, or late, determining whether the user's login email suffix is ​​a mainstream email, an uncommon email, or a company email, determining whether the user's username is a name, number, letter combination, or other complex text, determining the difficulty of the user's password, determining the network to which the user's registered mobile phone number belongs and whether it is a good number, determining whether the user chooses to enable notifications, determining whether the user chooses to obtain positioning, etc. In addition, feature attributes are used to specifically represent the user's interest and hobbies behavior trajectory. Based on this, under the premise that it is difficult to obtain user information and behavior, the recommended information type that the user likes is analyzed and located based on the login information of known users, thereby realizing personalized recommendations under the premise of incomplete user information.

[0064] The embodiments of the present application are described and illustrated below through preferred embodiments.

[0065] Figure 2 It is a schematic diagram of the principle of the recommended method for cold starting based on the login operation according to an embodiment of the present application.

[0066] refer to Figure 2 As shown, after the embodiment of the present application obtains the known user information and the login operation information of the new user in step S1, the login operation is classified according to the known user information in step S201 to determine whether the login date is a weekday, the login time segmentation of morning, noon and evening, the login mailbox suffix mainstream mailbox, uncommon mailbox, company mailbox, the user name is name, number, letter combination, non-mainstream, the password difficulty, the network to which the registered mobile phone number belongs and whether it is a good number, whether to choose to enable notifications, whether to choose to obtain positioning, etc., to form Figure 2 The login information relationship tree shown.

[0067] Then, in step S202, the login operation relationship tree is filled with recommended information types according to known user information; wherein, when the recommended information types corresponding to multiple identical login information are different, the recommended information types are sorted according to the matching degree.

[0068] Finally, step S3 is executed to compare the login operation information of the new user in the login operation relationship tree, find the corresponding login operation branch, and obtain the recommended information type of the branch to recommend the recommended information of the type corresponding to the operation branch to the new user, such as: Internet, travel, real estate and home furnishing.

[0069] It should be noted that the steps shown in the above process or the flowchart in 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.

[0070] In addition, combined Figure 1 The described embodiment of the present application according to the principle schematic diagram of the recommended method for cold start based on the login operation of the embodiment of the present application can be implemented by a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor runs the computer program, the recommended method for cold start based on the login operation in the embodiment of the present application is executed.

[0071] In addition, in combination with the recommendation method for cold start based on login operation in the above embodiment, the embodiment of the present application can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the recommendation methods for cold start based on login operation in the above embodiment is implemented.

[0072] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0073] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A recommendation method for cold start based on login operation, characterized in that: At least: Data acquisition step, used to obtain known user information and new user login operation information; The login information relationship tree establishment step is used to establish a login information relationship tree by analyzing the data of the known user information; wherein the login information relationship tree includes the known user information and its corresponding recommended information type, and the login information relationship tree establishment step further includes: A login operation classification step, for classifying the login information in the known user information based on a CART classification decision tree to obtain a login information relationship tree; a recommended information filling step, for performing data mining based on the known user information to obtain characteristic attributes matching the login information, and summarizing the characteristic attributes to obtain recommended information types, filling the recommended information types into the login information relationship tree, and obtaining the recommended information types corresponding to each operation branch, wherein the characteristic attributes are used to specifically represent the behavior trajectory of the user's interests and hobbies, and when the recommended information types corresponding to multiple identical login information are different, the matching degree between the login information and the recommended information type is calculated and the matching degrees are sorted to obtain the recommended information types with high matching degrees; A new user login recommendation step, for comparing and searching in the operation branch of the login information relationship tree based on the login operation information of the new user, obtaining an information type that matches the login operation information of the new user and using it as a new user login recommendation information type; The login information in the known user information and the login operation information of the new user at least include: user registration information, user operation information and user login information.

2. A recommendation system for cold start based on login operation, characterized in that: At least: Data acquisition module, used to obtain known user information and new user login operation information; A login information relationship tree establishment module is used to establish a login information relationship tree by analyzing the data of the known user information; wherein the login information relationship tree includes the known user information and its corresponding recommended information type, and the login information relationship tree establishment module further includes: A login operation classification module, used for classifying the login information in the known user information based on the CART classification decision tree to obtain a login information relationship tree; A recommended information filling module is used to perform data mining based on the known user information to obtain characteristic attributes matching the login information, summarize the characteristic attributes to obtain recommended information types, fill the recommended information types into the login information relationship tree, and obtain the recommended information types corresponding to each operation branch. The characteristic attributes are used to specifically represent the behavior trajectory of the user's interests and hobbies. When the recommended information types corresponding to multiple identical login information are different, the matching degree between the login information and the recommended information type is calculated and the matching degrees are sorted to obtain the recommended information types with high matching degrees; A new user login recommendation module, used to compare and search in the operation branch of the login information relationship tree based on the login operation information of the new user, obtain an information type that matches the login operation information of the new user and use it as a new user login recommendation information type; The login information in the known user information and the new user login operation information at least include: user registration information, user operation information and user login information.

3. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the recommendation method for cold start based on the login operation as claimed in claim 1 is implemented.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the recommendation method for cold start based on a login operation as claimed in claim 1 is implemented.

Images