CN114880567A

CN114880567A - Information pushing method and device

Info

Publication number: CN114880567A
Application number: CN202210545754.XA
Authority: CN
Inventors: 党娜; 徐凯路; 王春燕
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2022-05-19
Filing date: 2022-05-19
Publication date: 2022-08-09

Abstract

The embodiment of the invention provides an information pushing method and device, which can be used in the technical field of artificial intelligence, and the method comprises the following steps: respectively acquiring first information and second information from different information bases according to the determined interest categories of the users; performing keyword weight calculation on the first information to obtain a first keyword weight set; selecting target information from the second information according to the first keyword weight set; the target information is sent to the user terminal so that the user terminal can visually display the target information, the target information is selected based on the interest of the user and is pushed to the user terminal, the expandability of the pushed information is improved, the personalized degree of the pushed information is enhanced, and the user experience and the pushing efficiency are improved.

Description

Information pushing method and device

Technical Field

The invention relates to the technical field of computers, in particular to the technical field of artificial intelligence, and particularly relates to an information pushing method and device.

Background

At present, a user terminal receives a large amount of push information every day, and the push information is various and huge in quantity, so that the user experience is greatly reduced. In the related art, the collaborative filtering recommendation method has poor expandability, high repeatability of information pushed to a user, poor user experience, low pushing efficiency and low personalization degree of pushed information.

Disclosure of Invention

An object of the present invention is to provide an information pushing method, which selects target information based on user interest and pushes the target information to a user terminal, so as to improve expandability of pushed information, enhance personalization degree of the pushed information, and improve user experience and pushing efficiency. Another object of the present invention is to provide an information pushing apparatus. It is yet another object of the present invention to provide a computer readable medium. It is a further object of the present invention to provide a computer apparatus.

In order to achieve the above object, the present invention discloses an information pushing method, including:

respectively acquiring first information and second information from different information bases according to the determined interest categories of the users;

performing keyword weight calculation on the first information to obtain a first keyword weight set;

selecting target information from the second information according to the first keyword weight set;

and sending the target information to the user terminal so that the user terminal can visually display the target information.

Preferably, before the step of obtaining the first information and the second information from different information bases according to the determined interest categories of the users, the method further includes:

acquiring a transaction record of a user;

determining the transaction category to which the transaction record belongs according to the transaction record;

counting the category frequency of each transaction category in a specified time period;

and determining the transaction category of which the category frequency is greater than or equal to a preset frequency threshold value as the user interest category.

Preferably, the obtaining the first information and the second information from different information bases according to the determined interest categories of the users includes:

acquiring first information from an external information base according to the interest categories of users;

and acquiring second information from the local information base according to the interest categories of the users.

Preferably, the performing a keyword weight calculation on the first information to obtain a first keyword weight set includes:

extracting each keyword of the first information through a keyword extraction algorithm to obtain a first keyword set;

counting the first frequency number of each first keyword in the first keyword set;

sorting the first keywords according to the first frequency;

selecting a specified number of first target keywords from the sorted first keywords;

performing keyword weight calculation according to the set time weight and a first target frequency count of the first target keywords in the specified period to obtain a first target weight corresponding to each first target keyword, wherein the first target frequency count is the frequency of the first target keywords appearing in the specified period;

and obtaining a first keyword weight set according to the first target keyword and the corresponding first target weight.

Preferably, the first keyword weight set comprises first target keywords and corresponding first target weights;

selecting target information from the second information according to the first keyword weight set, including:

extracting keywords of each piece of second information according to the user interest categories through a keyword extraction algorithm to obtain a second keyword set corresponding to each user interest category;

adding the first target weights corresponding to each overlapped keyword in the keyword intersection between the second keyword set and the first keyword weight set to obtain the information weight of the second information;

sorting each piece of second information according to the information weight;

selecting a specified amount of information from the sorted second information as target information.

Preferably, after the target information is sent to the user terminal, the method further includes:

acquiring the playing information of the target information;

generating interest values of the users to the target information according to the playing information;

sorting the target information according to the interest values;

selecting a specified amount of information from the sorted target information as interest information;

performing information matching from a local information base according to the interest information to obtain matching information;

and sending the matching information to the user terminal so that the user terminal can visually display the matching information.

Preferably, the playing information includes a playing completion rate, a viewing duration and a forwarding rate;

generating interest values of users to the target information according to the playing information, comprising:

and multiplying the broadcasting completion rate, the viewing duration and the forwarding rate to obtain the interest value of the target information.

Preferably, the information matching is performed from the local information base according to the interest information to obtain matching information, and the method includes:

performing word segmentation processing on the interest information through a word segmentation algorithm to obtain interest segmented words;

vectorizing the interest participles by a specified statistical algorithm to obtain interest information characteristics;

similarity calculation is carried out on the interest information characteristics and each piece of information to be matched in the local information base, and similarity corresponding to each piece of information to be matched is obtained;

sorting the information to be matched according to the similarity;

and selecting the specified amount of information from the sorted information to be matched as matching information.

The invention also discloses an information pushing device, which comprises:

the first obtaining unit is used for obtaining first information and second information from different information bases according to the determined interest categories of the users;

the keyword weight calculation unit is used for performing keyword weight calculation on the first information to obtain a first keyword weight set;

the first selection unit is used for selecting target information from the second information according to the first keyword weight set;

and the sending unit is used for sending the target information to the user terminal so that the user terminal can visually display the target information.

Preferably, the apparatus further comprises:

the second acquisition unit is used for acquiring the transaction record of the user;

the first determining unit is used for determining the transaction category to which the transaction record belongs according to the transaction record;

the counting unit is used for counting the category frequency of each transaction category in a specified time period;

and the second determining unit is used for determining the transaction category of which the category frequency is greater than or equal to the preset frequency threshold value as the user interest category.

Preferably, the first obtaining unit is specifically configured to obtain the first information from the external information base according to the user interest category; and acquiring second information from the local information base according to the interest categories of the users.

Preferably, the keyword weight calculation unit is specifically configured to extract the keyword of each piece of first information through a keyword extraction algorithm to obtain a first keyword set; counting the first frequency number of each first keyword in the first keyword set; sorting the first keywords according to the first frequency; selecting a specified number of first target keywords from the sorted first keywords; performing keyword weight calculation according to the set time weight and a first target frequency count of the first target keywords in the specified period to obtain a first target weight corresponding to each first target keyword, wherein the first target frequency count is the frequency of the first target keywords appearing in the specified period; and obtaining a first keyword weight set according to the first target keyword and the corresponding first target weight.

the first selection unit is specifically used for extracting the keywords of each piece of second information according to the interest categories of the users through a keyword extraction algorithm to obtain a second keyword set corresponding to each interest category of the users; adding the first target weights corresponding to each overlapped keyword in the keyword intersection between the second keyword set and the first keyword weight set to obtain the information weight of the second information; sorting each piece of second information according to the information weight; selecting a specified amount of information from the sorted second information as target information.

Preferably, the apparatus further comprises:

a third obtaining unit, configured to obtain playing information of the target information;

the generating unit is used for generating interest values of the users to the target information according to the playing information;

the sorting unit is used for sorting the target information according to the interest values;

the second selection unit is used for selecting a specified amount of information from the sorted target information as interest information;

the information matching unit is used for performing information matching from the local information base according to the interest information to obtain matching information;

and the sending unit is also used for sending the matching information to the user terminal so that the user terminal can visually display the matching information.

and the generating unit is specifically used for multiplying the broadcasting completion rate, the viewing duration and the forwarding rate to obtain the interest value of the target information.

Preferably, the information matching unit is specifically configured to perform word segmentation processing on the interest information through a word segmentation algorithm to obtain an interest word; vectorizing the interest participles by a specified statistical algorithm to obtain interest information characteristics; similarity calculation is carried out on the interest information characteristics and each piece of information to be matched in the local information base, and similarity corresponding to each piece of information to be matched is obtained; sorting the information to be matched according to the similarity; and selecting the specified amount of information from the sorted information to be matched as matching information.

The invention also discloses a computer-readable medium, on which a computer program is stored which, when executed by a processor, implements a method as described above.

The invention also discloses a computer device comprising a memory for storing information comprising program instructions and a processor for controlling the execution of the program instructions, the processor implementing the method as described above when executing the program.

According to the determined interest categories of the users, first information and second information are respectively obtained from different information bases; performing keyword weight calculation on the first information to obtain a first keyword weight set; selecting target information from the second information according to the first keyword weight set; the target information is sent to the user terminal so that the user terminal can visually display the target information, the target information is selected based on the interest of the user and is pushed to the user terminal, the expandability of the pushed information is improved, the personalized degree of the pushed information is enhanced, and the user experience and the pushing efficiency are improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention 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 invention, 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 an information pushing method according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating another information pushing method according to an embodiment of the present invention;

FIG. 3 is a flowchart of information acquisition according to an embodiment of the present invention;

fig. 4 is a flowchart of obtaining a first keyword weight set according to an embodiment of the present invention;

FIG. 5 is a flowchart of selecting target information according to an embodiment of the present invention;

FIG. 6 is a flowchart illustrating information matching according to an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention.

It should be noted that the information pushing method and apparatus disclosed in the present application can be used in the technical field of artificial intelligence, and can also be used in any field except the technical field of artificial intelligence.

The following describes an implementation process of the information pushing method provided by the embodiment of the invention by taking the information pushing apparatus as an execution subject. It can be understood that the executing agent of the information push method provided by the embodiment of the invention includes but is not limited to the information push device.

Fig. 1 is a flowchart of an information pushing method according to an embodiment of the present invention, as shown in fig. 1, the method includes:

step 101, respectively acquiring first information and second information from different information bases according to the determined interest categories of the users.

Step 102, performing keyword weight calculation on the first information to obtain a first keyword weight set.

Step 103, selecting the target information from the second information according to the first keyword weight set.

And step 104, sending the target information to the user terminal so that the user terminal can visually display the target information.

According to the technical scheme provided by the embodiment of the invention, the first information and the second information are respectively obtained from different information bases according to the determined interest categories of the users; performing keyword weight calculation on the first information to obtain a first keyword weight set; selecting target information from the second information according to the first keyword weight set; the target information is sent to the user terminal so that the user terminal can visually display the target information, the target information is selected based on the interest of the user and is pushed to the user terminal, the expandability of the pushed information is improved, the personalized degree of the pushed information is enhanced, and the user experience and the pushing efficiency are improved.

Fig. 2 is a flowchart of another information pushing method according to an embodiment of the present invention, as shown in fig. 2, the method includes:

step 201, acquiring a transaction record of a user.

In the embodiment of the invention, each step is executed by the information pushing device.

In the embodiment of the invention, the transaction record of the user terminal is obtained, and the transaction record comprises but is not limited to a transaction name, transaction content, transaction time and transaction amount.

It should be noted that the technical solutions in the present application, such as obtaining, storing, using, and processing data, all conform to relevant regulations of national laws and regulations. The user information in the embodiment of the application is obtained through legal compliance, and the user information is obtained, stored, used, processed and the like through authorization approval of a client.

Step 202, determining the transaction type of the transaction record according to the transaction record.

In the embodiment of the present invention, the transaction category may be obtained by the transaction name, or the transaction category may be obtained by the transaction content. As an alternative, if the transaction name of the user is the consignment financing, the transaction category to which the consignment financing belongs is the fund; if the transaction name of the user is self-operation and financial management, the transaction category to which the self-operation and financial management belongs is financial management; and if the transaction content of the user is telephone fee recharging, the transaction category to which the telephone fee recharging belongs is life payment.

Step 203, counting the category frequency of each transaction category in the designated time period.

In the embodiment of the present invention, the specified time period may be set according to actual requirements, which is not limited in the embodiment of the present invention. As an alternative, the designated time period is 6 months, and the frequency of each transaction category of transactions performed by the user in 6 months is counted to obtain the transaction amount of each transaction category in 6 months.

And step 204, determining the transaction category with the category frequency greater than or equal to the preset frequency threshold value as the user interest category.

In the embodiment of the present invention, the frequency threshold may be set according to actual requirements, which is not limited in the embodiment of the present invention.

In the embodiment of the present invention, the transaction category of which the category frequency is greater than or equal to the frequency threshold is the transaction category in which the user is interested, that is: a user interest category.

As another alternative, the transaction categories are sorted from large to small according to the category frequency of each transaction category, and the transaction categories of N top-ranked transaction categories are determined as the user interest categories. The value of N may be set according to an actual situation, for example, the value of N is 3.

Step 205, obtaining the first information and the second information from different information bases according to the determined interest categories of the users.

Fig. 3 is a flowchart of acquiring information according to an embodiment of the present invention, as shown in fig. 3, step 205 specifically includes:

step 2051, obtain the first information from the external information base according to the user interest category.

In the embodiment of the invention, the external information base is a website or an application program provided by the third-party platform, and the specific selection of the third-party platform is not limited in the embodiment of the invention.

Specifically, information in an external information base is captured through a crawler technology to obtain first information, and the first information belongs to the user interest category.

Step 2052, obtain the second information from the local information base according to the user interest category.

In the embodiment of the invention, the local information base is a database provided locally, and various types of information are stored in the database.

Specifically, according to the user interest category, the matched information in the database is determined as the second information.

Step 206, performing a keyword weight calculation on the first information to obtain a first keyword weight set.

Fig. 4 is a flowchart of obtaining a first keyword weight set according to an embodiment of the present invention, and as shown in fig. 4, step 206 specifically includes:

step 2061, extracting each keyword of the first information through a keyword extraction algorithm to obtain a first keyword set.

Specifically, the number of the first information is multiple, each piece of the first information is input into a keyword extraction algorithm for keyword extraction, and a first keyword of each piece of the first information is output; and generating a first keyword set according to the plurality of first keywords.

Step 2062, count the first frequency of each first keyword in the first keyword set.

In the embodiment of the invention, each first keyword is counted to obtain the first frequency number of each first keyword appearing in the first keyword set. For example: the first keyword financing, wherein the first frequency in the first keyword set is 7 times; the first frequency of the first keyword fund in the first keyword set is 5 times.

Step 2063, the first keywords are sorted according to the first frequency.

In the embodiment of the present invention, the first keywords may be sorted in an ascending order according to the first frequency count, or sorted in a descending order according to the first frequency count, and the sorting manner is not limited in the embodiment of the present invention.

Step 2064, selecting a specified number of first target keywords from the sorted first keywords.

Specifically, if the first keywords are sorted in a descending order according to the first frequency number, the first keywords of N names before sorting are determined as the first target keywords. The value of N may be set according to an actual situation, for example, the value of N is 10.

As another alternative, if the first keywords are sorted in an ascending order according to the first frequency count, the N sorted first keywords are determined as the first target keywords. The value of N may be set according to an actual situation, for example, the value of N is 10.

It is worth explaining that the first keyword with the highest repetition degree is determined as the first target keyword, the keywords which are most interesting to the user can be embodied, and a foundation is laid for customizing personalized information recommendation.

Step 2065, performing keyword weight calculation according to the set time weight and the first target frequency count of the first target keywords in the specified period to obtain a first target weight corresponding to each first target keyword, where the first target frequency count is the number of times that the first target keywords appear in the specified period.

In the embodiment of the invention, the time weight can be set according to the distance between the first information time and the current time, and the closer the first information time is to the current time, the higher the time weight is; the farther the time is from the current time, the lower the time weight is, and the specific value of the time weight is not limited in the embodiment of the present invention.

In the embodiment of the invention, the designated period can be set according to the actual situation, and is less than the designated time period.

For example: the first target keyword includes: financing, wherein the designated period is within 10 days from the current time, the time weight t1 at the time t1 is set to be 3, the time weight at the time t2 is set to be 2, and the time weight at the time t3 is set to be 1; the first target keyword "financing" has a first target frequency of 7 in 10 days, a frequency of 2 at time t1, a frequency of 3 at time t2, and a frequency of 2 at time t3, and the first target weight is 3 × 2+2 × 3+1 × 2 — 14. Wherein, t1, t2 and t3 are all in a specified period of 10 days, and are sequentially distant from the current time.

Step 2066, a first keyword weight set is obtained according to the first target keyword and the corresponding first target weight.

In the embodiment of the invention, a plurality of first target keywords are respectively calculated to obtain a plurality of corresponding first target weights; and generating a first keyword weight set according to the plurality of first target keywords and the corresponding first target weights.

Step 207, selecting the target information from the second information according to the first keyword weight set.

In the embodiment of the present invention, the first keyword weight set includes a first target keyword and a corresponding first target weight.

Fig. 5 is a flowchart of selecting target information according to an embodiment of the present invention, as shown in fig. 5, step 207 specifically includes:

step 2071, extracting each keyword of the second information according to the user interest category through a keyword extraction algorithm to obtain a second keyword set corresponding to each user interest category.

Specifically, the number of the second information is multiple, each piece of the second information is input into a keyword extraction algorithm according to the interest category of the user, keyword extraction is carried out, and a second keyword of each piece of the second information is output; and generating a second keyword set corresponding to each user interest category according to the second keywords in each user interest category.

Step 2072, add the first target weights corresponding to each overlapped keyword in the keyword intersection between the second keyword set and the first keyword weight set to obtain the information weight of the second information.

In the embodiment of the invention, the first keyword weight set comprises a first target keyword and a corresponding first target weight; the second keyword set comprises a plurality of second keywords; and matching the first target keyword with the second keyword to obtain a coincident keyword, wherein the coincident keyword exists in the first keyword weight set and the second keyword set.

Specifically, a first target weight corresponding to the overlapped keyword is obtained from a first keyword weight set; adding the first target weights corresponding to each overlapped keyword to obtain the information weight of the second information.

For example: overlapping keywords are financing, fund and telephone charge; the corresponding first target weights are 5, 3 and 2, respectively, and the information weight of the second information is 5+3+ 2-10.

Step 2073, sort each piece of second information according to the information weight.

In the embodiment of the present invention, the second information may be sorted in an ascending order according to the information weight, or sorted in a descending order according to the information weight, and the sorting manner in the embodiment of the present invention is not limited.

Step 2074, select a predetermined number of information from the sorted second information as the target information.

Specifically, if the second information is sorted in descending order according to the information weight, the first N names of the second information are determined as the target information. The value of N may be set according to actual conditions, for example, the value of N is 20.

As another alternative, if the second information is sorted in ascending order according to the information weight, the sorted N second information is determined as the target information. The value of N may be set according to actual conditions, for example, the value of N is 20.

It is worth to be noted that, the information with higher information weight is determined as the target information, the information in which the user is most interested can be accurately obtained, and personalized information push for the user is realized.

And step 208, sending the target information to the user terminal so that the user terminal can visually display the target information.

In the embodiment of the invention, the target information is information customized for the user, the target information is pushed to the user terminal, and the user terminal performs visual display on the target information. The push method of the target information includes, but is not limited to, application program push and short message push, and the push method of the target information is not limited in the embodiment of the present invention.

Step 209, obtain the playing information of the target information.

In the embodiment of the present invention, the playing information of the target information includes, but is not limited to, a play-out rate, a viewing duration, and a forwarding rate. As an alternative, a front-facing camera of the user terminal captures a specific number of lines of the target information viewed by the eyeball of the user, and the specific number of lines is divided by the total number of lines of the target information to obtain the broadcasting completion rate.

Step 210, generating the interest value of the user in the target information according to the playing information.

Specifically, the broadcasting completion rate, the viewing duration and the forwarding rate are multiplied to obtain the interest value of the target information. The higher the interest value is, the more interested the user is in the target information; the lower the interest value, the less interest the user has in the target information.

Step 211, sorting the target information according to the interest values.

In the embodiment of the present invention, the target information may be sorted in an ascending order according to the interest values, or sorted in a descending order according to the interest values, and the sorting manner is not limited in the embodiment of the present invention.

Step 212, select a specified amount of information from the sorted target information as interest information.

Specifically, if the target information is sorted in descending order according to the interest value, the top N target information is determined as the interest information. The value of N may be set according to an actual situation, for example, the value of N is 3.

As another alternative, if the target information is sorted in ascending order according to the interest value, the N sorted target information is determined as the interest information. The value of N may be set according to actual conditions, for example, N is 3.

It is worth to be noted that, the information with the higher interest value is determined as the interest information, the information in which the user is most interested can be accurately obtained, and personalized information push for the user can be further realized.

Step 213, performing information matching from the local information base according to the interest information to obtain the matching information.

Fig. 6 is a flowchart of information matching according to an embodiment of the present invention, as shown in fig. 6, step 213 specifically includes:

step 2131, performing word segmentation processing on the interest information through a word segmentation algorithm to obtain interest word segments.

Specifically, the interest information is subjected to word segmentation processing through a jieba (jieba) word segmentation algorithm to obtain an interest word segmentation.

Step 2132, vectorizing the interest participles through a specified statistical algorithm to obtain the interest information characteristics.

In the embodiment of the invention, the specified statistical algorithm is a word frequency-inverse text frequency index (TF-IDF) algorithm, and the TF-IDF algorithm is a common weighting technology for information retrieval and data mining.

Specifically, the interest word is input into TF-IDF algorithm to output the interest information feature.

Step 2133, similarity calculation is performed on the interest information features and each piece of information to be matched in the local information base, so as to obtain a similarity corresponding to each piece of information to be matched.

In the embodiment of the invention, each piece of information to be matched in the local information base is subjected to word segmentation and vectorization so as to extract the information characteristics of the information to be matched.

In particular, by

A _i ＝(a ₁ ,a ₂ ,....,a _n ),B _i ＝(b ₁ ,b ₂ ,....,b _n ) And calculating the interest information characteristics and the information characteristics of the information to be matched to obtain the similarity between each piece of information to be matched and the interest information. Wherein A is _i As interest information, a _n Characteristic of interest information, B _i For information to be matched, b _n N is the number of features for the information features of the information to be matched.

Step 2134, sorting the information to be matched according to the similarity.

In the embodiment of the present invention, the information to be matched may be sorted in an ascending order according to the similarity, or sorted in a descending order according to the similarity, and the sorting manner is not limited in the embodiment of the present invention.

Step 2135, selecting a predetermined amount of information from the sorted information to be matched as matching information.

Specifically, if the information to be matched is sorted in descending order according to the similarity, the top N pieces of information to be matched are determined as matching information. The value of N may be set according to an actual situation, for example, the value of N is 10.

As another alternative, if the information to be matched is sorted in ascending order according to the similarity, the N sorted information to be matched is determined as the matching information. The value of N may be set according to an actual situation, for example, the value of N is 10.

Step 214, sending the matching information to the user terminal for the user terminal to perform visual display on the matching information.

Specifically, the matching information is pushed to the user terminal, and the user terminal visually displays the matching information. The push method of the matching information includes, but is not limited to, application program push and short message push, and the push method of the matching information is not limited in the embodiment of the present invention.

In the embodiment of the invention, the matching information is the information customized for the user in a personalized way, and is more suitable for the user preference.

According to the technical scheme of the information pushing method, the first information and the second information are respectively obtained from different information bases according to the determined interest categories of the users; performing keyword weight calculation on the first information to obtain a first keyword weight set; selecting target information from the second information according to the first keyword weight set; the target information is sent to the user terminal so that the user terminal can visually display the target information, the target information is selected based on the interest of the user and is pushed to the user terminal, the expandability of the pushed information is improved, the personalized degree of the pushed information is enhanced, and the user experience and the pushing efficiency are improved.

Fig. 7 is a schematic structural diagram of an information pushing apparatus according to an embodiment of the present invention, the apparatus is configured to execute the information pushing method, and as shown in fig. 7, the apparatus includes: a first acquiring unit 11, a keyword weight calculating unit 12, a first extracting unit 13, and a transmitting unit 14.

The first obtaining unit 11 is configured to obtain the first information and the second information from different information bases according to the determined user interest category.

The keyword weight calculation unit 12 is configured to perform keyword weight calculation on the first information to obtain a first keyword weight set.

The first selecting unit 13 is used for selecting the target information from the second information according to the first keyword weight set.

The sending unit 14 is configured to send the target information to the user terminal, so that the user terminal can visually display the target information.

In the embodiment of the present invention, the apparatus further includes: a second acquisition unit 15, a first determination unit 16, a statistical unit 17 and a second determination unit 18.

The second obtaining unit 15 is used for obtaining the transaction record of the user.

The first determining unit 16 is configured to determine a transaction category to which the transaction record belongs according to the transaction record.

The counting unit 17 is used for counting the category frequency of each transaction category in a specified time period.

The second determining unit 18 is configured to determine the transaction category with the category frequency greater than or equal to the preset frequency threshold as the user interest category.

In the embodiment of the present invention, the first obtaining unit 11 is specifically configured to obtain the first information from the external information base according to the user interest category; and acquiring second information from the local information base according to the interest categories of the users.

In the embodiment of the present invention, the keyword weight calculating unit 12 is specifically configured to extract the keyword of each piece of first information through a keyword extraction algorithm to obtain a first keyword set; counting the first frequency number of each first keyword in the first keyword set; sorting the first keywords according to the first frequency; selecting a specified number of first target keywords from the sorted first keywords; performing keyword weight calculation according to the set time weight and a first target frequency count of the first target keywords in the specified period to obtain a first target weight corresponding to each first target keyword, wherein the first target frequency count is the frequency of the first target keywords appearing in the specified period; and obtaining a first keyword weight set according to the first target keyword and the corresponding first target weight.

In the embodiment of the invention, the first keyword weight set comprises a first target keyword and a corresponding first target weight; the first selecting unit 13 is specifically configured to extract, through a keyword extraction algorithm, keywords of each piece of second information according to the user interest categories to obtain a second keyword set corresponding to each user interest category; adding the first target weights corresponding to each overlapped keyword in the keyword intersection between the second keyword set and the first keyword weight set to obtain the information weight of the second information; sorting each piece of second information according to the information weight; selecting a specified amount of information from the sorted second information as target information.

In the embodiment of the present invention, the apparatus further includes: a third acquiring unit 19, a generating unit 20, a sorting unit 21, a second selecting unit 22 and an information matching unit 23.

The third obtaining unit 19 is used for obtaining the playing information of the target information.

The generating unit 20 is used for generating the interest value of the user in the target information according to the playing information.

The sorting unit 21 is used for sorting the target information according to the interest value.

The second selecting unit 22 is used for selecting a specified amount of information from the sorted target information as interest information.

The information matching unit 23 is used for performing information matching from the local information base according to the interest information to obtain matching information.

The sending unit 14 is further configured to send the matching information to the user terminal, so that the user terminal can visually display the matching information.

In the embodiment of the invention, the playing information comprises the playing completion rate, the viewing duration and the forwarding rate; the generating unit 20 is specifically configured to multiply the broadcast completion rate, the viewing duration, and the forwarding rate to obtain an interest value of the target information.

In the embodiment of the present invention, the information matching unit 23 is specifically configured to perform word segmentation processing on the interest information through a word segmentation algorithm to obtain an interest word; vectorizing the interest participles by a specified statistical algorithm to obtain interest information characteristics; similarity calculation is carried out on the interest information characteristics and each piece of information to be matched in the local information base, and similarity corresponding to each piece of information to be matched is obtained; sorting the information to be matched according to the similarity; and selecting the specified amount of information from the sorted information to be matched as matching information.

According to the scheme of the embodiment of the invention, the first information and the second information are respectively obtained from different information bases according to the determined interest categories of the users; performing keyword weight calculation on the first information to obtain a first keyword weight set; selecting target information from the second information according to the first keyword weight set; the target information is sent to the user terminal so that the user terminal can visually display the target information, the target information is selected based on the interest of the user and is pushed to the user terminal, the expandability of the pushed information is improved, the personalized degree of the pushed information is enhanced, and the user experience and the pushing efficiency are improved.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

An embodiment of the present invention provides a computer device, including a memory and a processor, where the memory is used to store information including program instructions, and the processor is used to control execution of the program instructions, and the program instructions are loaded and executed by the processor to implement the steps of the information push method, and specific descriptions may refer to the information push method.

Referring now to FIG. 8, shown is a block diagram of a computer device 600 suitable for use in implementing embodiments of the present application.

As shown in fig. 8, the computer apparatus 600 includes a Central Processing Unit (CPU)601 which can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the computer apparatus 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output section 607 including a Cathode Ray Tube (CRT), a liquid crystal feedback (LCD), and the like, and a speaker and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted as necessary on the storage section 608.

In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the invention include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.

The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An information pushing method, the method comprising:

and sending the target information to a user terminal so that the user terminal can visually display the target information.

2. The method of claim 1, further comprising, before the obtaining the first information and the second information from different information bases according to the determined interest categories of the users, respectively:

acquiring a transaction record of a user;

3. The method of claim 1, wherein the obtaining the first information and the second information from different information bases according to the determined interest categories of the users comprises:

acquiring first information from an external information base according to the interest categories of the users;

and acquiring second information from a local information base according to the interest categories of the users.

4. The information pushing method of claim 1, wherein the performing the keyword weight calculation on the first information to obtain a first keyword weight set comprises:

sorting the first keywords according to a first frequency;

performing keyword weight calculation according to the set time weight and a first target frequency count of the first target keywords in a specified period to obtain a first target weight corresponding to each first target keyword, wherein the first target frequency count is the frequency of the first target keywords appearing in the specified period;

5. The information push method according to claim 1, wherein the first keyword weight set includes a first target keyword and a corresponding first target weight;

the selecting target information from the second information according to the first keyword weight set comprises:

sorting each piece of second information according to the information weight;

6. The information pushing method according to claim 1, further comprising, after said sending the target information to the user terminal:

acquiring the playing information of the target information;

generating an interest value of the user to the target information according to the playing information;

sorting the target information according to the interest values;

and sending the matching information to a user terminal so that the user terminal can visually display the matching information.

7. The information push method according to claim 6, wherein the playing information includes a play-out rate, a viewing duration and a forwarding rate;

generating the interest value of the user to the target information according to the playing information comprises the following steps:

8. The information push method according to claim 6, wherein the matching information from the local information base according to the interest information to obtain the matching information comprises:

vectorizing the interest participles through a specified statistical algorithm to obtain interest information characteristics;

sorting the information to be matched according to the similarity;

9. An information pushing apparatus, the apparatus comprising:

and the sending unit is used for sending the target information to a user terminal so that the user terminal can visually display the target information.

10. The information push device according to claim 9, further comprising:

and the second determining unit is used for determining the transaction category of which the category frequency is greater than or equal to a preset frequency threshold value as the user interest category.

11. The information push device according to claim 9,

the first obtaining unit is specifically used for obtaining first information from an external information base according to the user interest category; and acquiring second information from a local information base according to the interest categories of the users.

12. The information push device according to claim 9,

the keyword weight calculation unit is specifically used for extracting the keywords of each piece of first information through a keyword extraction algorithm to obtain a first keyword set; counting the first frequency number of each first keyword in the first keyword set; sorting the first keywords according to a first frequency; selecting a specified number of first target keywords from the sorted first keywords; performing keyword weight calculation according to the set time weight and a first target frequency count of the first target keywords in a specified period to obtain a first target weight corresponding to each first target keyword, wherein the first target frequency count is the frequency of the first target keywords appearing in the specified period; and obtaining a first keyword weight set according to the first target keyword and the corresponding first target weight.

13. The information pushing device as claimed in claim 9, wherein the first keyword weight set includes a first target keyword and a corresponding first target weight;

the first selection unit is specifically used for extracting the keywords of each piece of second information according to the user interest categories through a keyword extraction algorithm to obtain a second keyword set corresponding to each user interest category; adding the first target weights corresponding to each overlapped keyword in the keyword intersection between the second keyword set and the first keyword weight set to obtain the information weight of the second information; sorting each piece of second information according to the information weight; selecting a specified amount of information from the sorted second information as target information.

14. The information push device according to claim 9, further comprising:

the generating unit is used for generating an interest value of the user to the target information according to the playing information;

the sorting unit is used for sorting the target information according to the interest value;

the information matching unit is used for performing information matching from a local information base according to the interest information to obtain matching information;

and the sending unit is also used for sending the matching information to a user terminal so that the user terminal can visually display the matching information.

15. The information pushing device as claimed in claim 14, wherein the playing information includes a play-out rate, a viewing duration and a forwarding rate;

16. The information push device according to claim 14,

the information matching unit is specifically used for performing word segmentation processing on the interest information through a word segmentation algorithm to obtain interest segmented words; vectorizing the interest participles through a specified statistical algorithm to obtain interest information characteristics; similarity calculation is carried out on the interest information characteristics and each piece of information to be matched in the local information base, and similarity corresponding to each piece of information to be matched is obtained; sorting the information to be matched according to the similarity; and selecting the specified amount of information from the sorted information to be matched as matching information.

17. A computer-readable medium, on which a computer program is stored, wherein the program, when being executed by a processor, implements the information pushing method according to any one of claims 1 to 8.

18. A computer device comprising a memory for storing information including program instructions and a processor for controlling the execution of the program instructions, wherein the program instructions are loaded and executed by the processor to implement the information push method according to any one of claims 1 to 8.