Age prediction method, device and electronic equipment
Through a feature prediction model based on user historical information, efficient and accurate age prediction in Internet services is achieved, and the problem of low efficiency in collecting age information in the prior art is solved.
Patent Information
- Application Number
- CN201910591813.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-07-01
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2039-07-01
AI Technical Summary
In the prior art, the collection of user age information through questionnaires is inefficient and the effective information acquisition rate is low, making it difficult to meet the accurate and efficient needs of user age information in Internet services.
By determining the historical information of the target user, including the business object information it accesses within the preset period, the target characteristics are determined based on this information, and inputting it into the pre-trained prediction model, the age of the target user and its corresponding probability are predicted.
It improves the efficiency and accuracy of age prediction, reduces the dependence on user manual input of age information, and increases the acquisition rate of effective information.
Smart Images

Figure CN110415020B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Internet application technology, and in particular to an age prediction method, device and electronic device. Background Art
[0002] With the continuous development of Internet technology, many Internet-based services have emerged. At present, many Internet-based services need to collect the age of users or their relatives. Taking parent-child services as an example, it is usually necessary to collect the age information of users' children so as to recommend more appropriate and rich parent-child service items to users based on the age of their children. In related technologies, age information manually entered by users is generally collected through questionnaires. However, collecting age information in this way is inefficient and has a low acquisition rate of effective information. Summary of the invention
[0003] In order to solve one of the above technical problems, the present application provides an age prediction method, device and electronic device.
[0004] According to a first aspect of an embodiment of the present application, there is provided an age prediction method, comprising:
[0005] Determine the historical information of the target user for a preset type of service; the historical information includes information of the target object corresponding to the preset type of service visited by the target user within a preset period of time;
[0006] determining target characteristics based on the historical information;
[0007] The target feature is input into a pre-trained prediction model to predict one or more target ages for the target user and a prediction probability corresponding to each target age.
[0008] Optionally, the target objects include merchants that carry out the preset type of business and / or consumers corresponding to the preset type of business.
[0009] Optionally, determining the target feature based on the historical information includes:
[0010] Determining the probability of each of the target objects for each preset age based on the historical information;
[0011] Based on the probability of each target object for each preset age, the tendency value of the target user at each preset age is determined as the target feature.
[0012] Optionally, for any preset age, the inclination value of the target user at the preset age is determined in the following manner:
[0013] For each of the target objects, a target quotient value corresponding to the target object is determined; the target quotient value is the quotient of first data and second data, the first data is the probability of the target object for the preset age, and the second data is the difference between 1 and the first data;
[0014] The target quotient values corresponding to each of the target objects are multiplied together and multiplied by a preset constant to obtain the tendency value of the target user at the preset age.
[0015] Optionally, the historical information further includes time information of the target user accessing the target object within the preset time period;
[0016] Determining target features based on the historical information further includes:
[0017] Based on the time information, the number of days from the first visit to the target object and the last visit to the target object by the target user within the preset time period are determined as the target feature.
[0018] Optionally, the method further includes:
[0019] A target confidence level for each target age is determined; the target confidence level is used to screen users.
[0020] Optionally, determining the target confidence level of each target age includes:
[0021] Determining a target activity of the target user for the preset type of service;
[0022] Determining a target confidence level for each target age based on the target activity level and the predicted probability corresponding to each target age;
[0023] Among them, for any target age, the target confidence of the target age is positively correlated with the target activity and positively correlated with the predicted probability corresponding to the target age.
[0024] Optionally, determining the target confidence of each target age based on the target activity and the predicted probability corresponding to each target age includes:
[0025] Acquire a predetermined association relationship, where the association relationship represents an association relationship between the probability of the predicted age, the user's activity level for the preset type of service, and the confidence level of the predicted age;
[0026] Based on the association relationship, the target activity and the predicted probability corresponding to each of the target ages, a target confidence level for each of the target ages is determined.
[0027] According to a second aspect of an embodiment of the present application, there is provided an age prediction device, comprising:
[0028] A first determination module is used to determine the historical information of the target user for a preset type of service; the historical information includes information of the target object corresponding to the preset type of service visited by the target user within a preset period of time;
[0029] An extraction module, configured to determine target features based on the historical information;
[0030] The prediction module is used to input the target feature into a pre-trained prediction model to predict one or more target ages for the target user and the prediction probability corresponding to each target age.
[0031] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the first aspects is implemented.
[0032] According to a fourth aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of the first aspects is implemented.
[0033] The technical solution provided by the embodiments of the present application may have the following beneficial effects:
[0034] The age prediction method and device provided by the embodiment of the present application determines the historical information of the target user for the preset type of business, and the historical information includes the information of the target object corresponding to the preset type of business visited by the target user within the preset time period, determines the target feature based on the above historical information, and inputs the target feature into the pre-trained prediction model to predict one or more target ages for the target user, and the prediction probability corresponding to each target age. Since the present embodiment can predict the age according to the target object corresponding to the preset type of business visited by the target user, there is no need to collect the age information manually input by the user through a questionnaire. Therefore, under the premise of ensuring that the age prediction has a high accuracy, the efficiency of age prediction is improved and the acquisition rate of effective information is increased.
[0035] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0037] Figure 1is a flow chart of an age prediction method according to an exemplary embodiment of the present application;
[0038] Figure 2 is a flowchart of another age prediction method according to an exemplary embodiment of the present application;
[0039] Figure 3 is a flowchart of another age prediction method according to an exemplary embodiment of the present application;
[0040] Figure 4 is a block diagram of an age prediction method and device according to an exemplary embodiment of the present application;
[0041] Figure 5 is a block diagram of another age prediction method and device according to an exemplary embodiment of the present application;
[0042] Figure 6 is a block diagram of another age prediction method and device according to an exemplary embodiment of the present application;
[0043] Figure 7 is a block diagram of another age prediction method and device according to an exemplary embodiment of the present application;
[0044] Figure 8 is a block diagram of another age prediction method and device according to an exemplary embodiment of the present application;
[0045] Fig. 9 It is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0046] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0047] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.
[0048] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0049] like Figure 1 As shown, Figure 1 1 is a flowchart of an age prediction method according to an exemplary embodiment, which can be applied to a server. The method includes the following steps:
[0050] In step 101, historical information of a target user for a preset type of service is determined, where the historical information includes information of target objects corresponding to the preset type of service visited by the target user within a preset period of time.
[0051] In this embodiment, the business involved may be an Internet-based service business, such as a life review business, a group purchase business, or an online shopping business, etc. The preset type business is a business that requires the collection of the user's age or the age of the user's relatives. For example, the preset type business may be a parent-child type business, a leisure and entertainment type business, or a clothing and beauty type business, etc. It can be understood that the preset type business may be any reasonable business, and the present application does not limit the specific type of the preset type business.
[0052] In this embodiment, the historical information of the target user for the preset type of service may at least include information of the target object corresponding to the preset type of service visited (e.g., browsed, consumed, etc.) by the target user within a preset period of time. The target object information may specifically include sequence information of the target objects visited by the target user within the preset period of time, that is, sequence information obtained by arranging the target objects visited by the target user within the preset period of time in chronological order.
[0053] In this embodiment, the target object may include merchants that carry out preset type of business, and may also include consumer objects corresponding to the preset type of business (for example, specific commodities, or group purchase orders, or coupons, etc.). It may also include merchants that carry out preset type of business and consumer objects corresponding to the preset type of business. It can be understood that the present application does not limit the specific types of target objects. Among them, the preset time period can be a period of time in the past, for example, it can be a period of time in the past year, or it can be a period of time in the past month, etc. The present application does not limit the specific scope of the preset time period.
[0054] In this embodiment, the historical information of the target user for the preset type of service may further include the time information of the target user visiting the target object within the preset period, the consumption behavior information of the target user within the preset period (for example, the consumption amount, consumption items, etc.), etc. It can be understood that the above historical information may also include any other reasonable information, and the present application does not limit the specific content of this historical information.
[0055] In step 102, target features are determined based on the above historical information.
[0056] In this embodiment, the target feature can be determined based on the above historical information. The historical information may include, but is not limited to, information about the target object corresponding to the preset type of business visited by the target user within a preset period, time information when the target user visited the above target object within the preset period, and consumption behavior information of the target user within the preset period. Therefore, one or more corresponding target features can be determined based on each type of historical information.
[0057] In this embodiment, since the historical information at least includes the information of the target object corresponding to the preset type of business visited by the target user within the preset period, the corresponding target feature can be determined at least based on the information of the target object. Specifically, first, the probability of each target object for each preset age can be determined based on the historical information. Then, based on the probability of each target object for each preset age, the tendency value of the target user at each preset age is determined as the target feature. Since the tendency value of the target user at each preset age is used as the target feature, the accuracy of age prediction can be improved.
[0058] In this embodiment, the historical information may also include time information of the target user's access to the target object within a preset period of time. Therefore, the corresponding target feature may also be determined based on the time information. Specifically, the number of days from the first time the target user accesses the target object within the preset period of time to the present, and the number of days from the last time the target user accesses the target object within the preset period of time may be determined based on the time information as the target feature. Since the number of days from the first time the target user accesses the target object within the preset period of time to the present, and the number of days from the last time the target user accesses the target object within the preset period of time to the present, the active features of the target user for the target object can be better reflected, and the target object can reflect the age feature. Therefore, using the above days as the target feature can improve the accuracy of age prediction.
[0059] In step 103, the target features are input into a pre-trained prediction model to predict one or more target ages for the target user and the prediction probability corresponding to each target age.
[0060] In this embodiment, the target features can be input into a pre-trained prediction model to predict one or more target ages for the target user and the prediction probability corresponding to each target age. The prediction model can be any reasonable classifier model. Optionally, the prediction model can be a Light GBM (gradient boosting framework that uses tree based learning algorithm, using a gradient boosting framework based on a decision tree learning algorithm) model. It can be understood that the present application does not limit the specific type of the prediction model.
[0061] In this embodiment, after the target feature is input into the pre-trained prediction model, the prediction model can predict the prediction probability corresponding to each preset age. The preset age with the largest prediction probability can be selected as the target age, or a preset number of preset ages can be selected in descending order of prediction probability as the target age. At the same time, the prediction probability corresponding to each target age can also be obtained.
[0062] The age prediction method provided by the above-mentioned embodiment of the present application determines the historical information of the target user for the preset type of business, and the historical information includes the information of the target object corresponding to the preset type of business visited by the target user within the preset time period, determines the target feature based on the above-mentioned historical information, and inputs the target feature into the pre-trained prediction model to predict one or more target ages for the target user, and the prediction probability corresponding to each target age. Since the present embodiment can predict the age according to the target object corresponding to the preset type of business visited by the target user, there is no need to collect the age information manually input by the user through a questionnaire. Therefore, under the premise of ensuring that the age prediction has a high accuracy, the efficiency of age prediction is improved and the acquisition rate of effective information is increased.
[0063] like Figure 2 As shown, Figure 2 According to a flowchart of another age prediction method shown in an exemplary embodiment, the embodiment describes a process of determining target features. The method can be applied to a server and includes the following steps:
[0064] In step 201, historical information of a target user for a preset type of service is determined, where the historical information includes information of target objects corresponding to the preset type of service visited by the target user within a preset period of time.
[0065] In step 202, the probability of each target object for each preset age is determined based on the historical information.
[0066] In this embodiment, the target objects corresponding to the preset type of services visited by the target user can be determined based on the historical information, and then the probability of each target object for each preset age can be determined based on the pre-stored data. Specifically, a series of ages can be set in advance according to the actual needs of the preset type of services. And each target object corresponds to a probability for each preset age, which can be set in advance based on experience or obtained by statistics of a large amount of sampled data. The probability of each target object for each preset age can be stored.
[0067] For example, the preset ages include 1, 2, and 3 years old, and the target is merchant A. According to experience, the children of users who visit merchant A are usually 2 and 3 years old, and the proportion is half, while a small number of users who visit merchant A have children of 1 year old. Therefore, the probability corresponding to merchant A for 1 year old can be set to 10%, the probability corresponding to 2 years old is 45%, and the probability corresponding to 3 years old is 45%.
[0068] For another example, the preset ages include 1, 2, and 3, and the target object is product B. By statistically analyzing the historical consumption sampling data of a large number of users, it can be found that among the users who purchased product B, the proportion of users with children aged 1 is 50%, the proportion of users with children aged 2 is 30%, and the proportion of users with children aged 3 is 20%. Therefore, the probability of product B corresponding to 1 year old is 50%, the probability corresponding to 2 years old is 30%, and the probability corresponding to 3 years old is 20%.
[0069] It should be noted that the set age can be in months (such as one month, or two months, or three months, etc.), or in years (such as one year old, or two years old, or three years old, etc.). It can be understood that the set age can be any reasonable age range, and this application is not limited in this regard.
[0070] In step 203, based on the probability of each target object for each preset age, the tendency value of the target user at each preset age is determined as the target feature.
[0071] In this embodiment, based on the probability of each target object for each preset age, the inclination value of the target user at each preset age can be determined as the target feature. In one implementation, for any preset age, the sum of the probabilities of each target object for the preset age can be added as the inclination value of the target user at the preset age.
[0072] In another implementation, for any preset age, the inclination value of the target user at the preset age can also be determined in the following manner: First, for each target object, determine the target quotient value corresponding to the target object, which is the quotient of the first data and the second data, wherein the first data is the numerator and the second data is the denominator. The first data is the probability of the target object for the preset age, and the second data is the difference between 1 and the first data. Then, multiply the target quotient value corresponding to each target object and multiply it by a preset constant to obtain the inclination value of the target user for the preset age. It can be understood that the present application does not limit the specific setting of the preset constant. The above-mentioned inclination value obtained by this implementation method can more accurately reflect the age inclination corresponding to the target user.
[0073] In step 204, the target features are input into a pre-trained prediction model to predict one or more target ages for the target user and the prediction probability corresponding to each target age.
[0074] It should be noted that Figure 1 The same steps as in the embodiment, in the above Figure 2 The embodiments will not be described in detail. For related contents, please refer to Figure 1 Example.
[0075] The age prediction method provided by the above-mentioned embodiment of the present application determines the historical information of the target user for the preset type of business, and the historical information includes the information of the target object corresponding to the preset type of business visited by the target user within the preset time period, and determines the probability of each target object for each preset age based on the historical information, and determines the propensity value of the target user at each preset age based on the probability of each target object for each preset age as the target feature, and inputs the target feature into the pre-trained prediction model to predict one or more target ages for the target user, and the prediction probability corresponding to each target age. Because this embodiment determines the propensity value of the target user at each preset age as the target feature through the probability of each target object for each preset age. Thereby, the accuracy of age prediction is further improved.
[0076] In some other optional implementations, after predicting one or more target ages for the target user and the prediction probability corresponding to each target age, the target confidence of each target age can be further determined, and the target confidence can be used to screen users for message push and advertising promotion. For example, the target age predicted for the target user, the prediction probability corresponding to each target age, and the target confidence can be provided to some business terminals as reference information of the target user. The business terminal can determine whether it is necessary to push some specific messages or advertisements to the target user based on the reference information of the target user.
[0077] In this embodiment, not only the target age of the target user is predicted, but also the target confidence of the target age is predicted, so that the obtained age information is richer.
[0078] like Figure 3 As shown, Figure 3 According to a flowchart of another age prediction method shown in an exemplary embodiment, the embodiment describes in detail the process of determining the target confidence of each target age. The method can be applied to a server and includes the following steps:
[0079] In step 301, historical information of a target user for a preset type of service is determined, where the historical information includes information of target objects corresponding to the preset type of service visited by the target user within a preset period of time.
[0080] In step 302, target features are determined based on the above historical information.
[0081] In step 303, the target features are input into a pre-trained prediction model to predict one or more target ages for the target user and the prediction probability corresponding to each target age.
[0082] In step 304, the target activity of the target user for a preset type of service is determined.
[0083] In step 305, the target confidence of each target age is determined based on the target activity and the predicted probability corresponding to each target age.
[0084] In this embodiment, the target activity of the target user for the preset type of service is used to characterize the active status of the target user in accessing the preset type of service. For example, the number of visits of the target user to the preset type of service in the past preset period of time can be used as the target activity.
[0085] In this embodiment, the target confidence of each target age can be determined based on the target activity and the prediction probability corresponding to each target age. For any target age, the target confidence of the target age is positively correlated with the target activity of the target user for the preset type of service and is positively correlated with the prediction probability corresponding to the target age.
[0086] Specifically, the probability of the predicted age, the user's activity for the preset type of business and the confidence of the predicted age, and the correlation between the three can be obtained in advance. For example, the correlation can be set based on experience, or a large number of sample data sets collected can be statistically analyzed to obtain the correlation. It can be understood that the application does not limit the specific method of obtaining the correlation. Then, the correlation can be stored.
[0087] When determining the target confidence of each target age, first, the predetermined association relationship can be obtained from pre-stored data, and then the target confidence of each target age is determined based on the relationship data, the target activity and the predicted probability corresponding to each target age.
[0088] It should be noted that Figure 1 and Figure 2 The same steps as in the embodiment, in the above Figure 3 The embodiments will not be described in detail. For related contents, please refer to Figure 1 and Figure 2 Example.
[0089] The age prediction method provided by the above embodiment of the present application determines the target activity of the target user for the preset type of service, and determines the target confidence of each target age based on the target activity and the prediction probability corresponding to each target age. Thus, not only the target age for the target user is predicted, but also the target confidence of the target age is predicted, so that the obtained age information is richer.
[0090] It should be noted that although the operations of the method of the present application are described in a specific order in the above embodiments, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be changed in the order of execution. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.
[0091] Corresponding to the aforementioned age prediction method embodiment, the present application also provides an embodiment of an age prediction device.
[0092] like Figure 4 As shown, Figure 4 4 is a block diagram of an age prediction device according to an exemplary embodiment of the present application. The device may include: a first determination module 401, an extraction module 402 and a prediction module 403.
[0093] The first determining module 401 is used to determine the historical information of the target user for a preset type of service, where the historical information includes information of the target object corresponding to the preset type of service visited by the target user within a preset period of time.
[0094] The extraction module 402 is used to determine the target feature based on the above historical information.
[0095] The prediction module 403 is used to input the above target features into a pre-trained prediction model to predict one or more target ages for the target user and the prediction probability corresponding to each target age.
[0096] In some optional implementations, the target objects include merchants that conduct the preset type of business and / or consumers corresponding to the preset type of business.
[0097] like Figure 5 As shown, Figure 5 is another block diagram of an age prediction device according to an exemplary embodiment of the present application. Figure 4 Based on the illustrated embodiment, the extraction module 402 may include: a determination submodule 501 and a first calculation submodule 502 .
[0098] The determination submodule 501 is used to determine the probability of each target object for each preset age based on the above historical information.
[0099] The first calculation submodule 502 is used to determine the tendency value of the target user at each preset age based on the probability of each target object for each preset age as the target feature.
[0100] In some other optional implementations, for any preset age, the first calculation submodule 502 determines the inclination value of the target user at the preset age in the following manner: for each target object, determine the target quotient value corresponding to the target object, the target quotient value is the quotient of the first data and the second data, the first data is the probability of the target object for the preset age, and the second data is the difference between 1 and the first data. And multiply the target quotient value corresponding to each target object and multiply it by a preset constant to obtain the inclination value of the target user at the preset age.
[0101] like Figure 6 As shown, Figure 6 is another block diagram of an age prediction device according to an exemplary embodiment of the present application. Figure 5 On the basis of the illustrated embodiment, the extraction module 402 may further include: a second calculation submodule 503 .
[0102] The second calculation submodule 503 is used to determine the number of days from the first and last visits to the target object by the target user within the preset time period based on the time information as the target feature.
[0103] The above historical information also includes time information when the target user accesses the target object within a preset time period.
[0104] like Figure 7 As shown, Figure 7 is another block diagram of an age prediction device according to an exemplary embodiment of the present application. Figure 4 On the basis of the illustrated embodiment, the device may further include: a second determination module 404.
[0105] The second determination module 404 is used to determine the target confidence of each target age, and the target confidence is used to screen users.
[0106] like Figure 8 As shown, Figure 8 is another block diagram of an age prediction device according to an exemplary embodiment of the present application. Figure 7 On the basis of the illustrated embodiment, the second determining module 404 may include: a first obtaining submodule 801 and a second obtaining submodule 802 .
[0107] The first acquisition submodule 801 is used to determine the target activity of the target user for a preset type of service.
[0108] The second acquisition submodule 802 is used to determine the target confidence of each target age based on the target activity and the predicted probability corresponding to each target age.
[0109] Among them, for any target age, the target confidence of the target age is positively correlated with the target activity and positively correlated with the predicted probability corresponding to the target age.
[0110] In other optional embodiments, the second acquisition submodule 802 is configured to: obtain a predetermined association relationship, which represents the association relationship between the probability of the predicted age, the user's activity in a preset type of service and the confidence of the predicted age, and determine the target confidence of each target age based on the association relationship, the target activity and the predicted probability corresponding to each target age.
[0111] It should be understood that the above device can be pre-set in the server, or loaded into the server by downloading, etc. The corresponding modules in the above device can cooperate with the modules in the server to implement the age prediction solution.
[0112] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.
[0113] The present application also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figures 1 to 3 Any embodiment provides an age prediction method.
[0114] Corresponding to the above-mentioned age prediction method, the present application embodiment also proposes Fig. 9 The schematic structural diagram of an electronic device according to an exemplary embodiment of the present application is shown in FIG. Fig. 9 At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an age prediction device at the logical level. Of course, in addition to the software implementation, this application does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.
[0115] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.
[0116] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. An age prediction method, characterized in that: The method comprises: Determine the historical information of the target user for a preset type of service; the historical information includes information of the target object corresponding to the preset type of service visited by the target user within a preset period of time; determining target characteristics based on the historical information; Inputting the target feature into a pre-trained prediction model to predict one or more target ages for the target user and a prediction probability corresponding to each target age; The determining of the target feature based on the historical information includes: Determining the probability of each of the target objects for each preset age based on the historical information; Based on the probability of each target object for each preset age, determining the inclination value of the target user at each preset age as the target feature; For any preset age, the inclination value of the target user at the preset age is determined in the following manner: For each of the target objects, a target quotient value corresponding to the target object is determined; the target quotient value is the quotient of first data and second data, the first data is the probability of the target object for the preset age, and the second data is the difference between 1 and the first data; The target quotient values corresponding to each of the target objects are multiplied together and multiplied by a preset constant to obtain the tendency value of the target user at the preset age.
2. The method according to claim 1, characterized in that The target objects include merchants that carry out the preset type of business and / or consumers corresponding to the preset type of business.
3. The method according to claim 1, characterized in that The historical information also includes time information of the target user accessing the target object within the preset time period; Determining target features based on the historical information further includes: Based on the time information, the number of days from the first visit to the target object and the last visit to the target object by the target user within the preset time period are determined as the target feature.
4. The method according to claim 1, characterized in that The method further comprises: A target confidence level for each target age is determined; the target confidence level is used to screen users.
5. The method according to claim 4, characterized in that Determining the target confidence level of each target age includes: Determining a target activity of the target user for the preset type of service; Determining a target confidence level for each target age based on the target activity level and the predicted probability corresponding to each target age; Among them, for any target age, the target confidence of the target age is positively correlated with the target activity and positively correlated with the predicted probability corresponding to the target age.
6. The method according to claim 5, characterized in that The determining, based on the target activity and the predicted probability corresponding to each target age, a target confidence level for each target age, comprises: Acquire a predetermined association relationship, where the association relationship represents an association relationship between the probability of the predicted age, the user's activity level for the preset type of service, and the confidence level of the predicted age; Based on the association relationship, the target activity and the predicted probability corresponding to each of the target ages, a target confidence level for each of the target ages is determined.
7. An age prediction device, characterized in that: The device comprises: A first determination module is used to determine the historical information of the target user for a preset type of service; the historical information includes information of the target object corresponding to the preset type of service visited by the target user within a preset period of time; An extraction module, used to determine the target feature based on the historical information, including: determining the probability of each of the target objects for each preset age based on the historical information; determining the tendency value of the target user at each preset age based on the probability of each of the target objects for each preset age as the target feature; A prediction module is used to input the target feature into a pre-trained prediction model to predict one or more target ages for the target user and the prediction probability corresponding to each target age; for any preset age, the inclination value of the target user at the preset age is determined in the following manner: for each target object, a target quotient value corresponding to the target object is determined; the target quotient value is the quotient of first data and second data, the first data is the probability of the target object for the preset age, the second data is 1 minus the first data, the target quotient value corresponding to each target object is multiplied, and multiplied by a preset constant to obtain the inclination value of the target user at the preset age.
8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
9. An electronic 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 program, the method according to any one of claims 1 to 6 is implemented.
