CN113643072A - Data processing method and device, computer equipment and storage medium - Google Patents

Data processing method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN113643072A
CN113643072A CN202111017441.9A CN202111017441A CN113643072A CN 113643072 A CN113643072 A CN 113643072A CN 202111017441 A CN202111017441 A CN 202111017441A CN 113643072 A CN113643072 A CN 113643072A
Authority
CN
China
Prior art keywords
target
information
equity
value
piece
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111017441.9A
Other languages
Chinese (zh)
Inventor
吴桐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Ping An Medical Health Technology Service Co Ltd
Original Assignee
Ping An Medical and Healthcare Management Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Medical and Healthcare Management Co Ltd filed Critical Ping An Medical and Healthcare Management Co Ltd
Priority to CN202111017441.9A priority Critical patent/CN113643072A/en
Publication of CN113643072A publication Critical patent/CN113643072A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application relates to a data processing method, a data processing device, computer equipment and a storage medium, wherein the data processing method comprises the following steps: acquiring portrait data and at least one piece of interest information of a target object, wherein the at least one piece of interest information is used for exciting the target object to trigger a target event; performing equity conversion on the at least one piece of equity information based on an equity conversion rule to obtain at least one equity value corresponding to the at least one piece of equity data; inputting the image data into a rights and interests gain model to obtain a sensitive curve of the target object, wherein the sensitive curve is a probability gain curve of the target object for triggering the target event aiming at the at least one piece of rights and interests information; and pushing target right information to the target object based on the sensitivity curve and the at least one right value, wherein the target right information is at least one piece of the at least one piece of right information. Through the scheme of the application, the rights and interests information can be pushed to the required user more accurately.

Description

Data processing method and device, computer equipment and storage medium
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a data processing method and apparatus, a computer device, and a storage medium.
Background
With the continuous development and popularization of the internet, the service range of the online service provided based on the internet gradually covers most users, and the competition faced by the provider of the online service is more and more intense, so that the provider of the online service attracts users to join in marketing activities by putting rights and interests to the users in the process that the users participate in the online service in order to improve the conversion rate of the users; the traditional method for releasing rights and interests to users is to predict the probability of user conversion after predicting the rights and interests to users through a Response Model (Response Model), and then to release rights and interests according to the conversion probability of users. However, the response model only relates to the conversion probability of the user, and neglects the gain effect of the equity placement itself, so the manner of equity placement through the traditional response model is to be improved.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present application aims to provide a data processing method, aiming at providing a data processing method suitable for complex actual marketing scenarios.
In a first aspect, the present application provides a data processing method, including: acquiring portrait data and at least one piece of interest information of a target object, wherein the at least one piece of interest information is used for exciting the target object to trigger a target event; performing equity conversion on the at least one piece of equity information based on an equity conversion rule to obtain at least one equity value corresponding to the at least one piece of equity data; inputting the image data into a rights and interests gain model to obtain a sensitive curve of the target object, wherein the sensitive curve is a probability gain curve of the target object for triggering the target event aiming at the at least one piece of rights and interests information; and pushing target right information to the target object based on the sensitivity curve and the at least one right value, wherein the target right information is at least one piece of the at least one piece of right information.
In an optional implementation manner, before the inputting the image data into the interest gain model to obtain the sensitivity curve of the target object, the data processing method further includes: extracting the right and interest characteristic information corresponding to the at least one piece of right and interest information; the above inputting the image data into the equity gain model to obtain the sensitivity curve of the target object includes: and inputting the image data and the rights characteristic information into the rights gain model to obtain the sensitivity curve of the target object.
In actual marketing, the same user may have different gain probabilities for different scenes or different categories of rights and interests (such as red envelope, discount, coupon, gift, different scenes such as takeout, car-taking, shopping, etc.) with the same converted amount; therefore, in the embodiment of the application, the characteristics of the benefit information are also used as the input of the benefit gain model, so that the obtained sensitivity curve of the target user is more accurate.
In an alternative embodiment, the pushing target equity information to the target object based on the sensitivity curve and the at least one equity value includes: obtaining at least one sensitivity corresponding to the at least one equity value based on the sensitivity curve; selecting a first target equity value corresponding to the at least one sensitivity value being greater than a first threshold value; and pushing the right information corresponding to the first target right value to the target object.
In an optional implementation manner, the pushing, to the target object, right information corresponding to the first target right value includes: acquiring budget information and return on investment rate information for triggering the target event; calculating a second target equity value in the first target equity values based on the budget information and the return on investment rate information, wherein the second target equity value is an equity value which triggers the highest return on investment rate of the target event; and pushing the right information corresponding to the second target right value to the target object.
In an alternative embodiment, said calculating a second one of said first target equity values based on said budget information and said return on investment information comprises: determining the second threshold based on the budget information and return on investment information; and selecting the right value smaller than the second threshold value from the first target right values to obtain a second target right value.
In the embodiment of the application, the budget information and the return on investment rate information of the target event are triggered by obtaining; and then, determining the upper limit of the pushing rights and interests based on the budget information and the return on investment rate information, so that the scheme of the application is more intelligent and practical.
In an optional implementation, before acquiring the portrait data of the target object and the at least one piece of interest information, the data processing method further includes: acquiring a training sample and the at least one piece of rights and interests information, wherein the training sample comprises a reference group and an experimental group, the reference group comprises portrait data of a first training object and a trigger result of the first training object to the target event, and the experimental group comprises portrait data of a second training object and a trigger result of the second training object to the target event; performing equity conversion on the at least one piece of equity information based on the equity conversion rule to obtain at least one equity value corresponding to the at least one piece of equity data; and training by a deep learning method to obtain a gain model, wherein the gain model is obtained by inputting the image data of the first training object, outputting the trigger result of the first training object to the target event, inputting the image data of the second training object and the at least one gain value, and outputting the trigger result of the second training object to the target event.
In an optional implementation manner, before the equity gain model is trained by the deep learning method, the data processing method further includes: extracting the right and interest characteristic information corresponding to the at least one piece of right and interest information; in the training of the gain model by the deep learning method, the input of the image data of the second training target and the at least one gain value includes: the second training object image data, the at least one equity value, and the equity feature information are input.
In a second aspect, the present application provides a data processing apparatus, comprising: the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring sample data and application attribute characteristics of target application, and the sample data comprises object image characteristics of a sample object and object behavior characteristics of the sample object on at least one characteristic dimension; the conversion unit is used for carrying out rights and interests conversion on the at least one piece of rights and interests information based on a rights and interests conversion rule to obtain at least one rights and interests value corresponding to the at least one piece of rights and interests data; an input unit, configured to input the image data into a rights gain model to obtain a sensitivity curve of the target object, where the sensitivity curve is a probability gain curve of the target object for triggering the target event according to the at least one piece of rights information; and a pushing unit, configured to push target right information to the target object based on the sensitivity curve and the at least one right value, where the target right information is at least one piece of the at least one piece of right information.
In a third aspect, the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the data processing method provided in the first aspect when executing the computer program.
In a third aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for executing, when executed by a processor, the data processing method provided in the first aspect.
In the embodiment of the application, the sensitivity curve of the target user to the rights and interests is obtained by inputting the portrait data of the target object (namely the target user) into the rights and interests gain model, and then whether to push the rights and interests of the target user is judged based on the sensitivity curve and the converted value of the rights and interests to be pushed. Since the sensitivity curve is a probability gain curve of the target object triggering the target event for the at least one entitlement information. The curve reflects the relationship between the value after the equity conversion and the gain probability; the gain probability is the difference between the probability that the target user triggers the target event after being pushed with the right and the probability that the target user triggers the target event without being pushed with the right. In other words, the sensitivity curve reflects the gain probability that the target user is prompted to trigger the target event after the push right. Therefore, by the scheme of the application, the rights and interests information can be pushed to the user more accurately, and the user is prompted to trigger the target event, for example, the user is prompted to place an order; in addition, in the scheme of the application, the right information is numerically converted according to a preset rule, namely the right is converted into equivalent money, so that the scheme can adapt to various complicated rights pushing in actual situations.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flow chart of a data processing method provided in an embodiment of the present application;
FIG. 2 is a schematic flow chart diagram of another data processing method provided by the embodiments of the present application;
FIG. 3 is a schematic flow chart diagram of a method for equity gain model training provided by an embodiment of the present application;
fig. 4 is a schematic block diagram of a data processing apparatus provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application;
fig. 6 and 7 are sensitivity curve diagrams of the equity gain model output provided by the embodiments of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Referring to fig. 1, fig. 1 is a schematic flow chart of a data processing method provided in an embodiment of the present application, where the data processing method of the present application is mainly applied to various types of marketing campaigns; as shown, the method may include:
101: the method includes acquiring portrait data of a target object and at least one piece of interest information, where the at least one piece of interest information is information for motivating the target object to trigger a target event.
In this embodiment, the portrait data of the object may be data for describing the object, and the portrait data of the object may include various types, for example, at least one of the following types: gender of the subject, age of the subject, occupation of the subject, model of the device used by the subject, operating system of the device used by the subject, price of the device used by the subject, place of residence of the subject, fan count of the subject, status of the subject registering/installing a predetermined application, historical expense amount, historical account transfer, loan amount, and the like.
In one or more optional embodiments, the image data of the object may further include behavior data of the object, and the specific behavior data is data describing a behavior of the object that is continuously transformed, and belongs to dynamic data of the object. For example, when the object is a specific user, the behavior data of the object may be data of various behaviors of the user, for example, a user opens a web page and buys a cup; the user acts like sliding a dog in the evening, getting money once in the day, making a yawning, etc. When the user uses the service, various dynamic behavior data on the service can be recorded. For example, when the object is a user, and when the service used by the object is an internet application based on the internet, the behavior data of the user may include at least one of the following: the number of times that the user accesses the internet application within a predetermined time, the duration of stay while the user accesses the internet application, the interval duration of re-accessing the internet application after the user accesses the internet application, the operation performed by the user on the internet application, and the like. For example, when the internet application is a video-type application for interaction, the behavior data of the user may be: the number of times that the user accesses the video application within a predetermined time (one month), the duration of time that the user stays when accessing the video application, the duration of time between when the user accesses the video application and then accesses the video application again, the operation performed by the user on the video application (for example, the operation on a function control on the video application: comment, forwarding, praise, collection, etc. on a video in the video application), and the like. It should be appreciated that the above-described behavior of the user may be implemented by a device to which the user account of the user is logged in, e.g., the user accesses a video-like application multiple times a day through the device to which the user account is logged in.
In the embodiment of the present application, the aforementioned rights information refers to various preferential information provided for a user (i.e., the aforementioned object) in a marketing activity, and is information for motivating the aforementioned target object to trigger a target event. Such as discount information for a certain product to be sold, a coupon or red pack for a product, a gift for purchasing a certain product, etc.; it is understood that the rights information may be a single offer, such as a bonus packet, or a combination of offers, such as a coupon plus a gift.
In this embodiment of the present application, the triggering target event refers to a response to the right information received by the target object (i.e., the user) after receiving the right information; the trigger target event includes but is not limited to purchasing and responding to the marketing activity, which is determined by the marketing content; wherein, the result of the object responding to the received right information can be understood as whether the user is converted, and the conversion result comprises: and (3) transformation and non-transformation, wherein in the specific implementation, 1 is used for transformation, and 0 is used for non-transformation. For example, if a user successfully converts (e.g., purchases and responds to a product associated with a marketing campaign), the conversion result of the user is set to 1, whereas if a user does not convert (e.g., does not purchase and does not respond to a product associated with a marketing campaign), the conversion result of the user is set to 0.
102: and performing equity conversion on the at least one piece of equity information based on an equity conversion rule to obtain at least one equity value corresponding to the at least one piece of equity data.
Wherein, the above-mentioned equity value is the equivalent amount after equity conversion. In some possible cases, the equity information includes information of non-denomination categories, such as discount, gift, lottery, point, and so on. Aiming at the interest information of the non-sum numerical value classes, the embodiment of the application converts the interest information of the non-sum numerical value classes through a preset interest conversion rule, so that the sum numerical value which can be directly used is obtained. For example, the conversion may be performed according to the value of a gift, the conversion may be performed according to the point exchange rule, or the conversion may be performed according to the prize value and the winning probability of a lottery.
103: and inputting the image data into a rights and interests gain model to obtain a sensitive curve of the target object, wherein the sensitive curve is a probability gain curve of the target object for triggering the target event aiming at the at least one piece of rights and interests information.
In this embodiment of the present application, the equity gain model is a model trained in advance, and the specific construction and training process of the model may refer to the implementation manner corresponding to fig. 3, where the equity gain model specifically is:
Uplift＝G(YX,T＝t)-G(YX,T＝0)；
wherein, X is the image data of the object (user); t represents a converted equity value;
g (Y | X, T ═ T) represents the probability that the object triggers the target event when the converted equity value is T (T > 0);
g (Y | X, T ═ 0) represents the probability that the object triggers the target event when the converted equity value is 0(T > 0);
uplift represents the gain probability brought by the rights and interests information to the target object (i.e., the user) triggering the target event.
The sensitive curve is a relation curve between Uplift and the converted right value T. In the embodiment of the present application, the sensitivity curve output by the above equity gain model may be a sensitivity curve corresponding to a single equity information as shown in fig. 6, or may be a sensitivity curve corresponding to a plurality of equity information as shown in fig. 7. It is understood that in fig. 7, claim 1, claim 2 or claim 3 may be a single offer, such as a rebate pack, or a combination of offers, such as a coupon plus a gift.
104: and pushing target right information to the target object based on the sensitivity curve and the at least one right value, wherein the target right information is at least one piece of the at least one piece of right information.
In an optional implementation, the pushing target right information to the target object based on the sensitivity curve and the at least one right value may specifically include: obtaining at least one sensitivity corresponding to the at least one equity value based on the sensitivity curve; selecting a first target equity value corresponding to the sensitivity value larger than a first threshold value from the at least one sensitivity value; and pushing the right information corresponding to the first target right value to the target object.
The first threshold is a preset value, and for example, the first threshold may be 1%.
Further, the pushing of the right information corresponding to the first target right value to the target object may specifically include: acquiring budget information and investment return rate information for triggering the target event; calculating a second target equity value of the first target equity values based on the budget information and the return on investment information, wherein the second target equity value is an equity value triggering the highest return on investment of the target event; and pushing the right information corresponding to the second target right value to the target object.
Further, the calculating a second target equity value of the first target equity values based on the budget information and the return on investment information includes: determining said second threshold based on said budget information and return on investment information; selecting a value of the first target interest value that is less than the second threshold value to obtain the second target interest value.
In the application, the sensitivity curve of the target user to the rights and interests is obtained by inputting the portrait data of the target object (namely the target user) into the rights and interests gain model, and then whether the rights and interests are pushed to the target user is judged based on the sensitivity curve and the converted numerical value of the rights and interests to be pushed. Since the sensitivity curve is a probability gain curve of the target object triggering the target event for the at least one entitlement information. The curve reflects the relationship between the value after the equity conversion and the gain probability; the gain probability is the difference between the probability that the target user triggers the target event after being pushed with the right and the probability that the target user triggers the target event without being pushed with the right. In other words, the sensitivity curve reflects the gain probability that the target user is prompted to trigger the target event after the push right. Therefore, by the scheme of the application, the rights and interests information can be pushed to the user more accurately, and the user is prompted to trigger the target event, for example, the user is prompted to place an order; in addition, in the scheme of the application, the right information is numerically converted according to a preset rule, namely the right is converted into equivalent money, so that the scheme can adapt to various complicated rights pushing in actual situations.
Referring to fig. 2, fig. 2 is a schematic flow chart of another data processing method provided in an embodiment of the present application, and as shown in the figure, the method may include:
201: the method includes acquiring portrait data of a target object and at least one piece of interest information, where the at least one piece of interest information is information for motivating the target object to trigger a target event.
In this embodiment, the portrait data of the object may be data for describing the object, and the portrait data of the object may include various types, for example, at least one of the following types: gender of the subject, age of the subject, occupation of the subject, model of the device used by the subject, operating system of the device used by the subject, price of the device used by the subject, place of residence of the subject, fan count of the subject, status of the subject registering/installing a predetermined application, historical expense amount, historical account transfer, loan amount, and the like.
In one or more optional embodiments, the image data of the object may further include behavior data of the object, and the specific behavior data is data describing a behavior of the object that is continuously transformed, and belongs to dynamic data of the object. For example, when the object is a specific user, the behavior data of the object may be data of various behaviors of the user, for example, a user opens a web page and buys a cup; the user acts like sliding a dog in the evening, getting money once in the day, making a yawning, etc. When the user uses the service, various dynamic behavior data on the service can be recorded. For example, when the object is a user, and when the service used by the object is an internet application based on the internet, the behavior data of the user may include at least one of the following: the number of times that the user accesses the internet application within a predetermined time, the duration of stay while the user accesses the internet application, the interval duration of re-accessing the internet application after the user accesses the internet application, the operation performed by the user on the internet application, and the like. For example, when the internet application is a video-type application for interaction, the behavior data of the user may be: the number of times that the user accesses the video application within a predetermined time (one month), the duration of time that the user stays when accessing the video application, the duration of time between when the user accesses the video application and then accesses the video application again, the operation performed by the user on the video application (for example, the operation on a function control on the video application: comment, forwarding, praise, collection, etc. on a video in the video application), and the like. It should be appreciated that the above-described behavior of the user may be implemented by a device to which the user account of the user is logged in, e.g., the user accesses a video-like application multiple times a day through the device to which the user account is logged in.
In the embodiment of the present application, the aforementioned rights information refers to various preferential information provided for a user (i.e., the aforementioned object) in a marketing activity, and is information for motivating the aforementioned target object to trigger a target event. Such as discount information for a certain product to be sold, a coupon or red pack for a product, a gift for purchasing a certain product, etc.; it is understood that the rights information may be a single offer, such as a bonus packet, or a combination of offers, such as a coupon plus a gift.
In this embodiment of the present application, the triggering target event refers to a response to the right information received by the target object (i.e., the user) after receiving the right information; the trigger target event includes but is not limited to purchasing and responding to the marketing activity, which is determined by the marketing content; wherein, the result of the object responding to the received right information can be understood as whether the user is converted, and the conversion result comprises: and (3) transformation and non-transformation, wherein in the specific implementation, 1 is used for transformation, and 0 is used for non-transformation. For example, if a user successfully converts (e.g., purchases and responds to a product associated with a marketing campaign), the conversion result of the user is set to 1, whereas if a user does not convert (e.g., does not purchase and does not respond to a product associated with a marketing campaign), the conversion result of the user is set to 0.
202: and performing equity conversion on the at least one piece of equity information based on an equity conversion rule to obtain at least one equity value corresponding to the at least one piece of equity data.
Wherein, the above-mentioned equity value is the equivalent amount after equity conversion. In some possible cases, the equity information includes information of non-denomination categories, such as discount, gift, lottery, point, and so on. Aiming at the interest information of the non-sum numerical value classes, the embodiment of the application converts the interest information of the non-sum numerical value classes through a preset interest conversion rule, so that the sum numerical value which can be directly used is obtained. For example, the conversion may be performed according to the value of a gift, the conversion may be performed according to the point exchange rule, or the conversion may be performed according to the prize value and the winning probability of a lottery.
203: and extracting the right and interest characteristic information corresponding to the at least one piece of right and interest information.
In actual marketing, the same user may have different gain probabilities for different scenes or different categories of rights and interests (such as red envelope, discount, coupon, gift, different scenes such as takeout, car-taking, shopping, etc.) with the same converted amount; therefore, in the embodiment of the application, the characteristics of the benefit information are also used as the input of the benefit gain model, so that the obtained sensitivity curve of the target user is more accurate.
The rights and interests feature information includes, but is not limited to, a product or activity type corresponding to the rights and interests information, a scene corresponding to the rights and interests information, time corresponding to the rights and interests information, a platform corresponding to the rights and interests information, and the like.
204: and inputting the image data and the rights characteristic information into the rights gain model to obtain the sensitivity curve of the target object.
In this embodiment of the present application, the equity gain model is a model trained in advance, and the specific construction and training process of the model may refer to the implementation manner corresponding to fig. 3, where the equity gain model specifically is:
Uplift＝G(Y|X,M,n*T＝t)-G(Y|X,M,T＝0)；
wherein, X is the image data of the object (user); t represents a converted equity value, Y represents a trigger target event, M represents equity characteristic information, and n represents a weight value of equity information;
g (Y | X, T ═ T) represents the probability that the object triggers the target event when the converted equity value is T (T > 0);
g (Y | X, T ═ 0) represents the probability that the object triggers the target event when the converted equity value is 0(T > 0);
uplift represents the gain probability brought by the rights and interests information to the target object (i.e., the user) triggering the target event.
In some alternative embodiments, the interest features may be classified, and then, when calculating the sensitivity of the object in the interest gain model, each of the converted interest values is weighted, and the weighted weight depends on the input image data of the object and the feature information of the interest feature information; that is, the value of the weight is determined by the image data of the target object and the interest feature information. For example, in a scenario of clothing marketing, the image data includes gender and age of 40 of the target subject; the equity characteristic information comprises the type of children's clothes; the values of the above weights can be matched to 0 or close to 0. It is to be understood that the above examples are merely illustrative, and in practical cases, the above weight values are matched by a plurality of data in the user portrait data and a plurality of interest characteristic information.
In the embodiment of the application, the rights and interests feature information is introduced into the feature level of the model, so that the sensitivity curve output by the rights and interests gain model is more accurate.
The sensitive curve is a relation curve between Uplift and the converted right value T. In the embodiment of the present application, the sensitivity curve output by the above equity gain model may be a sensitivity curve corresponding to a single equity information as shown in fig. 6, or may be a sensitivity curve corresponding to a plurality of equity information as shown in fig. 7. It is understood that in fig. 7, claim 1, claim 2 or claim 3 may be a single offer, such as a rebate pack, or a combination of offers, such as a coupon plus a gift.
205: and pushing target right information to the target object based on the sensitivity curve and the at least one right value, wherein the target right information is at least one piece of the at least one piece of right information.
In an optional implementation, the pushing target right information to the target object based on the sensitivity curve and the at least one right value may specifically include: obtaining at least one sensitivity corresponding to the at least one equity value based on the sensitivity curve; selecting a first target equity value corresponding to the sensitivity value larger than a first threshold value from the at least one sensitivity value; and pushing the right information corresponding to the first target right value to the target object.
The first threshold is a preset value, and for example, the first threshold may be 1%.
Further, the pushing of the right information corresponding to the first target right value to the target object may specifically include: acquiring budget information and investment return rate information for triggering the target event; calculating a second target equity value of the first target equity values based on the budget information and the return on investment information, wherein the second target equity value is an equity value triggering the highest return on investment of the target event; and pushing the right information corresponding to the second target right value to the target object.
Further, the calculating a second target equity value of the first target equity values based on the budget information and the return on investment information includes: determining said second threshold based on said budget information and return on investment information; selecting a value of the first target interest value that is less than the second threshold value to obtain the second target interest value.
In the application, the sensitivity curve of the target user to the rights and interests is obtained by inputting the portrait data of the target object (namely the target user) into the rights and interests gain model, and then whether the rights and interests are pushed to the target user is judged based on the sensitivity curve and the converted numerical value of the rights and interests to be pushed. Since the sensitivity curve is a probability gain curve of the target object triggering the target event for the at least one entitlement information. The curve reflects the relationship between the value after the equity conversion and the gain probability; the gain probability is the difference between the probability that the target user triggers the target event after being pushed with the right and the probability that the target user triggers the target event without being pushed with the right. In other words, the sensitivity curve reflects the gain probability that the target user is prompted to trigger the target event after the push right. Therefore, by the scheme of the application, the rights and interests information can be pushed to the user more accurately, and the user is prompted to trigger the target event, for example, the user is prompted to place an order; in addition, in the scheme of the application, the right information is numerically converted according to a preset rule, namely the right is converted into equivalent money, so that the scheme can adapt to various complicated rights pushing in actual situations.
Referring to fig. 3, fig. 3 is a schematic flow chart of another equity gain model training method provided in the embodiment of the present application, and as shown in the figure, the method may include:
301: acquiring a training sample and at least one piece of interest information, wherein the training sample comprises a reference group and an experiment group, the reference group comprises portrait data of a first training object and a trigger result of the first training object to the target event, and the experiment group comprises portrait data of a second training object and a trigger result of the second training object to the target event.
In the embodiment of the present application, the information such as the rights information, the image data, the target event, and the like can refer to the embodiment corresponding to fig. 1 or fig. 2, and details are not repeated herein.
The marketing campaign described in the present application may be determined according to the applied business scenario, and the specific content of the marketing campaign is different from the applied business scenario, taking the banking field as an example, the related marketing campaigns are, for example, insurance business, financial product recommendation, online and offline consumption campaigns, and the content of the marketing campaign is not limited.
302: and performing the equity conversion on the at least one piece of equity information based on the equity conversion rule to obtain at least one equity value corresponding to the at least one piece of equity data.
Specifically, refer to the embodiment corresponding to fig. 1 or fig. 2, which is not described herein again.
303: and extracting the right and interest characteristic information corresponding to the at least one piece of right and interest information.
Specifically, refer to the embodiment corresponding to fig. 1 or fig. 2, which is not described herein again.
304: and training by a deep learning method to obtain a benefit gain model by taking the image data of the first training object as input, the trigger result of the first training object to the target event as output, and the image data of the second training object, the at least one benefit value and the benefit characteristic information as input, and the trigger result of the second training object to the target event as output.
Specifically, the rights gain model is as follows: uplift ═ G (Y | X, M, n ═ T) — G (Y | X, M, T ═ 0);
wherein, X is the image data of the object (user); t represents a converted equity value, Y represents a trigger target event, M represents equity characteristic information, and n represents a weight value of equity information;
g (Y | X, T ═ T) represents the probability that the object triggers the target event when the converted equity value is T (T > 0);
g (Y | X, T ═ 0) represents the probability that the object triggers the target event when the converted equity value is 0(T > 0);
uplift represents the gain probability brought by the rights and interests information to the target object (i.e., the user) triggering the target event.
In some alternative embodiments, the interest features may be classified, and then, when calculating the sensitivity of the object in the interest gain model, each of the converted interest values is weighted, and the weighted weight depends on the input image data of the object and the feature information of the interest feature information; that is, the value of the weight is determined by the image data of the target object and the interest feature information. For example, in a scenario of clothing marketing, the image data includes gender and age of 40 of the target subject; the equity characteristic information comprises the type of children's clothes; the values of the above weights can be matched to 0 or close to 0. It is to be understood that the above examples are merely illustrative, and in practical cases, the above weight values are matched by a plurality of data in the user portrait data and a plurality of interest characteristic information.
In the embodiment of the application, the rights and interests feature information is introduced into the feature level of the model, so that the sensitivity curve output by the rights and interests gain model is more accurate.
In some optional embodiments, the training of the equity gain model by the deep learning method may specifically include: establishing an N-layer neural network model, wherein the first N-1 layer adopts a ReLU function, and the last layer adopts a Sigmod activation function; initializing a neural network model; receiving as input the image data of the first training object, receiving as output a trigger result of the first training object for the target event, and receiving as input the image data of the second training object, the at least one equity value, and equity feature information, and receiving as output a trigger result of the second training object for the target event; constructing a loss function (Sigmoid cross) according to the input, the output and the neural network model; optimizing the neural network model according to the loss function; the optimized neural network model is the equity gain model.
In the application, the sensitivity curve of the target user to the rights and interests is obtained by inputting the portrait data of the target object (namely the target user) into the rights and interests gain model, and then whether the rights and interests are pushed to the target user is judged based on the sensitivity curve and the converted numerical value of the rights and interests to be pushed. Since the sensitivity curve is a probability gain curve of the target object triggering the target event for the at least one entitlement information. The curve reflects the relationship between the value after the equity conversion and the gain probability; the gain probability is the difference between the probability that the target user triggers the target event after being pushed with the right and the probability that the target user triggers the target event without being pushed with the right. In other words, the sensitivity curve reflects the gain probability that the target user is prompted to trigger the target event after the push right. Therefore, by the scheme of the application, the rights and interests information can be pushed to the user more accurately, and the user is prompted to trigger the target event, for example, the user is prompted to place an order; in addition, in the scheme of the application, the right information is numerically converted according to a preset rule, namely the right is converted into equivalent money, so that the scheme can adapt to various complicated rights pushing in actual situations.
The embodiment of the present application further provides a data processing apparatus, which is used for executing the unit of any one of the foregoing methods. Specifically, referring to fig. 4, a schematic block diagram of a data processing apparatus according to an embodiment of the present application is provided. The device of the embodiment comprises: an acquisition unit 410, a conversion unit 420, an input unit 430, and a push unit 440; wherein the content of the first and second substances,
the acquiring unit 410 is configured to acquire sample data and application attribute features of a target application, where the sample data includes an object image feature of a sample object and an object behavior feature of the sample object in at least one feature dimension;
a discount unit 420, configured to perform equity discount on the at least one piece of equity information based on an equity discount rule, so as to obtain at least one equity value corresponding to the at least one piece of equity data;
an input unit 430, configured to input the image data into a rights gain model to obtain a sensitivity curve of the target object, where the sensitivity curve is a probability gain curve of the target object for triggering the target event according to the at least one piece of rights information;
a pushing unit 440, configured to push target right information to the target object based on the sensitivity curve and the at least one right value, where the target right information is at least one of the at least one right information.
In the application, the sensitivity curve of the target user to the rights and interests is obtained by inputting the portrait data of the target object (namely the target user) into the rights and interests gain model, and then whether the rights and interests are pushed to the target user is judged based on the sensitivity curve and the converted numerical value of the rights and interests to be pushed. Since the sensitivity curve is a probability gain curve of the target object triggering the target event for the at least one entitlement information. The curve reflects the relationship between the value after the equity conversion and the gain probability; the gain probability is the difference between the probability that the target user triggers the target event after being pushed with the right and the probability that the target user triggers the target event without being pushed with the right. In other words, the sensitivity curve reflects the gain probability that the target user is prompted to trigger the target event after the push right. Therefore, by the scheme of the application, the rights and interests information can be pushed to the user more accurately, and the user is prompted to trigger the target event, for example, the user is prompted to place an order; in addition, in the scheme of the application, the right information is numerically converted according to a preset rule, namely the right is converted into equivalent money, so that the scheme can adapt to various complicated rights pushing in actual situations.
Fig. 5 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application. The video image processing apparatus 500 includes a processor 51, and may further include an input device 52, an output device 53, and a memory 54. The input device 52, the output device 53, the memory 54, and the processor 51 are connected to each other via a bus.
The memory includes, but is not limited to, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a portable read-only memory (CD-ROM), which is used for storing instructions and data.
The input means are for inputting data and/or signals and the output means are for outputting data and/or signals. The output means and the input means may be separate devices or may be an integral device.
The processor may include one or more processors, for example, one or more Central Processing Units (CPUs), and in the case of one CPU, the CPU may be a single-core CPU or a multi-core CPU. The processor may also include one or more special purpose processors, which may include GPUs, FPGAs, etc., for accelerated processing.
The memory is used to store program codes and data of the network device.
The processor is used for calling the program codes and data in the memory and executing the steps in the method embodiment. Specifically, reference may be made to the description of the method embodiment, which is not repeated herein.
It will be appreciated that fig. 5 only shows a simplified design of the motion recognition means. In practical applications, the motion recognition devices may also respectively include other necessary components, including but not limited to any number of input/output devices, processors, controllers, memories, etc., and all motion recognition devices that can implement the embodiments of the present application are within the scope of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the division of the unit is only one logical function division, and other division may be implemented in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. The shown or discussed mutual coupling, direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions according to the embodiments of the present application are wholly or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on or transmitted over a computer-readable storage medium. The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)), or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a read-only memory (ROM), or a Random Access Memory (RAM), or a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape, a magnetic disk, or an optical medium, such as a Digital Versatile Disk (DVD), or a semiconductor medium, such as a Solid State Disk (SSD).
The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A data processing method, characterized in that,
acquiring portrait data and at least one piece of interest information of a target object, wherein the at least one piece of interest information is information for exciting the target object to trigger a target event;
performing equity conversion on the at least one piece of equity information based on an equity conversion rule to obtain at least one equity value corresponding to the at least one piece of equity data;
inputting the image data into a rights and interests gain model to obtain a sensitive curve of the target object, wherein the sensitive curve is a probability gain curve of the target object for triggering the target event aiming at the at least one piece of rights and interests information;
and pushing target interest information to the target object based on the sensitivity curve and the at least one interest value, wherein the target interest information is at least one of the at least one piece of interest information.
2. The data processing method of claim 1, wherein prior to said inputting the image data into a gain model for interest, resulting in a sensitivity curve of the target object, the data processing method further comprises:
extracting the right and interest characteristic information corresponding to the at least one piece of right and interest information;
inputting the image data into a rights gain model to obtain a sensitivity curve of the target object, wherein the method comprises the following steps:
and inputting the portrait data and the rights and interests feature information into the rights and interests gain model to obtain the sensitivity curve of the target object.
3. The data processing method of claim 2, wherein the pushing target entitlement information to the target object based on the sensitivity curve and the at least one entitlement value comprises:
obtaining at least one sensitivity corresponding to the at least one equity value based on the sensitivity curve;
selecting a first target equity value corresponding to the at least one sensitivity value being greater than a first threshold value;
and pushing the right information corresponding to the first target right value to the target object.
4. The data processing method of claim 3, wherein the pushing of the interest information corresponding to the first target interest value to the target object comprises:
acquiring budget information and return on investment rate information for triggering the target event;
calculating a second target equity value in the first target equity values based on budget information and return on investment rate information, wherein the second target equity value is an equity value which triggers the highest return on investment rate of the target event;
and pushing the right information corresponding to the second target right value to the target object.
5. The data processing method of claim 4, wherein said calculating a second one of the first target equity values based on the budget information and the return on investment information comprises:
determining the second threshold based on the budget information and return on investment information;
and selecting the right value smaller than the second threshold value from the first target right values to obtain a second target right value.
6. The data processing method of any of claims 1-5, wherein prior to obtaining the representation data and the at least one piece of interest information for the target object, the data processing method further comprises:
acquiring a training sample and the at least one piece of equity information, wherein the training sample comprises a reference group and an experimental group, the reference group comprises portrait data of a first training object and a trigger result of the first training object to the target event, and the experimental group comprises portrait data of a second training object and a trigger result of the second training object to the target event;
performing equity conversion on the at least one piece of equity information based on the equity conversion rule to obtain at least one equity value corresponding to the at least one piece of equity data;
and taking the portrait data of the first training object as input, taking the triggering result of the first training object to the target event as output, taking the portrait data of the second training object and the at least one interest value as input, taking the triggering result of the second training object to the target event as output, and training by adopting a deep learning method to obtain an interest gain model.
7. The data processing method of claim 6, wherein prior to the training of the gain of interest model using the deep learning method, the data processing method further comprises:
extracting the right and interest characteristic information corresponding to the at least one piece of right and interest information;
in the training of the gain model by deep learning, the step of inputting the image data of the second training object and the at least one gain value comprises:
the second training subject's profile data, the at least one equity value, and equity feature information are input.
8. A data processing apparatus, comprising:
the system comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring sample data and application attribute characteristics of a target application, and the sample data comprises object image characteristics of a sample object and object behavior characteristics of the sample object on at least one characteristic dimension;
the conversion unit is used for carrying out equity conversion on the at least one piece of equity information based on an equity conversion rule to obtain at least one equity value corresponding to the at least one piece of equity data;
the input unit is used for inputting the portrait data into a rights and interests gain model to obtain a sensitive curve of the target object, wherein the sensitive curve is a probability gain curve of the target object for triggering the target event aiming at the at least one piece of rights and interests information;
and the pushing unit is used for pushing target interest information to the target object based on the sensitivity curve and the at least one interest value, wherein the target interest information is at least one of the at least one piece of interest information.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the data processing method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores an executing computer program, which when executed by a processor implements the data processing method of any one of claims 1 to 7.
CN202111017441.9A 2021-08-31 2021-08-31 Data processing method and device, computer equipment and storage medium Pending CN113643072A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111017441.9A CN113643072A (en) 2021-08-31 2021-08-31 Data processing method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111017441.9A CN113643072A (en) 2021-08-31 2021-08-31 Data processing method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113643072A true CN113643072A (en) 2021-11-12

Family

ID=78424818

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111017441.9A Pending CN113643072A (en) 2021-08-31 2021-08-31 Data processing method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113643072A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110675183A (en) * 2019-08-30 2020-01-10 阿里巴巴集团控股有限公司 Marketing object determining method, marketing promotion method and related device
CN110717785A (en) * 2019-09-29 2020-01-21 支付宝(杭州)信息技术有限公司 Decision method, system and device based on label distribution learning
CN111598632A (en) * 2020-07-17 2020-08-28 支付宝(杭州)信息技术有限公司 Method and device for determining equity shares and equity share sequence
CN111784419A (en) * 2020-07-28 2020-10-16 支付宝(杭州)信息技术有限公司 Information pushing method, server, terminal equipment and advertisement system
CN112488893A (en) * 2020-11-30 2021-03-12 泰康保险集团股份有限公司 Service data processing method and device, storage medium and electronic equipment
CN113159870A (en) * 2021-05-21 2021-07-23 口碑(上海)信息技术有限公司 Display method and device of push information and computer equipment

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110675183A (en) * 2019-08-30 2020-01-10 阿里巴巴集团控股有限公司 Marketing object determining method, marketing promotion method and related device
CN110717785A (en) * 2019-09-29 2020-01-21 支付宝(杭州)信息技术有限公司 Decision method, system and device based on label distribution learning
CN111598632A (en) * 2020-07-17 2020-08-28 支付宝(杭州)信息技术有限公司 Method and device for determining equity shares and equity share sequence
CN111784419A (en) * 2020-07-28 2020-10-16 支付宝(杭州)信息技术有限公司 Information pushing method, server, terminal equipment and advertisement system
CN112488893A (en) * 2020-11-30 2021-03-12 泰康保险集团股份有限公司 Service data processing method and device, storage medium and electronic equipment
CN113159870A (en) * 2021-05-21 2021-07-23 口碑(上海)信息技术有限公司 Display method and device of push information and computer equipment

Similar Documents

Publication Publication Date Title
CN109902222B (en) Recommendation method and device
US10956007B2 (en) Electronic device and method for providing search result thereof
CN110162703A (en) Content recommendation method, training method, device, equipment and storage medium
CN111784455A (en) Article recommendation method and recommendation equipment
CN111371767B (en) Malicious account identification method, malicious account identification device, medium and electronic device
CN110737811B (en) Application classification method and device and related equipment
CN116821475B (en) Video recommendation method and device based on client data and computer equipment
CN112819024B (en) Model processing method, user data processing method and device and computer equipment
CN111667024B (en) Content pushing method, device, computer equipment and storage medium
CN115705583A (en) Multi-target prediction method, device, equipment and storage medium
CN115730125A (en) Object identification method and device, computer equipment and storage medium
KR20180049791A (en) Method of filtering a plurality of messages and apparatus thereof
CN105809488B (en) Information processing method and electronic equipment
CN113643072A (en) Data processing method and device, computer equipment and storage medium
CN116151857A (en) Marketing model construction method and device
CN115809889A (en) Intelligent passenger group screening method, system, medium and equipment based on marketing effect
CN116228391A (en) Risk identification method and device, storage medium and electronic equipment
CN115409583A (en) Platform account processing method, system, computer equipment and medium
CN113553501A (en) Method and device for user portrait prediction based on artificial intelligence
JP7139270B2 (en) Estimation device, estimation method and estimation program
CN116109354A (en) Content recommendation method, apparatus, device, storage medium, and computer program product
CN113807920A (en) Artificial intelligence based product recommendation method, device, equipment and storage medium
CN113780318A (en) Method, apparatus, server and medium for generating prompt information
KR20200071477A (en) Electronic apparatus and controlling method thereof
CN111797303A (en) Information processing method, information processing apparatus, storage medium, and electronic device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right

Effective date of registration: 20220607

Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province

Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd.

Address before: Room 12G, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001

Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd.

TA01 Transfer of patent application right