CN111562963A - Personalized display method and device - Google Patents
Personalized display method and device Download PDFInfo
- Publication number
- CN111562963A CN111562963A CN202010369844.9A CN202010369844A CN111562963A CN 111562963 A CN111562963 A CN 111562963A CN 202010369844 A CN202010369844 A CN 202010369844A CN 111562963 A CN111562963 A CN 111562963A
- Authority
- CN
- China
- Prior art keywords
- user
- feature vector
- item
- function
- probability
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000013598 vector Substances 0.000 claims abstract description 96
- 230000006870 function Effects 0.000 claims description 136
- 238000012549 training Methods 0.000 claims description 38
- 238000004364 calculation method Methods 0.000 claims description 36
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 4
- 238000005094 computer simulation Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application provides a personalized display method and device, a feature vector corresponding to a user is generated according to attribute information of the user, the probability that each function item meets the user requirement is calculated according to the feature vector and the incidence relation between the feature vector corresponding to the historical user and the historical user requirement, and the first N function items are displayed in a function item display area of an application program according to the sequence from high to low of the probability of each function item. Because the attribute information comprises user identity information of the user and/or record information generated by the user using each function item of the application program in a preset time period and because the feature vector corresponding to the historical user has an incidence relation with the historical user requirement, the target function item calculated according to the feature vector and the incidence relation between the feature vector corresponding to the historical user and the historical user requirement conforms to the requirement of the user to a great extent, and the purpose of displaying the function item personalized to the user is achieved.
Description
Technical Field
The present application relates to the field of electronic information, and in particular, to a method and an apparatus for personalized display.
Background
With the development of science and technology, software technology is widely applied in various industries, for example, application programs are widely used in intelligent terminals.
At present, the sequencing positions of the function icons included in many application programs are usually set according to research on the market by business personnel, and the actual requirements of a user cannot be reflected, so that the user may need to perform a searching step to find the required function icon when using the application program, and the process may spend most of the time of the user, thereby reducing the user experience. Therefore, how to recommend the function icon meeting the user requirement for the user becomes a problem to be solved urgently.
Disclosure of Invention
In order to achieve the above object, the present application provides the following technical solutions:
a method of personalized display, comprising:
under the condition of receiving an instruction of a user for logging in an application program, generating a feature vector corresponding to the user according to the attribute information of the user; the attribute information comprises user identity information of the user and/or record information generated by the user by using each function item of the application program within a preset time period;
calculating the probability that each function item meets the user requirement according to the feature vector and the incidence relation between the feature vector corresponding to the historical user and the historical user requirement;
and according to the sequence of the probability of each function item from high to low, selecting the first N function items as target function items of the user, and displaying the target function items in a function item display area of the application program, wherein N is an integer.
Optionally, in the method, the generating a feature vector corresponding to the user according to the attribute information of the user includes:
extracting a plurality of target attribute items from the attribute information, wherein any one target attribute item is a verified information item which can be used for calculating the probability of the function item;
for each target attribute item, converting the target attribute item into a corresponding numerical value according to a preset conversion relation between the target attribute item and the numerical value;
and taking the numerical value corresponding to each target attribute item as an element of the feature vector.
Optionally, in the method, before generating the feature vector corresponding to the user according to the attribute information of the user, the method further includes acquiring the attribute information of the user, which is stored in advance and corresponds to the user identity, according to the user identity of the user, which is carried in the instruction for the user to log in the application program.
Optionally, in the method, the calculating, according to the feature vector and the association relationship between the feature vector corresponding to the historical user and the historical user requirement, the probability that each of the function items meets the user requirement includes:
inputting the feature vectors into a preset calculation model, and enabling the calculation model to output the probability that each function item meets the user requirement according to the feature vectors; the calculation model is obtained by training according to the incidence relation between the feature vector corresponding to the historical user and the historical user requirement;
training the calculation model by adopting a training sample to train a preset basic model until the basic model reaches a preset condition, and taking the basic model reaching the preset condition as the calculation model;
the training sample comprises the attribute information of the historical user and pre-recorded function items of the actual requirements of the historical user; the training error is an error between a function item which is recorded in advance and actually required by the historical user and a function item which is output by the basic model and meets the requirements of the historical user.
Optionally, the method further includes, after the function item display area of the application program displays the target function item:
recording the number of targets, wherein the number of targets is the number of functional items clicked by the user but not belonging to the target functional items;
determining the preset corresponding correct probability of the target quantity; the correct probability is the probability representing that the target function item meets the user requirement;
and correspondingly storing the identity code of the user and the correct probability.
An apparatus for personalized display, comprising:
the generating unit is used for generating a feature vector corresponding to a user according to the attribute information of the user under the condition of receiving an instruction of the user for logging in an application program; the attribute information comprises user identity information of the user and/or record information generated by the user by using each function item of the application program within a preset time period;
the calculating unit is used for calculating the probability that each function item meets the user requirement according to the feature vector and the incidence relation between the feature vector corresponding to the historical user and the historical user requirement;
and the display unit is used for selecting the first N function items as target function items of the user according to the sequence of the probability of each function item from high to low, and displaying the target function items in a function item display area of the application program, wherein N is an integer.
Optionally, in the apparatus above, the generating unit is configured to generate a feature vector corresponding to the user according to attribute information of the user, and includes:
the generating unit is specifically configured to extract a plurality of target attribute items from the attribute information, where any one of the target attribute items is a verified information item that can be used to calculate the probability of the function item;
for each target attribute item, converting the target attribute item into a corresponding numerical value according to a preset conversion relation between the target attribute item and the numerical value;
and taking the numerical value corresponding to each target attribute item as an element of the feature vector.
Optionally, in the above apparatus, the calculating unit is configured to calculate, according to the feature vector and an association relationship between the feature vector corresponding to the historical user and the historical user requirement, a probability that each of the function items meets the user requirement, including,
the computing unit is specifically configured to input the feature vector into a preset computing model, so that the computing model outputs, according to the feature vector, a probability that each of the function items meets the user requirement; the calculation model is obtained by training according to the incidence relation between the feature vector corresponding to the historical user and the historical user requirement.
An electronic device, comprising: a processor and a memory for storing a program; the processor is used for running the program to realize the personalized display method.
A computer-readable storage medium having stored therein instructions which, when run on a computer, cause the computer to perform the above-described method of personalizing a presentation.
According to the method and the device provided by the embodiment of the application, the feature vector corresponding to the user is generated according to the attribute information of the user, the probability that each function item meets the user requirement is obtained through calculation according to the feature vector and the incidence relation between the feature vector corresponding to the historical user and the historical user requirement, the first N function items are selected as target function items according to the sequence from high to low of the probability of each function item, and finally the target function items are displayed in the function item display area of the application program. Because the attribute information comprises user identity information of the user and/or record information generated by each function item of the application program used by the user in a preset time period, a feature vector obtained according to the attribute information of the user has strong relevance with the attribute information of the user, and because the feature vector corresponding to the historical user has relevance with the historical user requirements, a target function item calculated according to the feature vector and the relevance between the feature vector corresponding to the historical user and the historical user requirements meets the requirements of the user to a great extent, so that the purpose of displaying the function item personalized to the user is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a method for personalized display disclosed in an embodiment of the present application;
FIG. 2 is a flow chart of a method of generating a computational model as disclosed in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a personalized display apparatus disclosed in the embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device disclosed in an embodiment 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 only a part of the embodiments of the present application, and not all of the embodiments. 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.
Fig. 1 is a method for personalized display provided in the present application, and the method may include the following steps:
s101, under the condition that an instruction of a user for logging in an application program is received, a feature vector corresponding to the user is generated according to attribute information of the user.
In this embodiment, after the user performs login operation on the login interface of the application program, the login interface may be triggered to send an instruction of the user to log in the application program to the background server corresponding to the application program, where the instruction may carry an unique identity code of the user.
For a user who uses the application program for the first time, the attribute information of the user is user identity information of the user, and for the user who has used the application program, the attribute information of the user may be record information generated by the user using each function item of the application program within a preset time period, or user identity information of the user and record information generated by the user using each function item of the application program within the preset time period.
In this embodiment, for different application programs, attribute information of a user is different, for example, a mobile banking application program, user identity information may be information of the user's age, sex, occupation, marriage, asset condition, and the like, and the user identity information may be obtained by personal information that is filled in by the user when the user registers the application program, or by storing the personal information that is filled in by the user when a service organization corresponding to the application program handles a business. The record information generated by the user using each function item of the application program in the preset time period may be a browsing record or a transaction record generated by the user using a certain function item.
In this embodiment, the attribute information of the user, which corresponds to the user identity, may be obtained according to the unique user identity carried in the instruction of the user to log in the application program.
The feature vector corresponding to the user is a vector that can represent the attribute information of the user, and the specific implementation of generating the feature vector corresponding to the user according to the attribute information of the user may include steps a 1-A3:
step a1, extracting a plurality of target attribute items from the attribute information of the user.
The target attribute item is an information item which is screened from a plurality of items of attribute information of the user in the process of training the calculation model and can accurately calculate the functional item meeting the user requirement, namely, any one target attribute item is a verified information item which can be used for calculating the probability that the functional item meets the user requirement.
The condition that the target attribute item is the information item capable of accurately calculating the function item meeting the user requirement is judged, after the target attribute item is converted into the feature vector and is input into the preset calculation model, in the probability that each function item output by the calculation model meets the user requirement, the function items corresponding to the first N maximum probabilities comprise the function items meeting the actual requirement of the user. The calculation model is a model for calculating the probability that each function item in the application program meets the requirements of the user.
For example, the verified information items which can be used for calculating the probability that the function item meets the requirement of the user comprise the age, occupation and income of the user, and then information representing the age, occupation and income of the user is extracted from the attribute information of the user.
And A2, converting the target attribute items into corresponding numerical values according to the conversion relation between the preset target attribute items and the numerical values aiming at each target attribute item.
The conversion relation between the target attribute item and the numerical value is pre-stored in the background server, and different numerical values can be obtained through conversion according to different content information of the target attribute item. In this step, the information included in the target attribute item belongs to language text information, and the implementation manner of converting the language text information into a numerical value can refer to the prior art.
And step A3, taking the numerical value corresponding to each target attribute item as the element of the feature vector.
The specific implementation manner of this step may be: and according to the preset sequencing position of the numerical value corresponding to each target attribute item in the feature vector, carrying out position sequence arrangement on the numerical value corresponding to each target attribute item, and using each numerical value after the arrangement as an element of the feature vector, thereby obtaining the feature vector.
S102, calculating the probability that each function item meets the user requirement according to the feature vector and the incidence relation between the feature vector corresponding to the historical user and the historical user requirement.
The specific implementation manner of the step is as follows: and inputting the feature vectors into a pre-constructed calculation model, so that the calculation model outputs the probability that each function item meets the requirements of the user according to the feature vectors.
The calculation model is obtained by training according to the incidence relation between the feature vector corresponding to the historical user and the historical user requirement; the trained calculation model is a model capable of calculating the probability that each function item in the application program meets the user requirement according to the input feature vector, and the specific process of training to obtain the calculation model can refer to fig. 2, which is not described herein again.
S103, according to the sequence of the probability of each function item from high to low, selecting the first N function items as target function items of the user, and displaying the target function items in a function item display area of the application program.
The probability of the function item is the probability that the representation function item meets the requirements of the user, so that the former N function items with higher probability are selected as target function items, and the target function items are displayed in the function item display area, so that the user can conveniently find the function items meeting the requirements of the user after opening the application program. Wherein N is an integer, and the specific numerical value of N can be set by self.
According to the method provided by the embodiment, the feature vector corresponding to the user is generated according to the attribute information of the user, the probability that each function item meets the user requirement is calculated according to the feature vector and the incidence relation between the feature vector corresponding to the historical user and the historical user requirement, the first N function items are selected as the target function items according to the sequence from high to low of the probability of each function item, and finally the target function items are displayed in the function item display area of the application program. Because the attribute information comprises user identity information of the user and/or record information generated by each function item of the application program used by the user in a preset time period, a feature vector obtained according to the attribute information of the user has strong relevance with the attribute information of the user, and because the feature vector corresponding to the historical user has relevance with the historical user requirements, a target function item calculated according to the feature vector and the relevance between the feature vector corresponding to the historical user and the historical user requirements meets the requirements of the user to a great extent, so that the purpose of displaying the function item personalized to the user is achieved.
Fig. 2 is a method for generating a computational model according to an embodiment of the present application, which may include the following steps:
s201, obtaining a training sample.
In this step, each training sample includes attribute information of the historical user and a function item of the actual requirement of the historical user, which is recorded in advance. The label marked manually is divided into three types, namely a static label, a dynamic label and a user real demand label, wherein the static label is used for marking user identity information of the historical user, the dynamic label is used for marking recording information generated by using each function item of an application program in a preset time period of the historical user, and the user real demand label is used for marking the function item actually required by the historical user. The functional items actually required by the user can be obtained according to the recorded data of the functional items of the historical user using the application program. The carried labels can be used for conveniently converting various information of the training samples into numerical values according to the labels so as to obtain the feature vectors corresponding to the training samples, and the specific conversion method can refer to the prior art.
And S202, building a basic model.
The basic model can be selected from one or more common neural network models according to actual requirements, for example, the basic model can be obtained by one or more common DNN, RNN, LSTM and CNN.
S203, training the basic model by adopting the training samples until the basic model reaches the preset condition, and taking the basic model reaching the preset condition as a calculation model.
The preset condition is that the training error of the basic model is smaller than a threshold value, and the training error is the error between the function item which is recorded in advance and actually required by the historical user and the function item which is output by the basic model and meets the requirements of the historical user. Of course, the preset condition may be that the number of calculation iteration steps of the basic model is greater than a preset value. The process of training the basic model by using the training samples in this step can refer to the prior art.
According to the technical scheme, the training sample comprises the attribute information of the historical user and the function items of the pre-recorded actual requirements of the historical user, and the preset condition is that the error between the function items of the pre-recorded actual requirements of the historical user and the function items which are output by the basic model and meet the requirements of the historical user is smaller than a threshold value, so that the calculation model obtained by training is completed, and the target function items can be accurately obtained according to the input feature vector representing the attribute information of the user.
Referring to fig. 3, a schematic structural diagram of an apparatus 300 for personalized display provided in an embodiment of the present application is shown, including:
a generating unit 301, configured to generate a feature vector corresponding to a user according to attribute information of the user when an instruction for the user to log in an application program is received; the attribute information includes user identity information of the user and/or record information generated by the user using each function item of the application program within a preset time period.
The calculating unit 302 is configured to calculate, according to the feature vector and the association relationship between the feature vector corresponding to the historical user and the historical user requirement, a probability that each function item meets the user requirement.
The display unit 303 is configured to select the first N function items as target function items of the user according to a sequence of probabilities of the function items from high to low, and display the target function items in a function item display area of the application program, where N is an integer.
The apparatus 300 optionally further includes an obtaining unit 304, configured to obtain pre-stored attribute information of the user corresponding to the user identity according to the user identity carried in the instruction of the user to log in the application.
The apparatus 300, optionally, further includes a recording unit 305, configured to record a target number, where the target number is a number of function items clicked by the user and does not belong to the target function item; determining correct grade information corresponding to target quantity presetting; and correspondingly storing the identity identification code and the correct grade information of the user.
The specific implementation manner of generating the feature vector corresponding to the user by the generating unit 302 according to the attribute information of the user is as follows: extracting a plurality of target attribute items from the attribute information, wherein any one target attribute item is a verified information item which can be used for calculating the probability of the function item; for each target attribute item, converting the target attribute item into a corresponding numerical value according to a preset conversion relation between the target attribute item and the numerical value; and taking the numerical value corresponding to each target attribute item as an element of the feature vector.
The specific implementation manner of calculating the probability that each function item meets the user requirement according to the feature vector and the association relationship between the feature vector corresponding to the historical user and the historical user requirement by the calculating unit 302 is as follows: and inputting the feature vectors into a preset calculation model, so that the calculation model outputs the probability that each function item meets the user requirement according to the feature vectors, and the calculation model is obtained by training according to the incidence relation between the feature vectors corresponding to the historical users and the historical user requirements.
The calculation unit 302 is further configured to obtain a calculation model through training, in which a process of training the calculation model is to train a preset basic model by using a training sample until the basic model reaches a preset condition, and use the basic model reaching the preset condition as the calculation model;
the training sample comprises the attribute information of the historical user and a function item of the actual requirement of the historical user which is recorded in advance; the training error is the error between the function item which is recorded in advance and actually required by the historical user and the function item which is output by the basic model and meets the requirements of the historical user.
The device provided by this embodiment generates a feature vector corresponding to a user according to attribute information of the user, calculates a probability that each function item meets a user requirement according to the feature vector and an association relationship between the feature vector corresponding to a historical user and a historical user requirement, sorts the first N function items according to a high-to-low order of the probability of each function item, selects the first N function items as target function items, and finally displays the target function items in a function item display area of an application program. Because the attribute information comprises user identity information of the user and/or record information generated by each function item of the application program used by the user in a preset time period, a feature vector obtained according to the attribute information of the user has strong relevance with the attribute information of the user, and because the feature vector corresponding to the historical user has relevance with the historical user requirements, a target function item calculated according to the feature vector and the relevance between the feature vector corresponding to the historical user and the historical user requirements meets the requirements of the user to a great extent, so that the purpose of displaying the function item personalized to the user is achieved.
Fig. 4 is a schematic structural diagram of an electronic device 400 according to an embodiment of the present application, including: a processor 401 and a memory 402, the memory 402 is used for storing the application program, and the processor 401 is used for executing the application program to realize the personalized showing method.
The computer-readable storage medium provided in the embodiments of the present application stores instructions, and when the instructions are executed on a computer, the computer is enabled to execute the above personalized display method.
The functions described in the method of the embodiment of the present application, if implemented in the form of software functional units and sold or used as independent products, may be stored in a storage medium readable by a computing device. Based on such understanding, part of the contribution to the prior art of the embodiments of the present application or part of the technical solution may be embodied in the form of a software product stored in a storage medium and including several instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of personalized display, comprising:
under the condition of receiving an instruction of a user for logging in an application program, generating a feature vector corresponding to the user according to the attribute information of the user; the attribute information comprises user identity information of the user and/or record information generated by the user by using each function item of the application program within a preset time period;
calculating the probability that each function item meets the user requirement according to the feature vector and the incidence relation between the feature vector corresponding to the historical user and the historical user requirement;
and according to the sequence of the probability of each function item from high to low, selecting the first N function items as target function items of the user, and displaying the target function items in a function item display area of the application program, wherein N is an integer.
2. The method according to claim 1, wherein the generating the feature vector corresponding to the user according to the attribute information of the user comprises:
extracting a plurality of target attribute items from the attribute information, wherein any one target attribute item is a verified information item which can be used for calculating the probability of the function item;
for each target attribute item, converting the target attribute item into a corresponding numerical value according to a preset conversion relation between the target attribute item and the numerical value;
and taking the numerical value corresponding to each target attribute item as an element of the feature vector.
3. The method according to claim 1 or 2, wherein before generating the feature vector corresponding to the user according to the attribute information of the user, the method further includes, according to a user identity of the user carried in an instruction for the user to log in the application program, acquiring the attribute information of the user, which is stored in advance and corresponds to the user identity.
4. The method according to claim 1, wherein the calculating, according to the feature vector and the association relationship between the feature vector corresponding to the historical user and the historical user requirement, a probability that each of the function items meets the user requirement includes:
inputting the feature vectors into a preset calculation model, and enabling the calculation model to output the probability that each function item meets the user requirement according to the feature vectors; the calculation model is obtained by training according to the incidence relation between the feature vector corresponding to the historical user and the historical user requirement;
training the calculation model by adopting a training sample to train a preset basic model until the basic model reaches a preset condition, and taking the basic model reaching the preset condition as the calculation model;
the training sample comprises the attribute information of the historical user and pre-recorded function items of the actual requirements of the historical user; the training error is an error between a function item which is recorded in advance and actually required by the historical user and a function item which is output by the basic model and meets the requirements of the historical user.
5. The method of claim 1, further comprising, after the target function item is exposed in the function item exposure area of the application program:
recording the number of targets, wherein the number of targets is the number of functional items clicked by the user but not belonging to the target functional items;
determining the preset corresponding correct probability of the target quantity; the correct probability is the probability representing that the target function item meets the user requirement;
and correspondingly storing the identity code of the user and the correct probability.
6. An apparatus for personalized display, comprising:
the generating unit is used for generating a feature vector corresponding to a user according to the attribute information of the user under the condition of receiving an instruction of the user for logging in an application program; the attribute information comprises user identity information of the user and/or record information generated by the user by using each function item of the application program within a preset time period;
the calculating unit is used for calculating the probability that each function item meets the user requirement according to the feature vector and the incidence relation between the feature vector corresponding to the historical user and the historical user requirement;
and the display unit is used for selecting the first N function items as target function items of the user according to the sequence of the probability of each function item from high to low, and displaying the target function items in a function item display area of the application program, wherein N is an integer.
7. The apparatus according to claim 6, wherein the generating unit is configured to generate the feature vector corresponding to the user according to attribute information of the user, and includes:
the generating unit is specifically configured to extract a plurality of target attribute items from the attribute information, where any one of the target attribute items is a verified information item that can be used to calculate the probability of the function item;
for each target attribute item, converting the target attribute item into a corresponding numerical value according to a preset conversion relation between the target attribute item and the numerical value;
and taking the numerical value corresponding to each target attribute item as an element of the feature vector.
8. The apparatus according to claim 6, wherein the calculating unit is configured to calculate a probability that each of the function items meets the user requirement according to the feature vector and an association relationship between a feature vector corresponding to a historical user and the historical user requirement, including,
the computing unit is specifically configured to input the feature vector into a preset computing model, so that the computing model outputs, according to the feature vector, a probability that each of the function items meets the user requirement; the calculation model is obtained by training according to the incidence relation between the feature vector corresponding to the historical user and the historical user requirement;
the calculation unit is further used for obtaining the calculation model through training, and the process of training the calculation model is to train a preset basic model by using a training sample until the basic model reaches a preset condition, and take the basic model reaching the preset condition as the calculation model;
the training sample comprises the attribute information of the historical user and pre-recorded function items of the actual requirements of the historical user; the training error is an error between a function item which is recorded in advance and actually required by the historical user and a function item which is output by the basic model and meets the requirements of the historical user.
9. An electronic device, comprising: a processor and a memory for storing a program; the processor is used for running the program to realize the personalized display method of any one of claims 1 to 5.
10. A computer-readable storage medium having stored therein instructions which, when run on a computer, cause the computer to perform the method of personalizing a presentation according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010369844.9A CN111562963A (en) | 2020-04-30 | 2020-04-30 | Personalized display method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010369844.9A CN111562963A (en) | 2020-04-30 | 2020-04-30 | Personalized display method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111562963A true CN111562963A (en) | 2020-08-21 |
Family
ID=72070760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010369844.9A Pending CN111562963A (en) | 2020-04-30 | 2020-04-30 | Personalized display method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111562963A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280104A (en) * | 2017-02-13 | 2018-07-13 | 腾讯科技（深圳）有限公司 | The characteristics information extraction method and device of target object |
| CN110377829A (en) * | 2019-07-24 | 2019-10-25 | 中国工商银行股份有限公司 | Function recommended method and device applied to electronic equipment |
-
2020
- 2020-04-30 CN CN202010369844.9A patent/CN111562963A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280104A (en) * | 2017-02-13 | 2018-07-13 | 腾讯科技（深圳）有限公司 | The characteristics information extraction method and device of target object |
| CN110377829A (en) * | 2019-07-24 | 2019-10-25 | 中国工商银行股份有限公司 | Function recommended method and device applied to electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107798571B (en) | Malice address/malice order identifying system, method and device | |
| CN110427560B (en) | Model training method applied to recommendation system and related device | |
| EP3617952A1 (en) | Information search method, apparatus and system | |
| CN110827112B (en) | Deep learning commodity recommendation method and device, computer equipment and storage medium | |
| CN110347786B (en) | Semantic model tuning method and system | |
| CN116821475B (en) | Video recommendation method and device based on client data and computer equipment | |
| CN113190702A (en) | Method and apparatus for generating information | |
| CN115147130A (en) | Problem prediction method, apparatus, storage medium, and program product | |
| CN113781149A (en) | Information recommendation method and device, computer-readable storage medium and electronic equipment | |
| CN111680213B (en) | Information recommendation method, data processing method and device | |
| CN115345669A (en) | Method and device for generating file, storage medium and computer equipment | |
| CN117132326A (en) | Advertisement pushing method and device, electronic equipment and storage medium | |
| CN111768218B (en) | Method and device for processing user interaction information | |
| CN112100491A (en) | Information recommendation method, device and equipment based on user data and storage medium | |
| CN116703515A (en) | Recommendation method and device based on artificial intelligence, computer equipment and storage medium | |
| CN111562963A (en) | Personalized display method and device | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN111325614B (en) | Recommendation method and device of electronic object and electronic equipment | |
| CN111538905B (en) | Object recommendation method and device | |
| CN110837596B (en) | Intelligent recommendation method and device, computer equipment and storage medium | |
| CN113743982A (en) | Advertisement putting scheme recommendation method and device, computer equipment and storage medium | |
| CN110334177B (en) | Semantic similarity model training and semantic similarity recognition methods and devices and electronic equipment | |
| CN112989020A (en) | Information processing method, apparatus and computer readable storage medium | |
| CN111369315A (en) | Resource object recommendation method and device, and data prediction model training method and device | |
| CN111695922A (en) | Potential user determination method and device, storage medium and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200821 |
|
| RJ01 | Rejection of invention patent application after publication |