CN117041202A

CN117041202A - Chat user recommendation method, device, equipment and medium

Info

Publication number: CN117041202A
Application number: CN202311040132.2A
Authority: CN
Inventors: 洪宇; 范哲文; 余嘉禾
Original assignee: Hunan Malan Digital Education Technology Co ltd
Current assignee: Hunan Malan Digital Education Technology Co ltd
Priority date: 2023-08-17
Filing date: 2023-08-17
Publication date: 2023-11-10

Abstract

The invention discloses a recommendation method of chat users, which comprises the following steps: determining at least one type of current user portrait data corresponding to a current user and at least one type of other user portrait data corresponding to at least one other user; determining candidate users from other users according to the current user portrait data and other user portrait data; and determining the user to be recommended from the candidate users according to the chat characteristic data of the candidate users, and carrying out chat recommendation on the user to be recommended to the current user. When the chat user is recommended, the chat characteristic data of the user can be referred in addition to the user portrait data, so that the effect of recommending the chat user based on the multiple data dimensions of the user is realized, the accuracy and the suitability of the chat user recommendation are ensured, the chat experience of the user is further ensured, and the user viscosity is improved.

Description

Chat user recommendation method, device, equipment and medium

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for recommending chat users.

Background

With the development of computer technology and internet technology, the frequency of online chatting in life of people is increasing, and people can chat with other people online through various network platforms at any time and any place, for example, online chatting through software such as social software or virtual chat rooms.

In this context, how to recommend a suitable chat object for each user from the sea at the very large area becomes a problem to be solved.

Disclosure of Invention

The invention provides a recommendation method, device, equipment and medium for chat users, which are used for solving the problem that proper chat objects cannot be recommended for users.

According to one aspect of the present invention, there is provided a recommendation method for chat users, comprising:

determining at least one type of current user portrait data corresponding to a current user and at least one type of other user portrait data corresponding to at least one other user;

determining candidate users from the other users according to the current user portrait data and the other user portrait data;

determining a user to be recommended from the candidate users according to the chat feature data of the candidate users, and carrying out chat recommendation on the user to be recommended to the current user; the chat characteristic data comprises at least one of chat reply interval time, chat reply content data quantity, online time length, popularity and complaint times.

According to another aspect of the present invention, there is provided a recommendation device for chat users, comprising:

the portrait data determining module is used for determining at least one type of current user portrait data corresponding to the current user and at least one type of other user portrait data corresponding to at least one other user;

a candidate user determining module, configured to determine a candidate user from the other users according to the current user portrait data and the other user portrait data;

the user to be recommended determining module is used for determining a user to be recommended from the candidate users according to the chat characteristic data of the candidate users and chat recommendation is carried out on the user to be recommended to the current user; the chat characteristic data comprises at least one of chat reply interval time, chat reply content data quantity, online time length, popularity and complaint times.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the chat user recommendation method of any of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the chat user recommendation method according to any of the embodiments of the present invention when executed.

The technical scheme of the embodiment of the invention determines at least one type of current user portrait data corresponding to the current user and at least one type of other user portrait data corresponding to at least one other user; determining candidate users from the other users according to the current user portrait data and the other user portrait data; determining a user to be recommended from the candidate users according to the chat feature data of the candidate users, and carrying out chat recommendation on the user to be recommended to the current user; the chat feature data comprises at least one of chat reply interval time, chat reply content data quantity, online time length, popularity and complaint times, and the chat feature data of the user can be referred to besides the user portrait data when the chat user recommendation is performed, so that the effect of chat user recommendation based on multiple data dimensions of the user is achieved, accuracy and suitability of chat user recommendation are guaranteed, chat experience of the user is further guaranteed, and user viscosity is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flowchart of a method for recommending chat users according to an embodiment of the present invention;

fig. 2 is a flowchart of a chat user recommendation method according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of a recommendation device for chat users according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device implementing a recommendation method of chat users according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "current," "other," "candidate," "to be recommended," "first," "second," "third," "fourth," and "fifth," etc. in the description and claims of the present invention and the above drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a method for recommending chat users according to an embodiment of the present invention, where the method may be performed by a recommendation device of a chat user, and the recommendation device of a chat user may be implemented in hardware and/or software. As shown in fig. 1, the method includes:

S101, determining at least one type of current user portrait data corresponding to a current user and at least one type of other user portrait data corresponding to at least one other user.

Wherein the current user represents the user who needs to be recommended to the chat object, and the other users represent any other users which can be recommended besides the current user. The current user and other users represent users logged in on the same chat platform, for example, users logged in on the same social platform or the same virtual chat room, and the identities of the current user and other users can be the registered formal users or unregistered guest users.

User portrait data is a data tag which abstracts specific information of a user into data tags, and the user portrait is materialized by using the data tags, so that targeted services are provided for the user. It will be appreciated that the current user profile data represents the user profile data of the current user, while the other user profile data represents the user profile data of the other user. In this embodiment, the categories of user portrayal data include at least one category including, but not limited to, height, weight, constellation, occupation, age, gender, academic, specialty, personality, hobbies, and the like.

In one embodiment, the chat platform collects base data associated with each user under the authority of each user, the sources of the base data including, but not limited to, browsing records, purchase records, social media data, questionnaires, and the like of the user. The base data is subjected to data cleansing including, but not limited to, screening, deduplication, replenishment, and normalization to obtain clean user data. Data mining and analysis is performed on the clean user data, including but not limited to cluster analysis, classification analysis, association rule mining, time series analysis, and the like, to obtain mined user data. And finally modeling the mined user data to obtain user portrait data corresponding to each user. The chat platform stores the user portrait data of each user in association with the user identification of each user.

Under the condition that a current user initiates a chat pairing request to a chat platform, the chat platform determines user portrait data matched with the current user identification from stored user portrait data according to the current user identification of the current user, and the user portrait data is used as the current user portrait data. Correspondingly, the chat platform also determines other user portrait data matched with other user identifications from the stored user portrait data according to the other user identifications of the other users.

S102, determining candidate users from other users according to the current user portrait data and other user portrait data.

Wherein the candidate users represent other users that are similar to the user image data of the current user.

In one embodiment, the similarity matching is performed on the current user portrait data of the same category and other user portrait data, the data similarity between the current user portrait data of the same category and other user portrait data is determined, the matching score between each other user and the current user is determined according to the data similarity, and candidate users are determined from other users according to the sorting result of the matching score.

Optionally, according to the sorting result of the matching scores, other users with highest matching scores are used as candidate users.

For example, assuming that the matching scores between the other user a, the other user B, the other user C, and the other user D and the current user are 90, 80, 85, and 88, respectively, the other user a is taken as a candidate user.

S103, determining the user to be recommended from the candidate users according to the chat feature data of the candidate users, and carrying out chat recommendation on the user to be recommended to the current user.

Wherein the user to be recommended represents a chat object to be recommended to the current user by the chat platform. The chat feature data represents feature data generated by the user in the chat process, and can be used for depicting the chat habit and chat characteristic of the user. The chat characteristic data includes at least one of chat reply interval time, chat reply content data amount, online time length, popularity, and number of complaints. The chat reply interval time represents the average interval time of the chat process of the user and other users for replying to the information sent by other users. The chat reply content data amount represents the chat process of the user and other users, and the average data amount of reply information for replying to the information sent by other users can be represented by the number of character information or the duration of voice information. The online time length represents the total time length for the user to log in the chat platform to chat. Popularity represents the popularity of a user with other users in a chat platform, i.e., user popularity, and higher popularity represents higher user popularity, i.e., more other users like to chat with the user. The complaint times represent the total number of times a user is complained by other users during the chat process due to the occurrence of the offending performance.

In one embodiment, the chat platform stores chat characteristic data for each user in association with a user identification for each user.

And the chat platform determines chat feature data matched with the candidate user identification from the stored chat feature data according to the candidate user identification of the candidate user. And sequencing the candidate users according to the chat feature data, and determining the users to be recommended from the candidate users according to the sequencing result.

Optionally, when the chat feature data is chat reply interval time, ordering each candidate user according to the chat reply interval time of each candidate user, and taking the candidate users with the shortest chat reply interval time as the users to be recommended, where the preset number can be set and adjusted according to actual service requirements. For example, the five candidate users with the shortest chat reply interval time are used as users to be recommended.

Optionally, when the chat feature data is the chat reply content data amount, sorting the candidate users according to the chat reply content data amount of each candidate user, and taking the candidate users with the largest chat reply content data amount as the users to be recommended, wherein the preset number can be set and adjusted according to the actual service requirement. For example, the five candidate users with the largest chat reply content data amount are used as users to be recommended.

Optionally, when the chat feature data is online time, ordering each candidate user according to the online time of each candidate user, and taking the candidate users with the longest online time as users to be recommended, wherein the preset number can be set and adjusted according to actual service requirements. For example, the five candidate users with the longest online time length are used as users to be recommended.

Optionally, when the chat feature data is popularity, ranking each candidate user according to the popularity of each candidate user, and taking a preset number of candidate users with highest popularity as users to be recommended, wherein the preset number can be set and adjusted according to actual service requirements. For example, the five candidate users with highest popularity are used as users to be recommended.

Optionally, when the chat feature data is complaint times, sorting the candidate users according to the complaint times of the candidate users, and taking the candidate users with the least complaint times as the users to be recommended, wherein the preset number can be set and adjusted according to actual service requirements. For example, five candidate users with the least complaint times are used as users to be recommended.

The chat platform carries out chat recommendation on the determined at least one user to be recommended to the current user, the current user can select one or more users to be recommended to carry out chat requests, and an information transmission channel between the current user and the users to be recommended is established under the condition that the requested users to be recommended pass the requests, so that the chat effect is realized.

The technical scheme of the embodiment of the invention determines at least one type of current user portrait data corresponding to the current user and at least one type of other user portrait data corresponding to at least one other user; determining candidate users from other users according to the current user portrait data and other user portrait data; determining a user to be recommended from the candidate users according to the chat feature data of the candidate users, and carrying out chat recommendation on the user to be recommended to the current user; the chat feature data comprises at least one of chat reply interval time, chat reply content data quantity, online time length, popularity and complaint times, and the chat feature data of the user can be referred to besides the user portrait data when the chat user recommendation is performed, so that the effect of chat user recommendation based on multiple data dimensions of the user is achieved, accuracy and suitability of chat user recommendation are guaranteed, chat experience of the user is further guaranteed, and user viscosity is improved.

Example two

Fig. 2 is a flowchart of a chat user recommendation method provided in a second embodiment of the present invention, where the embodiment further optimizes and extends the above embodiment, and may be combined with the above alternative embodiments. As shown in fig. 2, the method includes:

s201, at least one type of current user portrait data corresponding to a current user and at least one type of other user portrait data corresponding to at least one other user are determined.

S202, determining at least one user image data matching pair from the current user image data and other user image data according to the user image data types, and performing similarity matching on the user image data included in the user image data matching pair to determine the data similarity of the user image data matching pair.

Wherein the user portrait data matching pair comprises current user portrait data and other user portrait data with the same user portrait data category.

In one embodiment, the current user portrait data and other user portrait data of the same user portrait data category are used together as a user portrait data matching pair. For example, the user portrait data category is used together with the current user portrait data and other user portrait data which are of the 'age' as a group of user portrait data matching pairs; for another example, the user portrait data category is matched with the current user portrait data and other user portrait data which are "interest" as a group of user portrait data.

And carrying out similarity matching on the included current user portrait data and other user portrait data by adopting a data similarity matching algorithm aiming at each user portrait data matching pair, and determining the data similarity between the current user portrait data and other user portrait data as the data similarity of the affiliated user portrait data matching pair.

S203, carrying out weighted summation on the user portrait data matching pair according to the data similarity and the data weight of the user portrait data matching pair, and determining the matching scores of other users and the current user according to the weighted summation result.

And setting corresponding data weights for each user portrait data matching pair according to the influence of each user portrait data category on the chat matching result in advance. It can be understood that if the influence of any user portrait data category on the chat matching result is larger, the data weight of the user portrait data matching pair corresponding to the user portrait data category is larger; correspondingly, if the influence of any user portrait data category on the chat matching result is smaller, the data weight of the user portrait data matching pair corresponding to the user portrait data category is smaller.

In one embodiment, weighted summation is performed according to the data similarity of the matching pair of the image data of each user and the data weight of the matching pair of the image data of each user, and the matching score of each other user and the current user is determined according to the weighted summation result.

For example, it is assumed that the other users a and the current user include four sets of user image data matching pairs, i.e., user image data matching pair 1, user image data matching pair 2, user image data matching pair 3, and user image data matching pair 4. Assuming that the data similarity corresponding to the user image data matching pair 1, the user image data matching pair 2, the user image data matching pair 3 and the user image data matching pair 4 is X1, X2, X3 and X4, and the data weights corresponding to the user image data matching pair 1, the user image data matching pair 2, the user image data matching pair 3 and the user image data matching pair 4 are A1, A2, A3 and A4, the matching scores of other users a and the current user are: x1+x2+a2+x3+a3+x4.a4.

And S204, determining candidate users from other users according to the matching scores and the data similarity.

In one embodiment, candidate users are screened and determined according to the numerical value of the matching score corresponding to each other user and the numerical value of the data similarity.

Determining at least one matching pair of user portrait data from the current user portrait data and other user portrait data according to the user portrait data category; performing similarity matching on the user image data included in the user image data matching pair, and determining the data similarity of the user image data matching pair; according to the data similarity and the data weight of the user portrait data matching pair, carrying out weighted summation on the user portrait data matching pair, and determining the matching scores of other users and the current user according to the weighted summation result; according to the matching score and the data similarity, candidate users are determined from other users, so that the candidate users and the current user have similar user portrait data, more common topics can be ensured when the current user and the candidate users chat, and chat experience of the current user is ensured.

Determining candidate users from other users according to the matching score and the data similarity, wherein the candidate users comprise:

s2041, according to the importance degree of the user portrait data category, determining the core portrait data category from the user portrait data category, and taking the user portrait data matching pair corresponding to the core portrait data category as the core portrait data matching pair.

The importance degree of the user portrait data category represents the influence degree of the user portrait data category on the chat experience, and it can be understood that if the influence degree of any user portrait data category on the chat experience is larger, namely the importance degree of the user portrait data category is larger; accordingly, if the influence degree of any user portrait data category on the chat experience is smaller, the importance degree of the user portrait data category is smaller.

In one embodiment, a predetermined number of user portrait data categories with a high importance level are used as core portrait data categories, and the core portrait data categories include at least one of an academy, an age, a character, and an interest. And the user image data matching pair corresponding to the core image data type is used as the core image data matching pair.

For example, assuming that the core portrait data category is "age", a user portrait data matching pair including the current user portrait data and other user portrait data whose user portrait data category is "age" is used as the core portrait data matching pair.

S2042, taking the data similarity of the core image data matching pair as the core data similarity, and taking other users with the matching score larger than a score threshold and the core data similarity larger than a similarity threshold as candidate users.

The score threshold and the similarity threshold are set empirically and can be adjusted according to actual business requirements.

Illustratively, assume that the other users include other user A, other user B, and other user C, with matching scores between three and the current user of 90, 85, and 96, respectively.

Assume that user image data matching pairs of which user image data categories are "age", "character" and "hobbies of interest" are set as core image data matching pairs. Assume that the core data similarity of the matching pairs of the core portrait data of the 'age', 'character' and 'hobby' between the other user A and the current user is 65%, 65% and 70% respectively; the similarity of core data of the matching pairs of the core portrait data of the age, character and hobby between the other users B and the current user is respectively 70%, 80% and 50%; the core data similarity of the matching pairs of the "age", "character" and "hobby" core portrait data between the other user C and the current user is 90%, 50% and 80%, respectively.

Assuming the score threshold is "88", the core data similarity is "60%", and other user a is considered as a candidate user since the match score 90 between other user a and the current user is greater than 88, and the core data similarity is greater than 60% for 65%, and 70%.

Determining a core portrait data category from the user portrait data categories according to the importance degree of the user portrait data categories, and taking a user portrait data matching pair corresponding to the core portrait data category as a core portrait data matching pair; the method comprises the steps that the data similarity of a core image data matching pair is used as the core data similarity, the matching score is larger than a score threshold, and other users with the core data similarity larger than the similarity threshold are used as candidate users, so that the determination of the candidate users depends not only on the total matching score but also on the similarity of various core data, the similarity degree of user image data between the candidate users and the current users is guaranteed, and the chat experience of the current users is guaranteed.

S205, sorting the candidate users according to the chat reply interval time, and determining a first order corresponding to the candidate users; sorting the candidate users according to the chat reply content data amount, and determining a second order corresponding to the candidate users; sequencing the candidate users according to the online time length, and determining a third sequence corresponding to the candidate users; sorting the candidate users according to the popularity, and determining a fourth order corresponding to the candidate users; and sorting the candidate users according to the complaint times, and determining a fifth order corresponding to the candidate users.

In one embodiment, the candidate users are ranked according to the order of short to long chat reply intervals, and a first order corresponding to the candidate users is determined. And sequencing the candidate users according to the sequence from the large to the small of the chat reply content data quantity, and determining a second sequence corresponding to the candidate users. And sequencing the candidate users according to the order of the online time length from long to short, and determining a third order corresponding to the candidate users. And sequencing the candidate users according to the sequence from high to low in popularity, and determining a fourth sequence corresponding to the candidate users. And sequencing the candidate users according to the sequence of the complaint times from small to large, and determining a fifth sequence corresponding to the candidate users.

S206, determining the user to be recommended from the candidate users according to the first order, the second order, the third order, the fourth order and the fifth order.

In one embodiment, the recommendation score of each candidate user is determined according to the first order, the second order, the third order, the fourth order and the fifth order corresponding to each candidate user, and the user to be recommended is determined from each candidate user according to the recommendation score.

Determining a first order corresponding to the candidate users by sequencing the candidate users according to the chat reply interval time; sorting the candidate users according to the chat reply content data amount, and determining a second order corresponding to the candidate users; sequencing the candidate users according to the online time length, and determining a third sequence corresponding to the candidate users; sorting the candidate users according to the popularity, and determining a fourth order corresponding to the candidate users; sorting the candidate users according to the complaint times, and determining a fifth order corresponding to the candidate users; and determining the user to be recommended from the candidate users according to the first order, the second order, the third order, the fourth order and the fifth order, so that the determination of the user to be recommended depends on chat characteristic data besides user portrait data, the suitability and the reliability of the user to be recommended as a chat object of the current user are ensured, and the chat experience of the current user is ensured.

Optionally, S206 includes:

s2061, determining a first base score according to the first order, and determining a first recommendation score corresponding to the candidate user according to the first base score and a first feature weight corresponding to the chat reply interval time.

S2062, determining a second base score according to the second order, and determining a second recommendation score corresponding to the candidate user according to the second base score and a second feature weight corresponding to the chat reply content data amount.

S2063, determining a third basic score according to the third order, and determining a third recommendation score corresponding to the candidate user according to the third basic score and a third feature weight corresponding to the online time length.

S2064, determining a fourth base score according to the fourth order, and determining a fourth recommendation score corresponding to the candidate user according to the fourth base score and a fourth feature weight corresponding to the popularity.

S2065, determining a fifth base score according to the fifth order, and determining a fifth recommendation score corresponding to the candidate user according to the fifth base score and a fifth feature weight corresponding to the number of complaints.

Wherein a corresponding base score is calibrated for each order in advance, it being understood that a higher order corresponds to a higher base score and, correspondingly, a lower order corresponds to a lower base score. For example, assuming that the order is "first", its corresponding base score is calibrated to be "100", the order is "second", its corresponding base score is calibrated to be "90", the order is "third", its corresponding base score is calibrated to be "80", and so on … …. The concept of the order and the base score is merely explained here, and the base score corresponding to each order is not specifically limited.

Specifically, the base score corresponding to the first order is the first base score, the base score corresponding to the second order is the second base score, the base score corresponding to the third order is the third base score, the base score corresponding to the fourth order is the fourth base score, and the base score corresponding to the fifth order is the fifth base score.

The feature weights are set according to the influence degree of each piece of chat feature data on the chat experience, and it can be understood that if the influence degree of any piece of chat feature data on the chat experience is larger, the feature weight of the chat feature data is larger; accordingly, if the influence degree of any chat feature data on the chat experience is smaller, the feature weight of the chat feature data is smaller.

Specifically, the first recommendation score is determined according to the product result of the first base score and the first feature weight; determining a second recommendation score according to the product result of the second base score and the second feature weight; the third recommendation score is determined according to the product result of the third basic score and the third characteristic weight; the fourth recommendation score is determined according to the product result of the fourth basic score and the fourth characteristic weight; the fifth recommendation score is determined based on the product of the fifth base score and the fifth feature weight.

S2066, determining a user to be recommended from the candidate users according to the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score and the fifth recommendation score.

In one embodiment, the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score and the fifth recommendation score corresponding to each candidate user are summed, and the user to be recommended is determined from the candidate users according to the result of the summation of the scores.

Determining a first recommendation score corresponding to the candidate user according to the first basic score and a first feature weight corresponding to the chat reply interval time by determining the first basic score according to the first order; determining a second basic score according to the second order, and determining a second recommendation score corresponding to the candidate user according to the second basic score and a second feature weight corresponding to the chat reply content data amount; determining a third basic score according to a third order, and determining a third recommendation score corresponding to the candidate user according to the third basic score and a third feature weight corresponding to the online time length; determining a fourth basic score according to the fourth order, and determining a fourth recommendation score corresponding to the candidate user according to the fourth basic score and a fourth feature weight corresponding to the popularity degree; determining a fifth basic score according to the fifth order, and determining a fifth recommendation score corresponding to the candidate user according to the fifth basic score and a fifth feature weight corresponding to the complaint times; and determining the user to be recommended from the candidate users according to the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score and the fifth recommendation score, so that the effect of jointly screening and obtaining the user to be recommended based on a plurality of chat feature data is realized, the user to be recommended is ensured to have excellent chat characteristics, and the chat experience between the current user and the user to be recommended is further ensured.

Optionally, S2066 includes:

determining a recommendation total score corresponding to the candidate user according to the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score and the fifth recommendation score; and determining the user to be recommended from the candidate users according to the sequencing result of the total recommendation score.

In one embodiment, the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score, and the fifth recommendation score corresponding to each candidate user are summed to determine a total recommendation score corresponding to each candidate user. And taking the preset number of candidate users with higher total recommendation scores as users to be recommended according to the sequencing result of the total recommendation scores.

Determining a recommendation total score corresponding to the candidate user according to the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score and the fifth recommendation score; and determining the user to be recommended from the candidate users according to the sequencing result of the total recommendation score, thereby ensuring that the comprehensive performance of the user to be recommended on each chat characteristic data is excellent, and further ensuring the chat experience between the current user and the user to be recommended.

S207, chat recommendation is conducted on the user to be recommended to the current user.

Example III

Fig. 3 is a schematic structural diagram of a recommendation device for chat users according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes:

the portrait data determining module 31 is configured to determine at least one type of current user portrait data corresponding to a current user and at least one type of other user portrait data corresponding to at least one other user.

A candidate user determination module 32 for determining candidate users from the other users based on the current user profile data and the other user profile data.

The to-be-recommended user determining module 33 is configured to determine a to-be-recommended user from the candidate users according to the chat feature data of the candidate users, and chat and recommend the to-be-recommended user to the current user; the chat characteristic data comprises at least one of chat reply interval time, chat reply content data quantity, online time length, popularity and complaint times.

Optionally, the candidate user determination module 32 is specifically configured to:

determining at least one user portrait data matching pair from the current user portrait data and other user portrait data according to the user portrait data category;

performing similarity matching on the user image data included in the user image data matching pair, and determining the data similarity of the user image data matching pair;

According to the data similarity and the data weight of the user portrait data matching pair, carrying out weighted summation on the user portrait data matching pair, and determining the matching scores of other users and the current user according to the weighted summation result;

candidate users are determined from the other users based on the match scores and the data similarity.

Optionally, the candidate user determination module 32 is specifically further configured to:

according to the importance degree of the user portrait data category, determining a core portrait data category from the user portrait data category, and taking a user portrait data matching pair corresponding to the core portrait data category as a core portrait data matching pair;

taking the data similarity of the core image data matching pair as the core data similarity, and taking other users with the matching score larger than a score threshold and the core data similarity larger than a similarity threshold as candidate users;

the core portrait data category comprises at least one of an academy, an age, a character and an interest.

Optionally, the user to be recommended determining module 33 is specifically configured to:

sequencing candidate users according to the chat reply interval time, and determining a first order corresponding to the candidate users;

sorting the candidate users according to the chat reply content data amount, and determining a second order corresponding to the candidate users;

Sequencing the candidate users according to the online time length, and determining a third sequence corresponding to the candidate users;

sorting the candidate users according to the popularity, and determining a fourth order corresponding to the candidate users;

sorting the candidate users according to the complaint times, and determining a fifth order corresponding to the candidate users;

and determining the user to be recommended from the candidate users according to the first order, the second order, the third order, the fourth order and the fifth order.

Optionally, the user determination module to be recommended 33 is specifically further configured to:

determining a first basic score according to the first order, and determining a first recommendation score corresponding to the candidate user according to the first basic score and a first feature weight corresponding to the chat reply interval time;

determining a second basic score according to the second order, and determining a second recommendation score corresponding to the candidate user according to the second basic score and a second feature weight corresponding to the chat reply content data amount;

determining a third basic score according to a third order, and determining a third recommendation score corresponding to the candidate user according to the third basic score and a third feature weight corresponding to the online time length;

determining a fourth basic score according to the fourth order, and determining a fourth recommendation score corresponding to the candidate user according to the fourth basic score and a fourth feature weight corresponding to the popularity degree;

Determining a fifth basic score according to the fifth order, and determining a fifth recommendation score corresponding to the candidate user according to the fifth basic score and a fifth feature weight corresponding to the complaint times;

and determining the user to be recommended from the candidate users according to the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score and the fifth recommendation score.

determining a recommendation total score corresponding to the candidate user according to the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score and the fifth recommendation score;

and determining the user to be recommended from the candidate users according to the sequencing result of the total recommendation score.

The chat user recommending device provided by the embodiment of the invention can execute the chat user recommending method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.

Example IV

Fig. 4 shows a schematic diagram of an electronic device 40 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 40 includes at least one processor 41, and a memory communicatively connected to the at least one processor 41, such as a Read Only Memory (ROM) 42, a Random Access Memory (RAM) 43, etc., in which the memory stores a computer program executable by the at least one processor, and the processor 41 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 42 or the computer program loaded from the storage unit 48 into the Random Access Memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 may also be stored. The processor 41, the ROM 42 and the RAM 43 are connected to each other via a bus 44. An input/output (I/O) interface 45 is also connected to bus 44.

Various components in electronic device 40 are connected to I/O interface 45, including: an input unit 46 such as a keyboard, a mouse, etc.; an output unit 47 such as various types of displays, speakers, and the like; a storage unit 48 such as a magnetic disk, an optical disk, or the like; and a communication unit 49 such as a network card, modem, wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 41 may be various general and/or special purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as the chat user recommendation method.

In some embodiments, the chat user recommendation method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 40 via the ROM 42 and/or the communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the chat user recommendation method described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the chat user recommendation method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on 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.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method for recommending chat users, comprising:

2. The method of claim 1, wherein said determining candidate users from said other users based on said current user profile data and said other user profile data comprises:

determining at least one user portrait data matching pair from the current user portrait data and the other user portrait data according to a user portrait data category;

according to the data similarity and the data weight of the user portrait data matching pair, carrying out weighted summation on the user portrait data matching pair, and determining matching scores of the other users and the current user according to a weighted summation result;

and determining candidate users from the other users according to the matching scores and the data similarity.

3. The method of claim 2, wherein said determining candidate users from said other users based on said match score and said data similarity comprises:

according to the importance degree of the user portrait data category, determining a core portrait data category from the user portrait data category, and taking the user portrait data matching pair corresponding to the core portrait data category as a core portrait data matching pair;

Taking the data similarity of the core image data matching pair as core data similarity, and taking the other users with the matching score larger than a score threshold and the core data similarity larger than a similarity threshold as the candidate users;

wherein the core portrait data category includes at least one of an academy, an age, a character, and an interest.

4. The method of claim 1, wherein said determining a user to be recommended from said candidate users based on chat feature data of said candidate users comprises:

sorting the candidate users according to the chat reply interval time, and determining a first order corresponding to the candidate users;

sorting the candidate users according to the online time length, and determining a third order corresponding to the candidate users;

And determining users to be recommended from the candidate users according to the first order, the second order, the third order, the fourth order and the fifth order.

5. The method of claim 4, wherein the determining a user to be recommended from the candidate users according to the first order, the second order, the third order, the fourth order, and the fifth order comprises:

determining a first basic score according to the first order, and determining a first recommendation score corresponding to the candidate user according to the first basic score and a first characteristic weight corresponding to the chat reply interval time;

determining a second base score according to the second order, and determining a second recommendation score corresponding to the candidate user according to the second base score and a second feature weight corresponding to the chat reply content data amount;

determining a third basic score according to the third order, and determining a third recommendation score corresponding to the candidate user according to the third basic score and a third feature weight corresponding to the online time length;

determining a fourth basic score according to the fourth order, and determining a fourth recommendation score corresponding to the candidate user according to the fourth basic score and a fourth feature weight corresponding to the popularity;

Determining a fifth basic score according to the fifth order, and determining a fifth recommended score corresponding to the candidate user according to the fifth basic score and a fifth feature weight corresponding to the complaint times;

and determining a user to be recommended from the candidate users according to the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score and the fifth recommendation score.

6. The method of claim 5, wherein the determining a user to be recommended from the candidate users based on the first recommendation score, the second recommendation score, the third recommendation score, the fourth recommendation score, and the fifth recommendation score comprises:

and determining the user to be recommended from the candidate users according to the sorting result of the total recommendation score.

7. A recommendation device for chat users, comprising:

8. The apparatus of claim 7, wherein the candidate user determination module is specifically configured to:

9. An electronic device, the electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the chat user recommendation method of any of claims 1-6.

10. A computer readable storage medium storing computer instructions for causing a processor to implement the chat user recommendation method of any of claims 1-6 when executed.