CN111859117A

CN111859117A - Information recommendation method and device, electronic equipment and readable storage medium

Info

Publication number: CN111859117A
Application number: CN202010567968.8A
Authority: CN
Inventors: 赵琳琳
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-06-19
Filing date: 2020-06-19
Publication date: 2020-10-30
Anticipated expiration: 2040-06-19
Also published as: CN111859117B

Abstract

The application relates to the technical field of internet, and discloses an information recommendation method, an information recommendation device, electronic equipment and a readable storage medium, wherein the information recommendation method comprises the following steps: respectively acquiring terminal use records of a plurality of users; the terminal usage record comprises the usage time of a plurality of application programs of each user for the user terminal and the type of the application program correspondingly used; determining a fuzzy relation among a plurality of users based on terminal use records of the plurality of users; classifying a plurality of users based on the fuzzy relation to obtain a classification result; and sending recommendation information to the user terminals of the plurality of users based on the classification result. The information recommendation method provided by the application can improve the classification accuracy, so that appropriate information can be recommended to corresponding users in an appropriate time period, and accurate recommendation is achieved.

Description

Information recommendation method and device, electronic equipment and readable storage medium

Technical Field

The application relates to the technical field of internet, in particular to an information recommendation method and device, an electronic device and a readable storage medium.

Background

With the development of internet technology, the personalized demand of users is further improved, and the users can be classified, so that recommendation information is sent to the users in a personalized manner, for example, the users are classified, and office workers who face nine-night-five recommend midday tea, and night-.

Currently, a preset condition is usually defined directly, and users are classified according to whether the users meet the preset condition, for example, a person who sleeps five days a week and a night is defined as a group who stays late often, and the person who sleeps four days later is excluded, so that the classification mode cannot accurately describe slight differences in the user behavior level, the classification result is inaccurate, and the time and the content of information recommended to the users may not meet the user requirements.

Disclosure of Invention

The purpose of the present application is to solve at least one of the above technical drawbacks, and to provide the following solutions:

in a first aspect, an information recommendation method is provided, including:

respectively acquiring terminal use records of a plurality of users; the terminal usage record comprises the usage time of a plurality of application programs of the user terminal and the type of the corresponding application program used by each user;

determining a fuzzy relation among a plurality of users based on terminal use records of the plurality of users;

Classifying the plurality of users based on the fuzzy relation to obtain a classification result;

and sending recommendation information to the user terminals of the plurality of users based on the classification result.

In an optional embodiment of the first aspect, determining the ambiguous relationship between the plurality of users based on the terminal usage records of the plurality of users comprises:

for any user, determining active frequency distribution data of the user in a preset period based on the terminal use record of the user;

determining fuzzy relations among the plurality of users based on the activity number distribution data of the plurality of users.

In an optional embodiment of the first aspect, the active number distribution data includes a cumulative active number of the user terminal for each preset time period in a preset period;

for any user, determining the distribution data of the active times of the user in a preset period based on the terminal usage record of the user, wherein the data comprises the following steps:

for any user, determining the number of active times of the user in each preset time period of each sub-period in a preset period based on the terminal usage record of the user;

and determining the accumulated active times of the user in each preset time period in the preset period based on the active times of the user in each preset time period in each sub-period in the preset period.

In an optional embodiment of the first aspect, determining, for any user, active number distribution data of the user in a preset period based on a terminal usage record of the user includes:

for any user, determining initial active time distribution data of the user in a preset period based on a terminal use record of the user;

and carrying out signal denoising on the initial active time distribution data of the user to obtain the active time distribution data of the user.

In an optional embodiment of the first aspect, performing signal denoising on the initial active time distribution data of the user to obtain the active time distribution data of the user includes:

determining the median of each active number value in a preset neighborhood of the active number value according to any active number value in the initial active number distribution data of the user;

replacing the number of active times with the determined median;

and acquiring active number distribution data based on the active number values after the replacement.

In an optional embodiment of the first aspect, the fuzzy relation comprises a similarity fuzzy relation matrix;

determining fuzzy relationships between the plurality of users based on the activity number distribution data of the plurality of users, including:

Generating an activity fuzzy set based on activity number distribution data of a plurality of user terminals;

and determining a similarity fuzzy relation matrix based on a predefined fuzzy similarity relation between any two activity times distribution data and the activity fuzzy set.

In an optional embodiment of the first aspect, classifying the plurality of users based on the fuzzy relation to obtain a classification result includes:

acquiring a cut matrix of the similarity fuzzy relation matrix;

classification results for a plurality of users are determined based on the truncation matrix.

In an optional embodiment of the first aspect, obtaining a cut matrix of the similarity ambiguity relationship matrix comprises:

determining a range of the number of categories corresponding to the classification result;

determining a threshold value of the truncation matrix based on the range of the number of categories;

and acquiring a truncation matrix of the similarity fuzzy relation matrix corresponding to the threshold.

In an optional embodiment of the first aspect, determining classification results for the plurality of users based on the truncation matrix comprises:

if the cut matrix is an equivalent matrix, determining a classification result based on the cut matrix;

and if the intercept matrix is not the equivalent matrix, adjusting the intercept matrix until the adjusted intercept matrix is the equivalent matrix, and determining a classification result based on the adjusted intercept matrix.

In an optional embodiment of the first aspect, the sending recommendation information to user terminals of a plurality of users based on the classification result comprises:

determining at least one sample user corresponding to each category based on the classification result;

aiming at any sample user, acquiring an information pushing time period of the sample user;

determining recommendation information corresponding to the information push time period;

and sending recommendation information to the users with the same category as the sample user in the information pushing time period.

In a second aspect, an information recommendation apparatus is provided, including:

the acquisition module is used for respectively acquiring terminal use records of a plurality of users; the terminal usage record comprises the usage time of a plurality of application programs of the user terminal and the type of the corresponding application program used by each user;

the determining module is used for determining fuzzy relations among a plurality of users based on the terminal use records of the users;

the classification module is used for classifying a plurality of users based on the fuzzy relation to obtain a classification result;

and the sending module is used for sending the recommendation information to the user terminals of the plurality of users based on the classification result.

In an optional embodiment of the second aspect, the determining module, when determining the fuzzy relationship between the multiple users based on the terminal usage records of the multiple users, is specifically configured to:

In an optional embodiment of the second aspect, the active number distribution data includes a cumulative active number of the user terminal for each preset time period in a preset period;

the determining module is specifically configured to, when determining, for any user, active number distribution data of the user in a preset period based on a terminal usage record of the user:

In an optional embodiment of the second aspect, for any user, when determining, for any user, the active number distribution data of the user in the preset period based on the terminal usage record of the user, the determining module is specifically configured to:

In an optional embodiment of the second aspect, when the determining module performs signal denoising on the initial active time distribution data of the user to obtain the active time distribution data of the user, the determining module is specifically configured to:

replacing the number of active times with the determined median;

In an alternative embodiment of the second aspect, the fuzzy relation comprises a similarity fuzzy relation matrix;

the determining module, when determining the fuzzy relationship between the multiple users based on the active number distribution data of the multiple users, is specifically configured to:

In an optional embodiment of the second aspect, the classification module is specifically configured to, when classifying the plurality of users based on the fuzzy relationship and obtaining a classification result:

acquiring a cut matrix of the similarity fuzzy relation matrix;

In an optional embodiment of the second aspect, when obtaining the cut matrix of the similarity fuzzy relation matrix, the classification module is specifically configured to:

In an optional embodiment of the second aspect, the classification module, when determining the classification results for the plurality of users based on the truncation matrix, is specifically configured to:

In an optional embodiment of the second aspect, when sending recommendation information to user terminals of multiple users based on the classification result, the sending module is specifically configured to:

In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the information recommendation method shown in the first aspect of the present application is implemented.

In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the information recommendation method shown in the first aspect of the present application.

In a fifth aspect, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium; the processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to make the computer device execute the information recommendation method shown in the first aspect.

The beneficial effect that technical scheme that this application provided brought is:

the fuzzy relation among the users is determined through the terminal use records of the users, the users are classified based on the fuzzy relation to obtain the classification result, and then the recommendation information corresponding to the classification result is sent.

Further, when abnormal data interference may occur in the sub-period, the accumulated active times of the user in each preset time period in the preset period are obtained by correspondingly overlapping the active times of the user in each preset time period in each sub-period in the preset period, so that the influence of the abnormal interference data in the sub-period can be reduced, the classification accuracy is improved, and the information recommendation accuracy is improved.

Furthermore, for the accumulated active times of the user in each preset time period in the preset period, the value of one point in the distribution of the accumulated active times is replaced by the median of each point in the neighborhood of the point through median filtering, so that the influence of voice point data and abnormal values of the behavior of the user can be further removed, and the accuracy of information recommendation is improved.

Furthermore, different threshold values are set for different classification quantities, so that a plurality of users are classified based on the truncation matrix of the similarity fuzzy relation matrix, and different classification quantities can be applied to recommendation scenes of different recommendation information.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is an application environment diagram of an information recommendation method according to an embodiment of the present application;

fig. 2 is a schematic flowchart of an information recommendation method according to an embodiment of the present application;

fig. 3 is a schematic flowchart of an information recommendation method according to an embodiment of the present application;

FIG. 4 is a schematic illustration of liveness number distribution data provided in an example of the present application;

FIG. 5 is a schematic diagram of a scheme for denoising liveness number distribution data according to an example of the present application;

FIG. 6 is a schematic illustration of liveness number distribution data provided in an example of the present application;

FIG. 7 is a schematic diagram illustrating a determination of a similarity fuzzy relationship matrix based on liveness number distribution data according to an example of the present application;

FIG. 8 is a schematic diagram of a scheme for classification based on activity distribution data according to an embodiment of the present application;

fig. 9 is a flowchart illustrating an information recommendation method in an example provided in the present application;

fig. 10 is a schematic structural diagram of an information recommendation device according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of an electronic device for information recommendation according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, 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 will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

Machine Learning (ML) is a multi-domain cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and formal education learning.

With the research and progress of artificial intelligence technology, the artificial intelligence technology is developed and applied in a plurality of fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, unmanned aerial vehicles, robots, smart medical care, smart customer service, and the like.

Big data (Big data) refers to a data set which cannot be captured, managed and processed by a conventional software tool within a certain time range, and is a massive, high-growth-rate and diversified information asset which can have stronger decision-making power, insight discovery power and flow optimization capability only by a new processing mode. With the advent of the cloud era, big data has attracted more and more attention, and the big data needs special technology to effectively process a large amount of data within a tolerance elapsed time. The method is suitable for the technology of big data, and comprises a large-scale parallel processing database, data mining, a distributed file system, a distributed database, a cloud computing platform, the Internet and an extensible storage system.

According to the method and the device, machine learning and big data can be combined to determine the fuzzy relation among a plurality of users, and accurate recommendation of information is achieved.

First, the fuzzy relation correlation technique will be briefly described.

Set fuzzy set with discourse domain U, called mapping

Determining fuzzy subsets on U

Mapping

Is called as

Membership functions of (a).

Referred to as x pairs

To the affiliate program of (1). For example: membership of "young" at age 20 is 100%, membership of "young" at age 30 is 80%, and membership of "young" at age 50 is 10%. Fuzzy sets are typically recorded using the zad representation:

Youth collection

Expressed as:

note that: here "+" does not mean a sum, nor a semicolon means a score. Only with symbolic meaning.

The operation of the fuzzy set is that discourse domain U is set as { x ═ x₁,x₂,…x_nThere are two fuzzy sets above:

note that: the upper ∑ signs do not indicate summation, and the preceding zade notation "+" is consistent.

Defining the intersection of the fuzzy sets:

defining a union of fuzzy sets:

here, ". ANGLE" means that the two values are taken to be the smallest, and ". V", means that the two values are taken to be the largest.

Fuzzy relation-a subset of fuzzy relations with discourse field U, V, UxV

Is a fuzzy relationship of U to V. The membership function is mapping:

combined balance

Is (x, y) about a fuzzy relationship

The degree of correlation of (c). Fuzzy relations are generalizations of common relations, e.g., "parent-child" is a common relation, while "familiar" between two people is a fuzzy relation.

Fuzzy relation matrix: let us assume that the familiarity of three persons, u1, u2, u3, is as follows, with familiarity 1 indicating complete familiarity and familiarity 0 indicating complete unfamiliarity, as shown in table 1 below:

TABLE 1

Familiarity with	u1	u2	u3
				u1
	1	0.8	0.5
				u2	0.8	1	0
u3	0.5	0	1

We use the fuzzy relation matrix R to represent, namely:

fuzzy equivalence relation: fuzzy relations

For fuzzy equivalence, if the above 3 points are satisfied:

1) Self-reflexibility

2) Symmetry property

3) Transmissibility of

Fuzzy equivalence matrix: fuzzy equivalence relation

The matrix of (d) is a fuzzy equivalence matrix.

The user's work and rest regularity, activity status, are valuable features in advertising recommendations, such as recommending office workers facing 9 nights and 5 nights for midnight tea, and recommending night nights for frequent night-out people. But the work and rest rules and the active states of the users are very complicated, and the boundary lines are difficult to be demarcated in each classification state. Such as people who often stay up all night: sleep several times a week late and stay up at night? If sleep late for 5 days without staying up, then sleep late for 4 days without waiting? A fuzzy set and fuzzy clustering method in fuzzy data is introduced to output dynamic clustering results under different intercepts. The results may be used in advertising recommendations and the like scenarios. The method skips the definition of the user behavior, and directly uses the fuzzy relation on the user behavior to perform clustering, so that the expression is more accurate and flexible.

The application provides an information recommendation method, an information recommendation device, an electronic device and a computer-readable storage medium, and aims to solve the above technical problems in the prior art.

The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

The information recommendation method provided by the application can be applied to the application environment shown in fig. 1. The server 101 acquires terminal usage records of a plurality of users from a plurality of terminals 102, respectively; the server 101 determines a fuzzy relationship between the plurality of users based on the terminal usage records of the plurality of users, classifies the plurality of users based on the fuzzy relationship to obtain classification results, and then sends recommendation information to the user terminals 102 of the plurality of users, respectively, based on the classification results.

Those skilled in the art will understand that the "terminal" used herein may be a Mobile phone, a tablet computer, a PDA (Personal Digital Assistant), an MID (Mobile Internet Device), etc.; a "server" may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.

A possible implementation manner is provided in the embodiment of the present application, and as shown in fig. 2, an information recommendation method is provided, which is described by taking an example that the method is applied to the server in fig. 1, and may include the following steps:

step S201, respectively obtaining terminal use records of a plurality of users; the terminal usage record includes usage times of a plurality of applications for the user terminal and types of the applications correspondingly used by each user.

The terminal usage record may further include operations of the user terminal by each user, such as clicking, touching, sliding frequency, and the like, for each time period.

Specifically, according to the terminal usage record of the user, it can be determined whether the user is in a state of frequently using the terminal or not using the terminal at different time periods, so as to determine whether the user may be at rest, sleep or work.

Step S202, based on the terminal usage records of a plurality of users, determining fuzzy relations among the plurality of users.

In particular, a common relationship can only describe two elements as being either related or unrelated. Either one of them is indispensable, and only one of them. However, there may be some relationships and close relationships among the objective things besides absolute relationships or no relationships, and there may be fuzzy concepts such as "some relationships" and "close relationships", for example, the relationship between weight and length may be "more normal" besides absolute development (satisfying formula) and abnormal, and a fuzzy relationship may be introduced by expressing such relationship.

Specifically, a fuzzy set can be determined according to the terminal usage record of the user, a similarity fuzzy relation matrix is obtained according to the fuzzy set, and finally fuzzy relations among a plurality of users are determined according to the similarity fuzzy relation matrix, wherein a specific process for determining the fuzzy relations is explained in detail below.

Step S203, classifying the plurality of users based on the fuzzy relation to obtain a classification result.

Specifically, the fuzzy relationship may be described in the form of a similarity fuzzy relationship matrix, an intercept matrix of the similarity fuzzy relationship matrix may be determined, and a classification result may be determined based on the intercept matrix of the similarity fuzzy relationship matrix, where a specific classification process based on the fuzzy relationship will be described in detail below.

And step S204, based on the classification result, sending recommendation information to the user terminals of a plurality of users.

The classification result may include which users are in the same class and what characteristics the users have.

In a specific implementation process, a plurality of classification results may be set first, and recommendation information corresponding to each classification result is set, for example, if a certain class of users is a 9-5-th office worker, then the users may be recommended to take lunch; if a certain type of user belongs to a group of people who often stay up night, the user can be recommended to the user in the night.

In the above embodiment, the fuzzy relations among the plurality of users are determined through the terminal use records of the plurality of users, the users are classified based on the fuzzy relations to obtain the classification results, and then the recommendation information corresponding to the classification results is sent.

The following describes a process for determining fuzzy relationships between multiple users with reference to the accompanying drawings and embodiments.

A possible implementation manner is provided in the embodiment of the present application, as shown in fig. 3, the determining the fuzzy relationship between multiple users based on the terminal usage records of multiple users in step S202 may include:

step S210, aiming at any user, determining the active frequency distribution data of the user in a preset period based on the terminal use record of the user;

the activity number distribution data may include a cumulative activity number of the user terminal in each preset time period in a preset period, for example, the cumulative activity number of the user terminal in each hour in each day in one month.

The number of active times may be the number of times that the user terminal receives various instructions sent by the user through clicking, touching or sliding, the number of active times per hour per day may be determined, and then the cumulative number of active times per hour in a month or a week is determined based on the number of active times per hour per day.

Specifically, the step S210 of determining, for any user, active number distribution data of the user in a preset period based on the terminal usage record of the user may include:

(1) For any user, determining the number of active times of the user in each preset time period of each sub-period in a preset period based on the terminal usage record of the user;

(2) and determining the accumulated active times of the user in each preset time period in the preset period based on the active times of the user in each preset time period in each sub-period in the preset period.

In particular, a user activity timing may be generated. Generating the active state of the user in a sequence of 0-24 hours, i.e.

Representing the k-th hour active times of the ith user, as shown in fig. 4, a state sequence of two users (user1, user2) in one day may be generated, that is, the active times of each user in each hour in one day may be obtained, for example, the active times of the user1 in 0:00-8:00am is 0; the number of times user2 is active at 0:00-5:00am is 0; wherein i and k are both positive integers.

Specifically, the active number distribution of each user in 24 hours in a day can be cumulatively added, for example, the cumulative active number of 0:00-1:00 in a month is obtained by adding the active number of 0:00-1:00 in each day.

Specifically, clustering using the user activity status of a single day is susceptible to interference from noisy point data and outliers. Because the signal-to-noise ratio is improved and the resolution is improved by adopting a data superposition technology. The specific method comprises the following steps: data for one period (week, month) of the user is aggregated. The specific period selection is subject to the service requirement. If the advertisement scene is sensitive to the behavior change of the user, the advertisement scene is not too long. The polymerization formula is as follows:

Wherein: t is a period, such as week and month; c. C_k ⁽ⁱ⁾Representing the aggregation active times of the ith user in the k hour on the period T; i and k are both positive integers.

In a specific implementation process, when abnormal data interference may occur in a sub-period, the cumulative active times of the user in each preset time period in the preset period are obtained by correspondingly overlapping the active times of the user in each preset time period in each sub-period in the preset period, so that the influence of the abnormal interference data in the sub-period can be reduced, the classification accuracy is improved, and the information recommendation accuracy is improved.

In one embodiment, the determining, for any user, the active number distribution data of the user in the preset period based on the terminal usage record of the user in step S210 may include:

(1) for any user, determining initial active time distribution data of the user in a preset period based on a terminal use record of the user;

(2) and carrying out signal denoising on the initial active time distribution data of the user to obtain the active time distribution data of the user.

Specifically, in order to further remove the influence of voice point data and abnormal values of the user's behavior, a smoothing and voice-removing step may be added.

The signal throat removing method can comprise the following steps: spatial domain based filtering-median filtering and wavelet domain based vocal-threshold vocal removal; the median filter is a common nonlinear smoothing filter, and the basic principle is that the value of one point in a signal sequence is replaced by the median of each point in the neighborhood of the point; vocal-threshold vocal-based vocal: the signal is transformed to the frequency domain by using wavelet transform, then the high frequency signal is subjected to threshold filtering, and then the signal is subjected to inverse wavelet transform to recover the signal.

The median filtering will be described in detail below as an example.

Specifically, performing signal denoising on the initial active time distribution data of the user to obtain the active time distribution data of the user may include:

a. determining the median of each active number value in a preset neighborhood of the active number value according to any active number value in the initial active number distribution data of the user;

b. replacing the number of active times with the determined median;

c. and acquiring active number distribution data based on the active number values after the replacement.

As shown in fig. 5, the median filter window size can be set to 3, and the calculation formula for each signal point is as follows:

Wherein, c_k ⁽ⁱ⁾Representing the cumulative active times of the ith user after denoising in the k hour in the period T; c. C_j ⁽ⁱ⁾Representing the cumulative active times of the ith user before denoising in the period T at the jth hour; j ═ (k-1, k, k + 1); wherein k is a positive integer greater than or equal to 0 and less than or equal to 23.

In the specific implementation process, for the accumulated active times of each preset time period in the preset period of the user, the value of one point in the distribution of the accumulated active times is replaced by the median of each point in the neighborhood of the point through median filtering, so that the influence of voice point data and abnormal values of the behavior of the user can be further removed, and the accuracy of information recommendation is improved.

Step S220, determining a fuzzy relationship between the plurality of users based on the active number distribution data of the plurality of users.

Wherein the fuzzy relation may comprise a similarity fuzzy relation matrix.

Specifically, determining the fuzzy relationship among the multiple users based on the activity number distribution data of the multiple users may include:

(1) generating an activity fuzzy set based on activity number distribution data of a plurality of user terminals;

(2) and determining a similarity fuzzy relation matrix based on a predefined fuzzy similarity relation between any two activity times distribution data and the activity fuzzy set.

Specifically, the generating of the liveness fuzzy set and the determining of the similarity fuzzy relation matrix may specifically include the following steps:

a. and generating an activity fuzzy set, wherein the formula is as follows:

wherein the content of the first and second substances,

representing a liveness fuzzy set; c. C_k ⁽ⁱ⁾Representing the cumulative active times of the ith user after denoising in the k hour in the period T; c. C_j ⁽ⁱ⁾Representing the cumulative active times of the ith user before denoising in the period T at the jth hour; j ═ (k-1, k, k + 1); wherein k is a positive integer greater than 0 and less than 23.

In one example, as shown in fig. 6, the generated liveness fuzzy set may be as shown in fig. 6, where h _0 may represent a time period between 0:00 and 1:00, and the rest of the time is analogized in turn, and the cumulative number of liveness times in each hour is subjected to smooth denoising, for example, by using spatial domain-based filtering-median filtering or wavelet domain-based denoising-threshold denoising, and the liveness fuzzy set is determined based on the denoised cumulative number of liveness times.

b. Calculating the activity similarity of the users, and defining the fuzzy similarity relation between the users i and j as follows:

wherein the content of the first and second substances,

representing fuzzy similarity between the user i and the user j;

here "|" means the modulus of the fuzzy set, as in the young fuzzy set above:

As shown in FIG. 7, based on the activity fuzzy sets of the user1 and the user2, the intersection and the union between the activity fuzzy sets of the

users

1 and 2 can be calculated, the modulus of the intersection and the modulus of the union are determined based on the intersection and the union, and finally the fuzzy relation between the activity fuzzy set of the user1 and the activity fuzzy set of the user2 is determined.

c. Generating a similarity fuzzy relation matrix

*＝[*]_n×n(14)

Wherein R represents a similarity fuzzy relation matrix, R_i,jRepresenting elements in the similarity fuzzy relation matrix; i and j are both positive integers.

Examples are: assuming that 5 users are provided, similarity is calculated for every two users by using a formula (12) to generate a fuzzy similarity relation matrix:

in the above embodiment, as shown in fig. 8, the active times of the user in each preset time period of each sub-period in the preset period may be respectively and correspondingly superimposed to obtain the cumulative active times of the user in each preset time period in the preset period, then the cumulative active times are subjected to smooth denoising, a similarity fuzzy relationship matrix is generated according to the denoised cumulative active times, and finally the classification result is obtained based on the similarity fuzzy relationship matrix.

The above embodiments illustrate a specific process of generating a similarity fuzzy relation matrix, and a specific process of classifying based on fuzzy relations will be described below with reference to the accompanying drawings and embodiments.

A possible implementation manner is provided in the embodiment of the present application, the classifying the multiple users based on the fuzzy relationship in step S203 to obtain a classification result may include:

(1) and acquiring a cut matrix of the similarity fuzzy relation matrix.

Wherein, let R ∈ [. T [ ]]_n×n，R＝(r_i,j) To, for

Note R_λ＝(λr_i,j) Wherein

Then R is_λReferred to as the lambda-cut matrix of R.

Specifically, obtaining the truncated matrix of the similarity fuzzy relationship matrix may include:

a. determining a range of the number of categories corresponding to the classification result;

b. determining a threshold value of the truncation matrix based on the range of the number of categories;

c. and acquiring a truncation matrix of the similarity fuzzy relation matrix corresponding to the threshold.

Specifically, the range of the number of categories is related to a threshold λ, and the larger the λ is, the more detailed the classification is, that is, the larger the number of categories is; the smaller the λ, the coarser the classification, i.e. the relatively smaller the number of classes, that is to say the inverse correlation between the number of classes and the threshold.

(2) Classification results for a plurality of users are determined based on the truncation matrix.

For example, 5 users (x1, x2, x3, x4, x5) are classified:

taking lambda as 1 to obtain

Then U is classified into 5 classes x1, x2, x3, x4, x5

Taking lambda as 0.8 to obtain

Then U is classified into 4 classes x1, x3, x2, x4, x5

Taking lambda as 0.6 to obtain

Then U is classified into 3 classes x1, x3, x2, x4, x 5.

The value of lambda is from large to small, and the fuzzy classification granularity is thicker and thicker. The classification of different granularities can be used in the advertisement recommendation scene, the fine granularity scene is suitable for accurate recommendation, and the coarse granularity scene is suitable for volume.

In the above embodiment, different threshold values are set for different classification quantities, so that a plurality of users are classified based on the intercept matrix of the similarity fuzzy relation matrix, and different classification quantities can be applied to recommendation scenes of different recommendation information.

Specifically, determining the classification results of the plurality of users based on the truncation matrix may include:

a. if the cut matrix is an equivalent matrix, determining a classification result based on the cut matrix;

b. and if the intercept matrix is not the equivalent matrix, adjusting the intercept matrix until the adjusted intercept matrix is the equivalent matrix, and determining a classification result based on the adjusted intercept matrix.

If R is_λIs equivalent, then R can be obtained_λClassification at the lambda level. If R is_λNot being equivalent, then R is_λModified to be equivalent. The transformation method comprises the following steps:

r is to be_λIn a formula as

Form of submatrix

Repeating the reconstruction step until stable, and recording the new matrix as

Is an equivalent matrix.

For example, when 5 users (x1, x2, x3, x4, x5) are classified, R is _0.5Not an equivalent matrix, it needs to be modified.

Taking lambda as 0.5 to obtain

R_0.5Instead of an equivalent matrix, it is modified to:

then U is classified into class 2 { x2}, { x1, x3, x4, x5}

The above embodiment illustrates a process of classifying based on the similarity fuzzy relation matrix, and how to send recommendation information according to the classification result will be further described below.

A possible implementation manner is provided in the embodiment of the present application, where the sending of the recommendation information to the user terminals of the multiple users based on the classification result in step S204 may include:

(1) determining at least one sample user corresponding to each category based on the classification result;

(2) aiming at any sample user, acquiring an information pushing time period of the sample user;

(3) determining recommendation information corresponding to the information push time period;

(4) and sending recommendation information to the users with the same category as the sample user in the information pushing time period.

Specifically, a plurality of sample users may be preset, and each sample user sets a corresponding information push time period and recommendation information.

For example, one sample user may be set to be a 9-evening 5 office worker, and the setting may give this class of sample users a recommendation for lunchtea between 3:00-4:30 pm; if a sample user is a group of people who often stay overnight, the sample user may be recommended to stay overnight between 10:00 and 12: 00.

In an embodiment, preset sample users may be mixed into a plurality of users to be classified, the sample users and the plurality of users are classified together, and after classification, the category where the sample user is located is confirmed, that is, the push time period and the recommendation information corresponding to the category can be determined.

In another embodiment, the characteristics of at least one user in each category of users may be determined directly according to the classification results of multiple users, that is, the characteristics of all users of the category where the user is located may be determined, so as to determine the push time period and the recommendation information corresponding to the characteristics of the user.

In order to better understand the above information recommendation method, an example of the information recommendation method of the present invention is set forth in detail below:

in an example, as shown in fig. 9, the information recommendation method provided by the present application may include the following steps:

step S901, acquiring terminal usage records of a plurality of users;

step S902, aiming at any user, determining initial activity times distribution data of the user in a preset period based on a terminal usage record of the user;

step S903, carrying out signal denoising on the initial activity time distribution data of the user to obtain the activity time distribution data of the user;

Step S904, generating an activity fuzzy set based on the activity times distribution data of a plurality of user terminals;

step S905, determining a similarity fuzzy relation matrix based on a fuzzy similarity relation between any two activity times distribution data and an activity fuzzy set;

step S906, acquiring a cut matrix of the similarity fuzzy relation matrix;

step S907, judging whether the intercept matrix is an equivalent matrix; if not, go to step S908; if yes, go to step S909;

step S908, adjusting the truncation matrix;

step S909 of determining a classification result based on the truncated matrix;

step S910, based on the classification result, sending recommendation information to the user terminals of a plurality of users.

According to the information recommendation method, the fuzzy relation among the users is determined through the terminal use records of the users, the users are classified based on the fuzzy relation to obtain the classification result, and then the recommendation information corresponding to the classification result is sent.

A possible implementation manner is provided in the embodiment of the present application, and as shown in fig. 10, an information recommendation apparatus 100 is provided, where the information recommendation apparatus 100 may include: an obtaining module 1001, a determining module 1002, a classifying module 1003 and a sending module 1004, wherein,

An obtaining module 1001, configured to obtain terminal usage records of multiple users respectively; the terminal usage record comprises the usage time of a plurality of application programs of the user terminal and the type of the corresponding application program used by each user;

a determining module 1002, configured to determine a fuzzy relationship between multiple users based on terminal usage records of the multiple users;

a classification module 1003, configured to classify multiple users based on a fuzzy relationship to obtain a classification result;

a sending module 1004, configured to send recommendation information to the user terminals of the multiple users based on the classification result.

In the embodiment of the present application, a possible implementation manner is provided, and when determining the fuzzy relationship between multiple users based on the terminal usage records of the multiple users, the determining module 1002 is specifically configured to:

The embodiment of the application provides a possible implementation manner, and the active time distribution data comprises the accumulated active times of the user terminal in each preset time period in a preset period;

The determining module 1002, when determining, for any user, active number distribution data of the user in a preset period based on a terminal usage record of the user, is specifically configured to:

In the embodiment of the present application, a possible implementation manner is provided, and when the determining module 1002 determines, for any user and based on a terminal usage record of the user, the active number distribution data of the user in a preset period, specifically:

A possible implementation manner is provided in the embodiment of the present application, and when the determining module 1002 performs signal denoising on the initial active time distribution data of the user to obtain the active time distribution data of the user, the determining module is specifically configured to:

replacing the number of active times with the determined median;

The embodiment of the application provides a possible implementation mode, and the fuzzy relation comprises a similarity fuzzy relation matrix;

the determining module 1002, when determining the fuzzy relationship between the multiple users based on the active number distribution data of the multiple users, is specifically configured to:

In the embodiment of the present application, a possible implementation manner is provided, and when the classification module 1003 classifies a plurality of users based on a fuzzy relation and obtains a classification result, the classification module is specifically configured to:

acquiring a cut matrix of the similarity fuzzy relation matrix;

In the embodiment of the present application, a possible implementation manner is provided, and when the classification module 1003 acquires the cut matrix of the similarity fuzzy relation matrix, the classification module is specifically configured to:

In the embodiment of the present application, a possible implementation manner is provided, and when determining the classification results of multiple users based on the cut matrix, the classification module 1003 is specifically configured to:

In the embodiment of the present application, a possible implementation manner is provided, and when the sending module 1004 sends recommendation information to user terminals of multiple users based on the classification result, the sending module is specifically configured to:

According to the information recommendation device, the fuzzy relation among the users is determined through the terminal use records of the users, the users are classified based on the fuzzy relation to obtain the classification result, and then the recommendation information corresponding to the classification result is sent.

The information recommendation device for pictures according to the embodiments of the present disclosure may execute the information recommendation method for pictures provided by the embodiments of the present disclosure, and the implementation principles thereof are similar, the actions performed by each module in the information recommendation device for pictures according to the embodiments of the present disclosure correspond to the steps in the information recommendation method for pictures according to the embodiments of the present disclosure, and for the detailed function description of each module of the information recommendation device for pictures, reference may be specifically made to the description in the information recommendation method for corresponding pictures shown in the foregoing, and details are not repeated here.

Based on the same principle as the method shown in the embodiments of the present disclosure, embodiments of the present disclosure also provide an electronic device, which may include but is not limited to: a processor and a memory; a memory for storing computer operating instructions; and the processor is used for executing the information recommendation method shown in the embodiment by calling the computer operation instruction. Compared with the prior art, the information recommendation method can improve the classification accuracy, so that appropriate information can be recommended to corresponding users in appropriate time periods.

In an alternative embodiment, an electronic device is provided, as shown in fig. 11, the electronic device 4000 shown in fig. 11 comprising: a processor 4001 and a memory 4003. Processor 4001 is coupled to memory 4003, such as via bus 4002. Optionally, the electronic device 4000 may further comprise a transceiver 4004. In addition, the transceiver 4004 is not limited to one in practical applications, and the structure of the electronic device 4000 is not limited to the embodiment of the present application.

The Processor 4001 may be a CPU (Central Processing Unit), a general-purpose Processor, a DSP (Digital Signal Processor), an ASIC (Application specific integrated Circuit), an FPGA (Field Programmable Gate Array) or other Programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 4001 may also be a combination that performs a computational function, including, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, or the like.

Bus 4002 may include a path that carries information between the aforementioned components. The bus 4002 may be a PCI (Peripheral Component Interconnect) bus, an EISA (extended industry Standard Architecture) bus, or the like. The bus 4002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 11, but this is not intended to represent only one bus or type of bus.

The Memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, an EEPROM (Electrically erasable programmable Read Only Memory), a CD-ROM (Compact Read Only Memory) or other optical disk storage, optical disk storage (including Compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to.

The memory 4003 is used for storing application codes for executing the scheme of the present application, and the execution is controlled by the processor 4001. Processor 4001 is configured to execute application code stored in memory 4003 to implement what is shown in the foregoing method embodiments.

Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 11 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

The present application provides a computer-readable storage medium, on which a computer program is stored, which, when running on a computer, enables the computer to execute the corresponding content in the foregoing method embodiments. Compared with the prior art, the information recommendation method can improve the classification accuracy, so that appropriate information can be recommended to corresponding users in appropriate time periods.

Embodiments of the present application provide a computer program product or computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium; the processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the computer device executes the information recommendation method. Compared with the prior art, the information recommendation method can improve the classification accuracy, so that appropriate information can be recommended to corresponding users in appropriate time periods.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.

Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of a module does not in some cases constitute a limitation of the module itself, for example, a classification module may also be described as a "module that classifies based on a similarity fuzzy relationship matrix".

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. An information recommendation method, comprising:

respectively acquiring terminal use records of a plurality of users; the terminal usage record comprises the usage time of a plurality of application programs of each user for the user terminal and the type of the application program correspondingly used;

classifying a plurality of users based on the fuzzy relation to obtain a classification result;

2. The information recommendation method according to claim 1, wherein determining fuzzy relationships between the plurality of users based on the terminal usage records of the plurality of users comprises:

3. The information recommendation method according to claim 2, wherein the activity number distribution data includes a cumulative activity number of the user terminal for each preset time period in the preset period;

the determining, for any user, the distribution data of the number of active times of the user in a preset period based on the terminal usage record of the user includes:

for any user, determining the number of active times of the user in each preset time period of each sub-period in the preset period based on the terminal usage record of the user;

4. The information recommendation method according to claim 2, wherein the determining, for any user, the data of the distribution of the number of active times of the user in a preset period based on the terminal usage record of the user comprises:

5. The information recommendation method according to claim 4, wherein the signal denoising the initial activity number distribution data of the user to obtain the activity number distribution data of the user comprises:

replacing the number of active times with the determined median;

and acquiring the active number distribution data based on the active number values after the replacement.

6. The information recommendation method of claim 2, wherein the fuzzy relationship comprises a similarity fuzzy relationship matrix;

determining fuzzy relations among the plurality of users based on the active number distribution data of the plurality of users, including:

And determining the similarity fuzzy relation matrix based on a predefined fuzzy similarity relation between any two activity times distribution data and the activity fuzzy set.

7. The information recommendation method according to claim 6, wherein the classifying the plurality of users based on the fuzzy relation to obtain a classification result comprises:

acquiring a cut matrix of the similarity fuzzy relation matrix;

determining the classification results for the plurality of users based on the truncation matrix.

8. The information recommendation method according to claim 7, wherein the obtaining a cut matrix of the similarity fuzzy relation matrix comprises:

and acquiring a truncation matrix of the similarity fuzzy relation matrix corresponding to the threshold value.

9. The information recommendation method of claim 7, wherein said determining the classification results of the plurality of users based on the cut matrix comprises:

if the truncation matrix is an equivalent matrix, determining the classification result based on the truncation matrix;

And if the intercept matrix is not the equivalent matrix, adjusting the intercept matrix until the adjusted intercept matrix is the equivalent matrix, and determining the classification result based on the adjusted intercept matrix.

10. The information recommendation method according to claim 1, wherein said sending recommendation information to user terminals of a plurality of users based on the classification result comprises:

and sending the recommendation information to the users with the same category as the sample user in the information pushing time period.

11. An information recommendation apparatus, comprising:

the acquisition module is used for respectively acquiring terminal use records of a plurality of users; the terminal usage record comprises the usage time of a plurality of application programs of each user for the user terminal and the type of the application program correspondingly used;

and the sending module is used for sending recommendation information to the user terminals of the plurality of users based on the classification result.

12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the information recommendation method of any one of claims 1-10 when executing the program.

13. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, implements the information recommendation method according to any one of claims 1 to 10.