CN109787784B - Group recommendation method and device, storage medium and computer equipment - Google Patents
Group recommendation method and device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN109787784B CN109787784B CN201811388966.1A CN201811388966A CN109787784B CN 109787784 B CN109787784 B CN 109787784B CN 201811388966 A CN201811388966 A CN 201811388966A CN 109787784 B CN109787784 B CN 109787784B
- Authority
- CN
- China
- Prior art keywords
- group
- recommended
- recommendation
- recommendation degree
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a group recommendation method, a group recommendation device, a storage medium and computer equipment. The group to be recommended comprises a robot account, and the group recommendation method comprises the following steps: acquiring group characteristics of a group to be recommended through a robot account; classifying groups to be recommended according to the group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, and one group to be recommended belongs to one or more classification categories; acquiring the active state of a group to be recommended through the account number of the robot; obtaining a first recommendation degree according to the active state; obtaining a second recommendation degree based on the classification category and the first recommendation degree; and recommending the group according to the second recommendation degree. By adopting the group recommendation method, group recommendation can be accurately carried out.
Description
[ technical field ] A method for producing a semiconductor device
The present invention relates to the field of computers, and in particular, to a group recommendation method, apparatus, storage medium, and computer device.
[ background of the invention ]
The current group recommendation is only limited to group recommendation in the same social group, and cannot support recommendation of various types of social groups. Moreover, a part of recommended groups are overdue, so that effective group recommendation cannot be achieved, even if the recommended groups are available, the attributes of the groups cannot be determined, and group recommendation cannot be accurately performed.
[ summary of the invention ]
In view of this, embodiments of the present invention provide a group recommendation method, an apparatus, a storage medium, and a computer device, so as to solve the problem that group recommendation cannot be performed accurately.
In order to achieve the above object, according to an aspect of the present invention, there is provided a group recommendation method, where a group to be recommended includes a robot account, the method including:
acquiring the group characteristics of the group to be recommended through the account number of the robot;
classifying the groups to be recommended according to the group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, and one group to be recommended belongs to one or more classification categories;
acquiring the active state of the group to be recommended through the account number of the robot;
obtaining a first recommendation degree according to the active state;
obtaining a second recommendation degree based on the classification category and the first recommendation degree;
and recommending the group according to the second recommendation degree.
Further, the acquiring the group characteristics of the group to be recommended through the robot account includes:
acquiring information sent by each user in the group to be recommended through the account number of the robot;
and analyzing the information sent by each user by adopting a natural language processing technology, and acquiring the group characteristics of the group to be recommended according to the analysis result.
Further, after obtaining the classification result of each group to be recommended, the method further includes:
re-acquiring the group characteristics of the group to be recommended every other preset time;
and classifying the group to be recommended according to the re-acquired group characteristics of the group to be recommended, and updating the classification result of the group to be recommended.
Further, the acquiring the active state of the group to be recommended through the robot account includes:
acquiring the group attribute of the group to be recommended through the account number of the robot;
calculating the information quantity sent by the group to be recommended within a preset time;
and inquiring a preset state comparison table in a database according to the group attribute and the information quantity to obtain the active state of the group to be recommended.
Further, the classifying result includes a class approximation degree, and the obtaining a second recommendation degree based on the classification class and the first recommendation degree includes:
determining a third recommendation degree according to the classification category and the category approximation degree;
and multiplying the first recommendation degree and the third recommendation degree to obtain the second recommendation degree.
In order to achieve the above object, according to an aspect of the present invention, there is provided a group recommendation apparatus, where a group to be recommended includes a robot account, the apparatus including:
the group characteristic acquisition module is used for acquiring the group characteristics of the group to be recommended through the account number of the robot;
the classification module is used for classifying the groups to be recommended according to the group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, and one group to be recommended belongs to one or more classification categories;
the active state acquisition module is used for acquiring the active state of the group to be recommended through the account number of the robot;
the first recommendation degree obtaining module is used for obtaining a first recommendation degree according to the active state;
the second recommendation degree obtaining module is used for obtaining a second recommendation degree based on the classification category and the first recommendation degree;
and the recommending module is used for recommending the group according to the second recommending degree.
Further, the group feature obtaining module includes:
the acquisition unit is used for acquiring information sent by each user in the group to be recommended through the account number of the robot;
and the group characteristic acquisition unit is used for analyzing the information sent by each user by adopting a natural language processing technology and acquiring the group characteristics of the group to be recommended according to the analysis result.
Further, the apparatus further comprises:
the characteristic retrieving unit is used for retrieving the group characteristics of the group to be recommended every other preset time;
and the classification result updating unit is used for classifying the group to be recommended according to the re-acquired group characteristics of the group to be recommended and updating the classification result of the group to be recommended.
In order to achieve the above object, according to one aspect of the present invention, a computer-readable storage medium is provided, and the computer-readable storage medium includes a stored computer program, wherein when the computer program runs, the apparatus on which the computer-readable storage medium is located is controlled to execute the above group recommendation method.
To achieve the above object, according to one aspect of the present invention, there is provided a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the group recommendation method described above when executing the computer program.
In the embodiment of the invention, the group characteristics and the active state of the group to be recommended are obtained through the account number of the robot. The method of the robot account number can ensure that the acquired information related to the group to be recommended is real-time and accurate, has high timeliness, and can directly analyze and process the acquired information. The method comprises the steps of classifying groups to be recommended through acquired group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, one group to be recommended belongs to one or more classification categories, and obtaining a first recommendation degree through the acquired active state. And combining the classification category with the first recommendation degree to obtain a second recommendation degree for group recommendation, wherein the second recommendation degree comprehensively considers the group characteristics, the activity degree of the group and other dimensions closely related to the group, and the group recommendation can be accurately performed by adopting the second recommendation degree to perform group recommendation.
[ description of the drawings ]
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
FIG. 1 is a flowchart of a group recommendation method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a group recommendation device according to an embodiment of the present invention.
[ detailed description ] embodiments
For better understanding of the technical solutions of the present invention, the following detailed descriptions of the embodiments of the present invention are provided with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all 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.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that although the terms first, second, third, etc. may be used to describe preset ranges, etc. in embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, the first preset range may also be referred to as a second preset range, and similarly, the second preset range may also be referred to as the first preset range, without departing from the scope of the embodiments of the present invention.
The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
Fig. 1 shows a flowchart of the group recommendation method in the present embodiment. The group recommendation method can be applied to a system, a platform or an application program, is used for realizing the function of accurately recommending the group required by the user, and can be particularly applied to a group recommendation application program installed on computer equipment. The computer device is a device capable of performing human-computer interaction with a user, and includes, but is not limited to, a computer, a smart phone, a tablet and the like. As shown in fig. 1, the group recommendation method includes the following steps:
s10: and acquiring the group characteristics of the group to be recommended through the account number of the robot.
In an embodiment, the group characteristics of the group to be recommended may be specifically obtained by using a robot account, and the group to be recommended may be directly analyzed to obtain the group characteristics with higher accuracy, where the group to be recommended includes a robot account.
Further, in step S10, the acquiring the group characteristics of the group to be recommended by the robot account includes: acquiring information sent by each user in a group to be recommended through a robot account; and analyzing the information sent by each user by adopting a natural language processing technology, and acquiring the group characteristics of the group to be recommended according to the analysis result. Natural Language Processing (NLP) is a field in which computer science, artificial intelligence, and linguistics focus on the interaction between computers and human (natural) languages. The natural language processing technology includes Text to Speech (Text to Speech), Speech synthesis (Speech synthesis), Speech recognition (Speech recognition), Chinese automatic word segmentation (Chinese word segmentation), Part-of-Speech tagging (Part-of-Speech tagging), and syntactic analysis (Parsing). In one embodiment, a natural language processing technology is adopted to analyze information sent by each user in the group to be recommended, the intention of the user expressed in the group to be recommended is analyzed, and the group characteristics of the group to be recommended are obtained according to the analysis result. The group characteristics obtained by the method can be directly obtained according to the information sent by the user, data preprocessing operations such as data cleaning and the like do not need to be carried out on the information sent by the user, and the accuracy of the group characteristics can be effectively improved.
S20: and classifying the groups to be recommended according to the group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, and one group to be recommended belongs to one or more classification categories.
It is understood that the group characteristics of the same group to be recommended may include both singing and dancing, and thus a group to be recommended may be classified into classification categories of a singing group and a dancing group. The way that one group to be recommended belongs to one or more classification categories can make full use of resources of the group to be recommended, rather than individually classifying one group to be recommended into a certain category. When the group is recommended, the same group to be recommended can be recommended repeatedly according to different keywords, resources can be fully mobilized, and the characteristic that the group to be recommended has the group characteristics with multiple dimensions is exerted.
S30: and acquiring the active state of the group to be recommended through the account number of the robot.
The active state of the group to be recommended is used for measuring the user activity degree of the group to be recommended. The user activity is an important index for reflecting whether the group is worth recommending, and when the user activity of a group to be recommended is high enough, the group to be recommended is more worth recommending.
Further, in step S30, acquiring the active state of the group to be recommended by the robot account includes: acquiring group attributes of a group to be recommended through the account number of the robot; calculating the information quantity sent by the group to be recommended within a preset time; and inquiring a preset state comparison table in a database according to the group attribute and the information quantity to obtain the active state of the group to be recommended. It can be understood that the active state of the group to be recommended may be represented by a group attribute of the group to be recommended and an information amount sent within a preset time, where the group attribute includes basic conditions such as the number of people in the group, the proportion of people in the group, group announcements, group chat applets, and the like, the group attribute may reflect the property, the composition structure, the characteristics, and the like of the group to be recommended to a certain extent, and these may reflect the active state of the group, and the information amount sent within a unit preset time period, such as the number of group speeches in the last 7 days, may also be used as an important reference point for judging the active state. The state comparison table is a data table preset according to the group attributes and the information quantity, and the data table describes the mapping relation between the group attributes and the information quantity and the active state. For example, if the number of group chat applets in the group attribute exceeds 10 and the number of group utterances (information volume) in the last 7 days exceeds 5 thousand, the active state may be located as an "very active state with an activity of 90" according to the mapping relationship stored in the state comparison table, and it can be understood that the active states specifically compared with different group attributes and information volumes are different, and the active state of the group can be quickly known through the active comparison table. The embodiment considers the practical value of the group to be recommended from the active state of the group for the first recommendation degree set subsequently, and is favorable for recommendation decision.
S40: and obtaining a first recommendation degree according to the active state.
S50: and obtaining a second recommendation degree based on the classification category and the first recommendation degree.
In an embodiment, considering that the classification category is also an important index that reflects whether the group is worth recommending in fact, the classification category and the first recommendation degree are considered together, and the second recommendation degree is obtained based on the classification category and the first recommendation degree.
Further, the classification result includes a class approximation degree, and in step S50, obtaining a second recommendation degree based on the classification class and the first recommendation degree includes: determining a third recommendation degree according to the classification category and the category approximation degree; and multiplying the first recommendation degree and the third recommendation degree to obtain a second recommendation degree. It is understood that a group to be recommended may belong to a plurality of classification categories at the same time, but each classification category has a corresponding category similarity, for example, a group to be recommended is a singing group with a category similarity of 65%, a dancing group with a category similarity of 30%, and the remaining 5% is the sum of the category similarities of the other classification categories. Obviously, the class similarity has an important influence on the recommendation of the group to be recommended, and therefore, a third recommendation degree needs to be determined according to the classification class and the class similarity, where the third recommendation degree is set relative to the classification class, and it needs to be noted that one group to be recommended may have a plurality of third recommendation degrees (that is, the classification classes of the group to be recommended all set corresponding third recommendation degrees according to the class similarity). And multiplying the first recommendation degree and the third recommendation degree to obtain a second recommendation degree. The second recommendation degree corresponding to each third recommendation degree is obtained by multiplying the first recommendation degree representing the active state of the group by each third recommendation degree. When the second recommendation degree is adopted for recommendation, recommendation can be carried out according to the second recommendation degree, and recommendation cannot be carried out on classification categories which are not classified. Different classification categories are allowed for one group, the actual conditions of the group can be reflected more reasonably, resources are fully mobilized, certain groups are not screened due to single classification, and accurate group recommendation is facilitated.
S60: and recommending the group according to the second recommendation degree.
Further, after step S20, that is, after obtaining the classification result of each group to be recommended, the method further includes: re-acquiring the group characteristics of the group to be recommended every other preset time; and classifying the group to be recommended according to the re-acquired group characteristics of the group to be recommended, and updating the classification result of the group to be recommended. In an embodiment, the group characteristics of the group to be recommended may change with time, for example, after a group to be recommended is replaced with a group owner, the group characteristics of the group to be recommended may be completely different from the original group characteristics. The mode of regularly updating the group characteristics can ensure that the group to be recommended is updated in time, and is beneficial to the recommendation decision of the group to be recommended.
In the scheme, the group characteristics and the active state of the group to be recommended are acquired by using the account number of the robot. The method of the robot account number can ensure that the acquired information related to the group to be recommended is real-time and accurate, has high timeliness, and can directly analyze and process the acquired information. The method comprises the steps of classifying groups to be recommended through acquired group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, one group to be recommended belongs to one or more classification categories, and obtaining a first recommendation degree through the acquired active state. And combining the classification category with the first recommendation degree to obtain a second recommendation degree for group recommendation, wherein the second recommendation degree comprehensively considers the group characteristics, the activity degree of the group and other dimensions closely related to the group, and group recommendation is performed through the second recommendation degree embodying the dimensions, so that group recommendation can be performed accurately.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
An embodiment of the present invention provides a group recommendation apparatus, where the group recommendation apparatus is configured to execute the group recommendation method, and as shown in fig. 2, the apparatus includes: the recommendation system comprises a group feature acquisition module 10, a classification module 20, an active state acquisition module 30, a first recommendation degree acquisition module 40, a second recommendation degree acquisition module 50 and a recommendation module 60.
The group feature obtaining module 10 is configured to obtain a group feature of the group to be recommended through the account of the robot.
In an embodiment, the group characteristics of the group to be recommended may be specifically obtained by using a robot account, and the group to be recommended may be directly analyzed to obtain the group characteristics with higher accuracy, where the group to be recommended includes a robot account.
The classification module 20 is configured to classify the groups to be recommended according to the group characteristics to obtain a classification result of each group to be recommended, where the classification result includes classification categories, and one group to be recommended belongs to one or more classification categories.
It is understood that the group characteristics of the same group to be recommended may include both singing and dancing, and thus a group to be recommended may be classified into classification categories of a singing group and a dancing group. The way that one group to be recommended belongs to one or more classification categories can make full use of resources of the group to be recommended, rather than individually classifying one group to be recommended into a certain category. When the group is recommended, the same group to be recommended can be recommended repeatedly according to different keywords, resources can be fully mobilized, and the characteristic that the group to be recommended has the group characteristics with multiple dimensions is exerted.
And an active state obtaining module 30, configured to obtain an active state of the group to be recommended through the robot account.
The user activity is an important index for reflecting whether the group is worth recommending, and when the user activity of a group to be recommended is high enough, the group to be recommended is more worth recommending.
And the first recommendation degree obtaining module 40 is configured to obtain the first recommendation degree according to the active state.
And a second recommendation degree obtaining module 50, configured to obtain a second recommendation degree based on the classification category and the first recommendation degree.
In an embodiment, considering that the classification category is also an important index that reflects whether the group is worth recommending in fact, the classification category and the first recommendation degree are considered together, and the second recommendation degree is obtained based on the classification category and the first recommendation degree.
And the recommending module 60 is configured to recommend the group according to the second recommendation degree.
Optionally, the group feature acquiring module 10 includes an acquiring unit and a group feature acquiring unit.
And the acquisition unit is used for acquiring information sent by each user in the group to be recommended through the account number of the robot.
And the group characteristic acquisition unit is used for analyzing the information sent by each user by adopting a natural language processing technology and acquiring the group characteristics of the group to be recommended according to the analysis result.
In one embodiment, a natural language processing technology is adopted to analyze information sent by each user in the group to be recommended, the intention of the user expressed in the group to be recommended is analyzed, and the group characteristics of the group to be recommended are obtained according to the analysis result. The group characteristics obtained by the method can be directly obtained according to the information sent by the user, data preprocessing operations such as data cleaning and the like do not need to be carried out on the information sent by the user, and the accuracy of the group characteristics can be effectively improved.
Optionally, the group recommendation device further includes a feature retrieving unit and a classification result updating unit.
And the characteristic acquiring unit is used for acquiring the group characteristics of the group to be recommended again at intervals of a preset time.
And the classification result updating unit is used for classifying the group to be recommended according to the re-acquired group characteristics of the group to be recommended and updating the classification result of the group to be recommended.
In an embodiment, the group characteristics of the group to be recommended may change with time, for example, after a group to be recommended is replaced with a group owner, the group characteristics of the group to be recommended may be completely different from the original group characteristics. The mode of regularly updating the group characteristics can ensure that the group to be recommended is updated in time, and is favorable for realizing the recommendation decision of the group to be recommended.
Optionally, the active state acquisition module 30 includes a group attribute acquisition unit, an information amount calculation unit, and an active state acquisition unit.
And the group attribute acquisition unit is used for acquiring the group attribute of the group to be recommended through the account number of the robot.
And the information quantity calculating unit is used for calculating the information quantity sent by the group to be recommended within the preset time.
And the active state acquisition unit is used for inquiring a preset state comparison table in the database according to the group attribute and the information quantity to obtain the active state of the group to be recommended.
It can be understood that the active state of the group to be recommended may be represented by a group attribute of the group to be recommended and an information amount sent within a preset time, where the group attribute includes group basic conditions such as a group number, a group male-female ratio, a group announcement, a group chat applet, and the like, the group attribute may reflect properties, a composition structure, characteristics, and the like of the group to be recommended to a certain extent, and these may all reflect the active state of the group, and the information amount sent within a unit preset time period, such as the number of group speeches in the last 7 days, may also be used as an important reference point for judging the active state. The practical value of the group to be recommended is considered from the active state of the group in the first recommendation degree set subsequently, and recommendation decision is facilitated.
Optionally, the classification result includes a class approximation.
Optionally, the second recommendation degree obtaining module 50 includes a third recommendation degree obtaining unit and a second recommendation degree obtaining unit.
And the third recommendation degree acquisition unit is used for determining a third recommendation degree according to the classification category and the category approximation degree.
And the second recommendation degree obtaining unit is used for multiplying the first recommendation degree and the third recommendation degree to obtain a second recommendation degree.
It is understood that a group to be recommended may belong to a plurality of classification categories at the same time, but each classification category has a corresponding category similarity, for example, a group to be recommended is a singing group with a category similarity of 65%, a dancing group with a category similarity of 30%, and the remaining 5% is the sum of the category similarities of the other classification categories. Obviously, the class similarity has an important influence on the recommendation of the group to be recommended, and therefore, a third recommendation degree needs to be determined according to the classification class and the class similarity, where the third recommendation degree is set relative to the classification class, and it needs to be noted that one group to be recommended may have a plurality of third recommendation degrees (that is, the classification classes of the group to be recommended all set corresponding third recommendation degrees according to the class similarity). And multiplying the first recommendation degree and the third recommendation degree to obtain a second recommendation degree. The second recommendation degree corresponding to each third recommendation degree is obtained by multiplying the first recommendation degree representing the active state of the group by each third recommendation degree. When the second recommendation degree is adopted for recommendation, recommendation can be carried out according to the second recommendation degree, and recommendation cannot be carried out on classification categories which are not classified. Different classification categories are allowed for one group, the actual conditions of the group can be reflected more reasonably, resources are fully mobilized, certain groups are not screened due to single classification, and accurate group recommendation is facilitated.
The embodiment of the invention provides a computer-readable storage medium, which comprises a computer program, wherein when the computer program runs, a device where the computer-readable storage medium is located is controlled to execute the following steps:
and acquiring the group characteristics of the group to be recommended through the account number of the robot.
And classifying the groups to be recommended according to the group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, and one group to be recommended belongs to one or more classification categories.
And acquiring the active state of the group to be recommended through the account number of the robot.
The active state of the group to be recommended is used for measuring the user activity degree of the group to be recommended. The user activity is an important index for reflecting whether the group is worth recommending, and when the user activity of a group to be recommended is high enough, the group to be recommended is more worth recommending.
And obtaining a first recommendation degree according to the active state.
And obtaining a second recommendation degree based on the classification category and the first recommendation degree.
And recommending the group according to the second recommendation degree.
Optionally, the apparatus, in which the computer program is executed, is further configured to: acquiring information sent by each user in a group to be recommended through a robot account; and analyzing the information sent by each user by adopting a natural language processing technology, and acquiring the group characteristics of the group to be recommended according to the analysis result.
Optionally, the apparatus, in which the computer program is executed, is further configured to: after the classification result of each group to be recommended is obtained, the group characteristics of the group to be recommended are obtained again at intervals of a preset time; and classifying the group to be recommended according to the re-acquired group characteristics of the group to be recommended, and updating the classification result of the group to be recommended.
Optionally, the apparatus, in which the computer program is executed, is further configured to: acquiring group attributes of a group to be recommended through the account number of the robot; calculating the information quantity sent by the group to be recommended within a preset time; and inquiring a preset state comparison table in a database according to the group attribute and the information quantity to obtain the active state of the group to be recommended.
Optionally, the classification result includes a class approximation, and the controlling device of the computer readable storage medium further performs the following steps when the computer program is executed: determining a third recommendation degree according to the classification category and the category approximation degree; and multiplying the first recommendation degree and the third recommendation degree to obtain a second recommendation degree.
The embodiment of the invention provides computer equipment, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the following steps:
and acquiring the group characteristics of the group to be recommended through the account number of the robot.
And classifying the groups to be recommended according to the group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, and one group to be recommended belongs to one or more classification categories.
And acquiring the active state of the group to be recommended through the account number of the robot.
The active state of the group to be recommended is used for measuring the user activity degree of the group to be recommended. The user activity is an important index for reflecting whether the group is worth recommending, and when the user activity of a group to be recommended is high enough, the group to be recommended is more worth recommending.
And obtaining a first recommendation degree according to the active state.
And obtaining a second recommendation degree based on the classification category and the first recommendation degree.
And recommending the group according to the second recommendation degree.
Optionally, the processor, when executing the computer program, further performs the following steps: acquiring information sent by each user in a group to be recommended through a robot account; and analyzing the information sent by each user by adopting a natural language processing technology, and acquiring the group characteristics of the group to be recommended according to the analysis result.
Optionally, the processor, when executing the computer program, further performs the following steps: after the classification result of each group to be recommended is obtained, the group characteristics of the group to be recommended are obtained again at intervals of a preset time; and classifying the group to be recommended according to the re-acquired group characteristics of the group to be recommended, and updating the classification result of the group to be recommended.
Optionally, the processor, when executing the computer program, further performs the following steps: acquiring group attributes of a group to be recommended through the account number of the robot; calculating the information quantity sent by the group to be recommended within a preset time; and inquiring a preset state comparison table in a database according to the group attribute and the information quantity to obtain the active state of the group to be recommended.
Optionally, the classification result includes a class approximation, and optionally, the processor, when executing the computer program, further implements the following steps: determining a third recommendation degree according to the classification category and the category approximation degree; and multiplying the first recommendation degree and the third recommendation degree to obtain a second recommendation degree.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions in actual implementation, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) or a Processor (Processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A group recommendation method is characterized in that a group to be recommended comprises a robot account, and the method comprises the following steps:
acquiring the group characteristics of the group to be recommended through the account number of the robot;
classifying the groups to be recommended according to the group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, and one group to be recommended belongs to one or more classification categories;
acquiring the active state of the group to be recommended through the account number of the robot;
obtaining a first recommendation degree according to the active state;
obtaining a second recommendation degree based on the classification category and the first recommendation degree;
recommending the group according to the second recommendation degree;
the classification result includes a class approximation degree, and the obtaining of a second recommendation degree based on the classification class and the first recommendation degree includes:
determining a third recommendation degree according to the classification category and the category approximation degree;
and multiplying the first recommendation degree and the third recommendation degree to obtain the second recommendation degree.
2. The method according to claim 1, wherein the obtaining of the group feature of the group to be recommended through the robot account comprises:
acquiring information sent by each user in the group to be recommended through the account number of the robot;
and analyzing the information sent by each user by adopting a natural language processing technology, and acquiring the group characteristics of the group to be recommended according to the analysis result.
3. The method according to claim 1, wherein after the obtaining of the classification result of each of the groups to be recommended, the method further comprises:
re-acquiring the group characteristics of the group to be recommended every other preset time;
and classifying the group to be recommended according to the re-acquired group characteristics of the group to be recommended, and updating the classification result of the group to be recommended.
4. The method according to claim 1, wherein the obtaining the active state of the group to be recommended through the robot account comprises:
acquiring the group attribute of the group to be recommended through the account number of the robot;
calculating the information quantity sent by the group to be recommended within a preset time;
and inquiring a preset state comparison table in a database according to the group attribute and the information quantity to obtain the active state of the group to be recommended.
5. A group recommendation device is characterized in that a group to be recommended comprises a robot account, and the device comprises:
the group characteristic acquisition module is used for acquiring the group characteristics of the group to be recommended through the account number of the robot;
the classification module is used for classifying the groups to be recommended according to the group characteristics to obtain a classification result of each group to be recommended, wherein the classification result comprises classification categories, and one group to be recommended belongs to one or more classification categories;
the active state acquisition module is used for acquiring the active state of the group to be recommended through the account number of the robot;
the first recommendation degree obtaining module is used for obtaining a first recommendation degree according to the active state;
the second recommendation degree obtaining module is used for obtaining a second recommendation degree based on the classification category and the first recommendation degree;
the recommending module is used for recommending the group according to the second recommending degree;
the classification result comprises a class approximation degree, the second recommendation degree obtaining module comprises a third recommendation degree obtaining unit and a second recommendation degree obtaining unit, and the third recommendation degree obtaining unit is used for determining a third recommendation degree according to the classification class and the class approximation degree;
the second recommendation degree obtaining unit is configured to multiply the first recommendation degree and the third recommendation degree to obtain the second recommendation degree.
6. The apparatus of claim 5, wherein the group feature obtaining module comprises:
the acquisition unit is used for acquiring information sent by each user in the group to be recommended through the account number of the robot;
and the group characteristic acquisition unit is used for analyzing the information sent by each user by adopting a natural language processing technology and acquiring the group characteristics of the group to be recommended according to the analysis result.
7. The apparatus of claim 5, further comprising:
the characteristic retrieving unit is used for retrieving the group characteristics of the group to be recommended every other preset time;
and the classification result updating unit is used for classifying the group to be recommended according to the re-acquired group characteristics of the group to be recommended and updating the classification result of the group to be recommended.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the group recommendation method according to any one of claims 1 to 4.
9. A computer arrangement comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the group recommendation method according to any one of claims 1 to 4 when executing the computer program.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2018112568095 | 2018-10-26 | ||
| CN201811256809 | 2018-10-26 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109787784A CN109787784A (en) | 2019-05-21 |
| CN109787784B true CN109787784B (en) | 2022-04-22 |
Family
ID=66496470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811388966.1A Active CN109787784B (en) | 2018-10-26 | 2018-11-21 | Group recommendation method and device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109787784B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111431727B (en) * | 2020-02-19 | 2022-01-21 | 北京达佳互联信息技术有限公司 | Group display method, device, terminal, server and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104092596A (en) * | 2014-01-20 | 2014-10-08 | 腾讯科技（深圳）有限公司 | Music user group management method, device and system |
| CN105069106A (en) * | 2015-08-07 | 2015-11-18 | 小米科技有限责任公司 | Application group recommendation method and device |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7844668B2 (en) * | 2004-07-30 | 2010-11-30 | Microsoft Corporation | Suggesting a discussion group based on indexing of the posts within that discussion group |
| CN102387093B (en) * | 2011-10-06 | 2017-07-21 | 福建爱特点信息科技有限公司 | The method and system that a kind of instant messaging good friend shares with group |
| US8938512B2 (en) * | 2012-09-06 | 2015-01-20 | Facebook, Inc. | Recommending groups to create in a social networking system |
| US9558242B2 (en) * | 2013-10-15 | 2017-01-31 | Google Inc. | Social where next suggestion |
| CN104615616B (en) * | 2014-05-04 | 2017-03-22 | 腾讯科技（深圳）有限公司 | group recommendation method and system |
| CN105207880B (en) * | 2014-06-10 | 2019-09-27 | 腾讯科技（深圳）有限公司 | Group recommending method and device |
| CN104317959B (en) * | 2014-11-10 | 2018-07-17 | 北京字节跳动网络技术有限公司 | Data digging method based on social platform and device |
| CN106302085B (en) * | 2015-05-18 | 2020-08-25 | 腾讯科技（深圳）有限公司 | Recommendation method and system for instant messaging group |
| CN107807943B (en) * | 2016-09-09 | 2020-06-02 | 腾讯科技（深圳）有限公司 | Application recommendation message pushing method and device, server and storage medium |
| CN107947951B (en) * | 2017-12-21 | 2019-10-15 | Oppo广东移动通信有限公司 | Groups of users recommended method, device and storage medium and server |
-
2018
- 2018-11-21 CN CN201811388966.1A patent/CN109787784B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104092596A (en) * | 2014-01-20 | 2014-10-08 | 腾讯科技（深圳）有限公司 | Music user group management method, device and system |
| CN105069106A (en) * | 2015-08-07 | 2015-11-18 | 小米科技有限责任公司 | Application group recommendation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 组推荐系统及其应用研究;张玉洁等;《计算机学报》;20160430(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109787784A (en) | 2019-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110909165A (en) | Data processing method, device, medium and electronic equipment | |
| CN109597874B (en) | Information recommendation method, device and server | |
| CN111179935B (en) | Voice quality inspection method and device | |
| CN112035599B (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| CN112749344A (en) | Information recommendation method and device, electronic equipment, storage medium and program product | |
| CN113495900A (en) | Method and device for acquiring structured query language sentences based on natural language | |
| TW201915777A (en) | Financial analysis system and method for unstructured text data | |
| CN113407677B (en) | Method, apparatus, device and storage medium for evaluating consultation dialogue quality | |
| CN111428503B (en) | Identification processing method and processing device for homonymous characters | |
| CN109615009B (en) | Learning content recommendation method and electronic equipment | |
| CN111079029A (en) | Sensitive account detection method, storage medium and computer equipment | |
| CN114579104A (en) | Data analysis scene generation method, device, equipment and storage medium | |
| CN110473543B (en) | Voice recognition method and device | |
| KR102307380B1 (en) | Natural language processing based call center support system and method | |
| CN109787784B (en) | Group recommendation method and device, storage medium and computer equipment | |
| CN114253990A (en) | Database query method and device, computer equipment and storage medium | |
| CN114880498B (en) | Event information display method and device, equipment and medium | |
| CN113095073B (en) | Corpus tag generation method and device, computer equipment and storage medium | |
| CN112989003B (en) | Intention recognition method, device, processing equipment and medium | |
| CN115186063A (en) | Service data processing method, device, equipment and storage medium | |
| CN109242690A (en) | Finance product recommended method, device, computer equipment and readable storage medium storing program for executing | |
| CN115129864A (en) | Text classification method and device, computer equipment and storage medium | |
| CN114676237A (en) | Sentence similarity determining method and device, computer equipment and storage medium | |
| CN111178038B (en) | Document similarity recognition method and device based on latent semantic analysis | |
| CN113870998A (en) | Interrogation method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |