CN110545232A

CN110545232A - group message prompting method, group message prompting device, data processing method, data processing device, electronic equipment and storage equipment

Info

Publication number: CN110545232A
Application number: CN201810531500.6A
Authority: CN
Inventors: 靳玉康
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2018-05-29
Filing date: 2018-05-29
Publication date: 2019-12-06

Abstract

the application discloses a prompting method and a prompting device of group messages, a data processing method and a data processing device, electronic equipment and storage equipment, wherein the prompting method comprises the following steps: obtaining a current group message, wherein the current group message is a current message sent to group members in a group, and the group comprises at least two group members; determining an association between the current group message and the group member; the group member can know whether the current group message in the group is important to the group member and whether the current group message needs to be checked according to the prompt, namely the group member can check the group message in the group in time according to the received prompt, so that the group message related to the group member is avoided being missed, and the prompt method of the group message provided by the application can pointedly send the prompt to the group member.

Description

group message prompting method, group message prompting device, data processing method, data processing device, electronic equipment and storage equipment

Technical Field

The present application relates to the field of computer applications, and in particular, to a group message prompting method and apparatus, a data processing method and apparatus, an electronic device, and a storage device.

background

instant Messaging may also be referred to as Instant Messaging (IM), which allows two or more people to communicate and interact with each other by using a network to transmit data information such as text messages, files, voice, video, etc. in real time, or may refer to Instant Messaging software as a chat tool.

With the development of internet technology, a large number of enterprises use chat tools to communicate and manage their internal works. A large number of work groups are usually established in an enterprise to carry out corresponding communication, however, each employee joins a large number of different groups, so that a large number of members exist in part of the enterprise groups, chatting in each group is very complicated, many chats are only related to part of people in the group, and further each group member receives a large number of messages which are not related to the group member every day, and the messages which are related to the group member are submerged by the unrelated messages, so that the group member misses important messages.

based on the above analysis, in the prior art, the new message in the group needs to be notified to all members in the group, and the prompt for the new message lacks pertinence.

disclosure of Invention

The application provides a prompting method of a group message, which aims to solve the problem that the message in the group can not be pointed and prompted to group members in the prior art.

the application provides a prompting method of a group message, which comprises the following steps:

obtaining a current group message, wherein the current group message is a current message sent to group members in a group, and the group comprises at least two group members;

determining an association between the current group message and the group member;

and prompting the current group message to the group member according to the relevance between the current group message and the group member.

Preferably, the determining the association between the current group message and the group member comprises:

Obtaining data characteristics of the cluster, the data characteristics of the cluster including: data characteristics of the group members and data characteristics of the group itself;

calculating an association evaluation value between the current group message and the group member according to the data characteristics of the group;

And determining the relevance between the current group message and the group member according to the relevance evaluation value.

preferably, the data characteristic of the group is acquired in at least one of the following ways:

acquiring text data characteristics of the historical group message according to the historical group message of the group;

acquiring the importance data characteristics of the group members in the group according to the importance of the group relative to the group members;

Acquiring the character of the keyword data according to the historical message segment of the group;

and acquiring behavior data characteristics according to the historical behavior data information of the group members in the group.

preferably, the text data characteristic of the history group message includes at least one of the following text data characteristics: a feature vector of the history group message text length;

URL feature vectors in the history group message text;

Picture feature vectors in the historical group message text;

and expressing the characteristic vector in the historical group message text.

Preferably, the importance data characteristic of the group member comprises at least one of the following importance data characteristics:

Identity feature vectors of the group members;

A time length feature vector for the group member to join the group;

a quantity feature vector of the group members;

an active number feature vector for the group member.

preferably, the acquiring the keyword data feature according to the historical message segment of the group includes:

aggregating the historical group message segments of the group members meeting the aggregation condition to obtain an aggregated group message;

extracting historical keywords according to the aggregated group message, and determining message tags of the group members;

taking the historical group message segment which is adjacent to the current group message and does not accord with the aggregation condition as a breakpoint, and extracting a current keyword in the current aggregation message formed by the current group message;

matching the current keyword with the message tag to obtain a feature vector of the message tag to which the current keyword belongs, and taking the feature vector of the message tag as the data feature of the keyword.

preferably, the aggregation condition is an interval time between two adjacent history messages sent by the same group member in the group;

the aggregating the historical group message segments of the group members meeting the aggregation condition includes:

and judging whether the time interval of the historical message segments meets a set interval threshold, and if so, aggregating the historical message segments of the group members meeting the set interval threshold.

preferably, the historical behavior data characteristics include at least one of the following historical behavior data characteristics:

Group message quantity characteristic vectors sent by members of the same group in the group;

a notified number of feature vectors that members of the same group are notified within the group;

the same group member notifies other group members of the notification quantity characteristic vector in the group;

the group member replies a time interval characteristic vector of the group message at the closest time to the current group message;

the time interval characteristic vector of the time interval notified by the closest time of the group member to the current group information acquisition.

preferably, the acquiring the data characteristics of the group includes:

and when the number of the acquired data features of the group is at least two, merging the acquired data features.

Preferably, the calculating the association evaluation value between the current group message and the group member according to the data feature includes:

And calculating the association evaluation value of the current group message and the group member by utilizing a machine learning algorithm.

preferably, the prompting the group member of the current group message according to the association between the current group message and the group member includes:

And sending prompt information to the group members according to the relevance grade of the current group message and the group members.

Preferably, the prompting the group message to the group member according to the association between the group message and the group member includes:

determining a prompting mode corresponding to the relevance according to the relevance between the group message and the group members;

and prompting the group information to the group members according to the prompting mode corresponding to the relevance.

The present application further provides a group message prompting device, including:

an obtaining unit, configured to obtain a current group message, where the current group message is a current message sent to group members in a group, and the group includes at least two group members;

A determining unit, configured to determine an association between the current group message and the group member;

and the prompting unit is used for prompting the current group message to the group members according to the relevance between the current group message and the group members.

preferably, the determination unit includes:

an obtaining unit, configured to obtain data characteristics of the group, where the data characteristics of the group include: data characteristics of the group members and data characteristics of the group itself;

a calculating unit, configured to calculate an association evaluation value between the current group message and the group member according to the data feature of the group;

and the corresponding relation establishing unit is used for determining the relevance between the current group message and the group member according to the relevance evaluation value.

preferably, the acquiring unit specifically adopts at least one of the following acquiring subunits:

the text acquisition subunit is used for acquiring the text data characteristics of the historical group message according to the historical group message of the group;

the importance acquiring subunit is used for acquiring the importance data characteristics of the group members in the group according to the importance of the group relative to the group members;

A keyword acquisition subunit, configured to acquire a keyword data feature according to the historical message segment of the group;

and the behavior acquisition subunit is used for acquiring behavior data characteristics according to the historical behavior data information of the group members in the group.

preferably, the text acquiring subunit acquires at least one text data feature of:

A feature vector of the history group message text length;

URL feature vectors in the history group message text;

Picture feature vectors in the historical group message text;

and expressing the characteristic vector in the historical group message text.

preferably, the importance acquiring subunit acquires at least one of the following importance data characteristics:

identity feature vectors of the group members;

a time length feature vector for the group member to join the group;

a quantity feature vector of the group members;

An active feature vector of the group member.

Preferably, the keyword obtaining subunit includes:

The aggregation unit is used for aggregating the historical group message segments of the group members meeting the aggregation condition to obtain an aggregated group message;

a tag determining unit, configured to extract a history keyword according to the aggregation group message, and determine a message tag of the group member;

a current keyword extracting unit, configured to extract a current keyword in a current aggregated message formed by the current group message, with the first two history group message segments of the current group message as breakpoints;

and the keyword data feature determining unit is used for matching the current keyword with the message tag, obtaining a feature vector of the message tag to which the current keyword belongs, and determining the feature vector as the keyword data feature.

preferably, the aggregation condition is an interval time of sending the historical messages in the group; the polymerization unit includes:

and the judging unit is used for judging whether the time interval of the historical message segments meets a set time interval threshold value or not, and if so, aggregating the historical group message segments of the group members meeting the set time interval threshold value.

preferably, the behavior acquiring subunit acquires at least one of the following historical behavior data characteristics:

A number feature vector for which members of the same group are notified within the group;

preferably, the acquiring unit includes:

and a merging unit, configured to merge the acquired data features when the acquired data features of the group are at least two.

preferably, the calculation unit calculates the association evaluation value of the current group message with the group member by using a machine learning algorithm.

preferably, the prompting unit is specifically configured to send a prompting message to the group member according to the level of the relevance evaluation value between the current group message and the group member.

preferably, the prompting unit includes:

a prompting mode determining unit, configured to determine a prompting mode corresponding to the association according to the association between the group message and the group member;

The prompting unit is specifically configured to prompt the group member with the group message in the prompting manner corresponding to the relevance.

the application also provides a prompting method of the group message, which comprises the following steps:

Prompting the group member for the current group message and an association between the current group message and the group member.

preferably, the prompting the current group message to the group member includes:

and sending a prompt for checking the current group message to the group members in a prompt mode set corresponding to different levels according to the level of the relevance between the current group message and the group members.

preferably, the prompting mode includes at least one of the following prompting modes:

sending data information of a prompt for checking the current group message to the group members in a short message form;

Sending data information in the form of a vibration to the group members for a prompt to view the current group message;

Sending data information in a flashing form to the group members for a prompt to view the current group message;

sending data information to the group members in a highlighted form to view a prompt for the current group message;

sending data information of a prompt to view the current group message to the group members in a notification bar;

Sending data information of a prompt for viewing the current group message to the group members in a screen locking mode;

sending data information of a prompt to view the current group message to the group members in a voice form;

the content of the prompt comprises a prompt mode and/or the current group message.

Preferably, the sending a prompt to view the current group message to the group member in a prompt manner set corresponding to different levels according to the level of the relevance between the current group message and the group member includes: and sending the prompted data information to the equipment for receiving the current group message by the group members.

Preferably, the prompting the group member of the association between the current group message and the group member includes:

Prompting the relevance evaluation value between the current group message and the group member; and/or the presence of a gas in the gas,

Prompting an association level value between the current group message and the group member.

And sending the associated data information to the equipment of the group member receiving the current group message.

and the prompting unit is used for prompting the current group message and the association between the current group message and the group member to the group member.

obtaining a current group message, wherein the current group message is a message needing to be prompted to group members in a group, and the group comprises at least two group members;

and aiming at least two group members, prompting the group message to the at least two group members in different prompting modes respectively.

preferably, the prompting of the group message to the at least two group members is performed in different prompting manners, where the prompting manners include at least the following two different manners:

sending a prompt for viewing the current group message to the group members in a short message form;

sending a prompt to the group members to view the current group message in a vibratory form;

sending a prompt to the group members to view the current group message in a flashing form;

sending a prompt to the group members in highlighted form to view the current group message;

sending a prompt to the group members in the form of a notification bar to view the current group message;

sending a prompt to the group members to view the current group message in a screen-locked manner;

Sending a prompt to the group members in voice form to view the current group message;

An obtaining unit, configured to obtain a current group message, where the group message is a current message sent to group members in a group, and the group includes at least two group members;

and the prompting unit is used for prompting the group message to at least two group members in different prompting modes respectively.

the application provides an electronic device, including:

a processor;

a memory for storing a program for processing data generated by a network platform, the program when read and executed by the processor performing the following operations:

the present application further provides a storage device, comprising: storing data generated by a network platform and a program for processing the data generated by the network platform;

when read and executed by a processor, the program performs the following operations:

The present application further provides a data processing method, including:

Acquiring a message to be sent to an object in a first set, wherein the first set comprises a plurality of objects;

determining associations between the messages and the plurality of objects respectively;

And sending the message to the object meeting the relevance condition.

Preferably, the determining the association between the message and the plurality of objects respectively includes:

Obtaining the first set of data features, the first set of data features comprising: data features of a plurality of objects in the first set and data features of the first set itself;

Calculating relevance evaluation values between the current message and the plurality of objects in the first set according to the data characteristics of the first set;

And determining the relevance between the current message and the plurality of objects according to the relevance evaluation value.

preferably, the data characteristics of the first set are acquired in at least one of the following ways:

acquiring text data characteristics of the historical messages according to the historical messages in the first set;

acquiring importance data characteristics of the objects in the first set according to the importance of the first set relative to the objects;

Acquiring key word data characteristics according to the historical message segments of the first set;

and acquiring behavior data characteristics according to the historical behavior data information of the objects in the first set.

preferably, the text data characteristic of the history message includes at least one of the following text data characteristics: a feature vector of the historical message text length;

URL feature vectors in the history message text;

picture feature vectors in the historical message text;

And expressing the characteristic vector in the historical message text.

preferably, the importance data characteristic of the object comprises at least one of the following importance data characteristics:

An identity feature vector of the object;

adding the object to the duration feature vector of the first set;

a quantitative feature vector of the object;

an active number feature vector of the object.

preferably, the acquiring the keyword data characteristics according to the historical message segments of the first set comprises:

Aggregating the historical message segments of the objects meeting the aggregation condition to obtain aggregated messages;

extracting historical keywords according to the aggregated message, and determining a message tag of the object;

Taking the historical message segment which is adjacent to the current message and does not accord with the aggregation condition as a breakpoint, and extracting a current keyword in the current aggregation message formed by the current message;

Preferably, the aggregation condition is an interval time between two adjacent history messages sent by the same object in the first set;

the aggregating the historical message segments of the objects meeting the aggregation condition includes:

and judging whether the time interval of the historical message segments meets a set interval threshold, and if so, aggregating the historical message segments of the object meeting the set interval threshold.

Message quantity feature vectors sent by the same object in the first set;

A notified number of feature vectors that the same object is notified of within the first set;

the same object notifies other objects in the first set of the notification quantity feature vector;

the object is closest to the acquired current message, and a time interval characteristic vector of the current message is replied;

the time interval characteristic vector of the object, which is notified when the object is closest to the current message acquisition time.

preferably, the method further comprises the following steps:

and when the number of the acquired data features of the first set is at least two, merging the acquired data features.

preferably, the calculating the association evaluation value between the current message and the object according to the data feature includes:

And calculating the relevance evaluation value of the current message and the object by utilizing a machine learning algorithm.

preferably, the sending the message to the object satisfying the association condition includes:

and judging whether the relevance evaluation value is larger than a set relevance threshold value or not, and if so, executing the step of sending the message to the object meeting the relevance condition.

the present application also provides a data processing apparatus, comprising:

The device comprises a message acquisition unit, a message processing unit and a message processing unit, wherein the message acquisition unit is used for acquiring messages to be sent to objects in a first set, and the first set comprises a plurality of objects;

a determining unit, configured to determine associations between the messages and the plurality of objects, respectively;

And the sending unit is used for sending the message to the object meeting the relevance condition.

Preferably, the determination unit includes:

a data feature obtaining subunit, configured to obtain data features of the first set, where the data features of the first set include: data features of a plurality of objects in the first set and data features of the first set itself;

a calculating subunit, configured to calculate, according to the data features of the first set, association evaluation values between the current message in the first set and the plurality of objects;

and the relevance determining subunit is used for determining the relevance between the current message and the plurality of objects according to the relevance evaluation value.

preferably, the data feature obtaining subunit includes at least one of the following subunits:

the text data acquisition subunit is used for acquiring text data characteristics of the historical messages according to the historical messages in the first set;

the important data acquisition subunit is used for acquiring the important data characteristics of the objects in the first set according to the importance of the first set relative to the objects;

A keyword obtaining subunit, configured to obtain a keyword data feature according to the history message segment of the first set;

and the behavior acquisition subunit acquires behavior data characteristics according to the historical behavior data information of the objects in the first set.

Preferably, the text data acquiring subunit is specifically configured to acquire at least one text data feature including:

a feature vector of the historical message text length;

URL feature vectors in the history message text;

picture feature vectors in the historical message text;

and expressing the characteristic vector in the historical message text.

preferably, the important data acquiring subunit is specifically configured to acquire at least one important data feature including:

an identity feature vector of the object;

Adding the object to the duration feature vector of the first set;

a quantitative feature vector of the object;

an active number feature vector of the object.

preferably, the keyword obtaining subunit includes:

The aggregation subunit is configured to aggregate the historical message segments of the objects that meet the aggregation condition to obtain an aggregated message;

A message tag determining subunit, configured to extract a history keyword according to the aggregated message, and determine a message tag of the object;

the extracting subunit is configured to extract a current keyword in a current aggregated message formed by the current message, with the historical message segment that is adjacent to the current message and does not meet the aggregation condition as a breakpoint;

And the matching subunit is used for matching the current keyword with the message tag to obtain a feature vector of the message tag to which the current keyword belongs, and taking the message tag feature vector as the keyword data feature.

the polymeric subunits comprising:

and the judging subunit is used for judging whether the time interval of the historical message segments meets a set interval threshold, and if so, aggregating the historical message segments of the object meeting the set interval threshold.

Preferably, the behavior obtaining subunit is specifically configured to obtain at least one of the following historical behavior data characteristics:

Message quantity feature vectors sent by the same object in the first set;

preferably, the method further comprises the following steps:

a merging unit, configured to, when the number of the acquired data features of the first set is at least two, merge the acquired data features.

preferably, the calculation subunit calculates the relevance evaluation value of the current message and the object by using a machine learning algorithm.

Preferably, the sending unit includes:

and the judging subunit is used for judging whether the relevance evaluation value is larger than a set relevance threshold value or not, and if so, executing the step of sending the message to the object meeting the relevance condition.

compared with the prior art, the method has the following advantages:

According to the prompting method of the group message, the relevance between the current group message and the group members in the group is determined according to the obtained current group message, after the relevance is determined, the prompting can be sent to the group members according to the relevance between the group members and the current group message, the group members can know whether the current group message is important to the group members in the group or not and need to check according to the prompting, namely the group members can check the group message in the group in time according to the received prompting, the missing of the group message related to the group members is avoided, and the prompting method of the group message provided by the application can send the prompting to the group members in a targeted manner.

According to the prompting method of the group message, the prompting information for prompting the current group message is sent to the group member and the data information of the relevance between the prompting information and the current group message is sent to the group member according to the obtained relevance between the current group message and the group member, so that the group member can determine whether to check the current group message according to the relevance condition, and the relevance is prompted to the group member, so that the group member can know the relevance between the current group message and the group member.

according to the prompting method of the group message, the current group message is prompted to the group members according to the obtained relevance between the current group message and the group members, so that the group members can check the current group message relevant to the group members in time, and the current group message is prevented from being covered by a large number of follow-up messages to cause the trouble in checking the group members.

The application provides a data processing method, which is characterized in that according to the information to be sent to the objects in the first set and the relevance between the information and each object in the first set, the acquired information is sent to the objects in the first set meeting the relevance, so that the information can be sent in a targeted manner according to the relation between the information and the objects, the disturbance of a large number of irrelevant information is avoided, and meanwhile the trouble caused by the fact that the relevant information is covered or not received timely is avoided.

drawings

fig. 1 is a flowchart of an embodiment of a group message prompting method provided in the present application;

FIG. 2 is a flowchart of an embodiment of determining relevance in a group message prompting method provided by the present application;

Fig. 3 is a schematic structural diagram of an embodiment of a group message prompting device provided in the present application;

Fig. 4 is a schematic structural diagram of an embodiment of determining relevance in a group message prompting device provided in the present application;

Fig. 5 is a flowchart of an embodiment of a group message prompting method provided in the present application;

fig. 6 is a schematic structural diagram of an embodiment of a group message prompting device provided in the present application;

FIG. 7 is a flowchart of an embodiment of a group message prompting method provided in the present application;

fig. 8 is a schematic structural diagram of an embodiment of a group message prompting device provided in the present application;

FIG. 9 is a flow chart of an embodiment of a data processing method provided herein;

Fig. 10 is a schematic structural diagram of an embodiment of a data processing apparatus provided in the present application.

Detailed Description

in the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.

in a communication group, a group message sent by a group member in the group is sent to terminal device application software interfaces of all group members, and the group message is not specifically sent to the group members to prompt the group members to view.

the group message prompting method can send out a prompt for correspondingly checking the current group message according to the relevance between each group member in the group and the current group message in the group, so that the group members are prevented from missing the group messages related to the group members, or the group messages related to the group members are submerged by a large amount of irrelevant group messages due to untimely checking.

referring to fig. 1, fig. 1 is a flowchart of an embodiment of a group message prompting method provided by the present application, where the embodiment of the group message prompting method provided by the present application can be described based on an instant messaging software for chat, but the prompting method provided by the present application is not limited to the application scenario of the instant messaging software, and the prompting method provided by the present application can be adopted in a case of interaction in a group with multiple members.

As shown in fig. 1, the method for prompting a group message provided by the present application includes:

step S101: a current group message is obtained, the current group message being a current message sent to group members within a group, the group including at least two group members.

in step S101, the current group message is any current message sent by a group member in the group where the current group message is located, and the current message is sent to each group member in the group. For example: in an application chat software, a plurality of groups can be established, each group can include a plurality of partially or totally identical group members, or partially or totally different group members, each group member can send a group message in the group, and the sent group message can be obtained or received by each group member in the group.

step S102: an association between the current group message and the group member is determined.

the purpose of step S102 is to determine the association between the current group message and the group members in the group, but of course, the association between the current group message and the group members in the group may also be determined as well as the association between the current group message and the partial group members in the group.

In this embodiment, the association between the current group message and the group member may be determined according to the requirements of the group member, for example: the group member may select whether to determine the association between the current group message and the group member, similar to the notification and non-notification that the group member may select the group message, i.e.: the message is not disturbed. The optional determination of the association between the group members and the current group message is not a matter of focus and is, therefore, relatively simple to describe.

please refer to fig. 2 in conjunction with fig. 1, fig. 2 is a flowchart illustrating an embodiment of determining relevance in a group message prompting method provided in the present application.

Specifically, the step S102 of determining the association between the current group message and the group member may include:

Step S102-1: obtaining data characteristics of the cluster, the data characteristics of the cluster including: data characteristics of the group members and data characteristics of the group itself.

the acquiring of the data characteristics of the group includes acquiring data characteristics of the group itself and data characteristics of group members in the group. The data characteristics of the cluster itself include: the time of group establishment, the number of group members, group authority, group level and other related data; the data characteristics of the group members include: data relating to the group members sending messages, the positions of the group members in the group, etc. In this implementation, the acquiring the data characteristic of the group may be according to at least one of the following acquiring manners:

The method a: and acquiring the text data characteristics of the historical group message according to the historical group message of the group.

In the manner a, the obtaining of the text data feature of the history group message may be performed for each history group message in the group, or may be performed for a part of the history group messages, and specifically, the text data feature range of the history group message may be determined by setting an obtaining time range, for example: set 3 months or a certain time period before the current group message reception time, etc.

the method a comprises the following steps of obtaining at least one text data characteristic:

acquiring a feature vector of the historical group message TEXT LENGTH (TEXT _ LENGTH) in the group;

acquiring a URL (CONTAIN _ URL) feature vector in the historical group message text in the group;

Acquiring a PICTURE (CONTAIN _ PICTURE) feature vector in the historical group message text in the group;

and obtaining expression (CONTAIN _ EMOTION) feature vectors in the historical group message texts in the group.

the above description has been given for the case where the text data feature of the history group message is acquired in the above aspect a, and the actually acquired feature vector is not limited to the above description, and the feature vector may be acquired with respect to the text data feature of the history group message in the group.

it should be noted that, in the acquiring of the URL feature vector in the history group message text in the group; or, obtaining picture characteristic vectors in the historical group message texts in the group; or, in the process of acquiring the expression feature vector in the history group message text in the group, the URL feature vector may be acquired according to URL information included in the group message text, or may be acquired only by URL information according to the group message. The picture feature vector may be obtained according to picture information included in the group message text, or may be obtained according to only picture information included in the group message. The expression feature vector may be obtained according to expression information included in the group message text, or may be obtained according to the group message including only expression information. For example: the group message may include one or more combinations of text information and URL information, text information and picture information, and text information and emotion information, and the group message may also include only: the history group message may also include one or more of text information + URL information, text information + picture information, and text information + emotion information.

Mode b: and acquiring the importance data characteristics of the group members in the group according to the importance of the group relative to the group members.

The same feature of acquiring the importance data of the group in the manner b may be acquired for all group members in the group or only for some group members, and when acquiring for some group members, the importance data may be determined by the number of messages sent by the group members in the group, or may be determined according to the time when the group members join the group.

The obtaining of the importance data characteristics of the group members in the group in the mode b may include obtaining at least one of the following importance data characteristics:

obtaining identity (USER _ roll) feature vectors of the group members in the group;

Acquiring a characteristic vector of the time LENGTH (USER _ JOIN _ LENGTH) for the group member to JOIN the group in the group;

obtaining a quantity of group members (TRIBE _ USER _ NUM) feature vector within the group;

Obtaining a number of ACTIVE (TRIBE _ ACTIVE _ USER _ NUM) feature vector for the group members within the group.

In the above obtained feature vector, the identity feature vector may refer to a specific role of the group member in the group, for example: the group member is an administrator, a group owner, or a general group member, and the role of the group member may also be determined according to the actual application scenario of the group, for example: when a group is a workgroup, the roles of the group members may correspond to the actual job positions of the group members, i.e. the identity feature vectors of the group members are determined according to the uses of the different groups.

in the obtaining of the active number feature vector of the group member in the group, the active number refers to how many active group members are in the group, and the active group members may be determined according to the number of messages sent by the group members in the group. The active number is the sum of the number of all active group members within the group.

mode c: and acquiring the data characteristics of the keywords according to the historical message segments of the group.

the history message segment in the manner c may refer to a set of each group message in a certain time period, and in this embodiment, the history message segment may specifically be a history message segment of a group member in the group.

the acquiring of the key data characteristics in the mode c may include:

step c 1: aggregating the historical group message segments of the group members meeting the aggregation condition to obtain an aggregated group message;

The aggregation condition may be an interval time between two adjacent history messages sent by the same group member in the group. The aggregating the historical group message segments of the group members that satisfy the aggregation condition comprises:

and judging whether the time interval of the historical message segments meets a set interval threshold, if so, performing aggregation on the historical message segments of the group members meeting the set interval threshold, and obtaining aggregated group messages.

it should be noted that, for the same group member, the interval time between two adjacent history messages sent by the same group member in the group may not necessarily be adjacent on the display, that is, there are history messages sent by other group members in the middle, and after the history messages sent by the same group member in the group are extracted according to the time sequence, the two adjacent history messages and the interval time between two adjacent history messages can be obtained.

step c 2: extracting historical keywords according to the aggregated group message, and determining message tags of the group members;

in this embodiment, the aggregation condition is the sending interval time between two adjacent history messages of the same group member, and therefore, multiple paragraphs may exist in the aggregated group message. In the step c2, the keywords in the aggregated group message are extracted, and the extraction mode may be a TextRank algorithm, and during the extraction, aggregated group messages (aggregated group message paragraphs) after the aggregation of the historical group message fragments formed by each group member in the group are extracted, so as to determine the message tags of all group members in the group. The message tags may be categorized with respect to the same or similar keywords extracted from aggregated group messages of the same group member, thereby determining the message tags (which may also be chat tags) of the group member.

step c 3: taking the historical group message segment adjacent to the current group message as a breakpoint, and extracting a current keyword in a current aggregation message formed by the current group message;

the plurality of group message segments that may be sent by the group member that sends the current group message in the current aggregated message may also include only the current group message, and then, when the plurality of group message segments are included in the current aggregated message, the keyword extraction is performed on the current aggregated message formed by the plurality of group message segments, or when only the current group message is included in the current aggregated message, the keyword extraction is performed on the current aggregated message formed by the current group message. That is, the current aggregated message is formed by aggregating message segments including the current group message with a history group message segment adjacent to the current group message and not meeting the aggregation condition as a starting point to form the current aggregated message.

It should be noted that the current aggregation message may include a group message sent by any group member, and when extracting a keyword from the current aggregation message formed by a plurality of group message segments, the current aggregation message may be extracted according to a set interval time, that is, the keyword is extracted from the current aggregation message segment formed by the current group message according to the set interval time.

step c 4: matching the current keyword with the message tag to obtain a feature vector of the message tag to which the current keyword belongs, and taking the feature vector of the message tag as the data feature of the keyword.

Mode d: and acquiring behavior data characteristics according to the historical behavior data information of the group members in the group.

the method d mainly aims to obtain the degree of closeness between the group members and the group through historical behavior data information of the group members in the group. In this embodiment, obtaining the historical behavior data feature includes obtaining according to at least one of the following manners:

acquiring a group message quantity characteristic vector sent by the same group member in the group;

Acquiring the notified quantity characteristic vector of the same group member notified in the group;

Acquiring a notification quantity characteristic vector of a same group member notifying other group members in the group;

acquiring the time interval characteristic vector of the group member from the nearest time of the current group message and replying the group message;

and acquiring the time interval characteristic vector of the time interval notified by the closest time of the group member to the current group information acquisition.

note that the above-mentioned notification and notified message may be understood as @ receiver, the notification may be @ a group member @ another group member, the notified message may be @ a group member another group member, or the notification may be that a message sent to a certain group member (notification object) in the group needs to remind another group member of attention, or may be that another group member of attention needs to pay attention; another group member or members that need to be reminded are notified.

the above-mentioned modes a, b, c and d may be arbitrarily combined or may be separately adopted, and when the data features of the group are acquired in a combination form of the above-mentioned modes or the data features of the group are acquired as at least two data feature vectors, the acquired data features may be subjected to merging processing, that is, the acquired feature vectors may be subjected to merging processing. In this embodiment, the merging process of the plurality of data features may also use a machine learning algorithm to fuse the data features.

step S102-2: and calculating the association evaluation value between the current group message and the group member according to the data characteristics.

The purpose of step S102-2 is to obtain a probability of association between the current group message and the group member, which may be embodied by an association evaluation value, i.e., the association evaluation value may be understood as an association probability value.

in this embodiment, the relevance assessment of the current group message to the group members is calculated using a machine learning algorithm, which may be a SVM classifier, a decision tree, a logistic regression or neural network, or the like. In the embodiment of the present application, obtaining an association evaluation value between the current group message and the group member is described by using an SVM classifier.

First, svm (support Vector machine) refers to a support Vector machine, which is a common discrimination method. In the field of machine learning, it is commonly used to perform pattern recognition, classification, and regression analysis. Before calculating the relevance evaluation value between the current group message and the group member, the acquired data characteristics of the group member and the group per se are input into an SVM classifier as sample data for training to obtain training data, and the training data is stored in MultiSVMTrain. And obtaining a relevance evaluation value between the data characteristics and each group member in the training data so as to obtain the trained SVM classifier.

It should be noted that the acquiring of the data characteristics of the group members and the group itself includes the feature vector of the LENGTH of the history group message TEXT (TEXT _ LENGTH), the feature vector of the URL (content _ URL) in the history group message TEXT, the feature vector of the PICTURE in the history group message TEXT (content _ PICTURE), the feature vector of the expression in the history group message TEXT (content _ entity), the feature vector of the identity of the group member (USER _ roll), the feature vector of the duration of the group member joining the group (USER _ JOIN _ LENGTH), the feature vector of the number of the group members (trigger _ USER _ NUM), the feature vector of the ACTIVE number of the group members (trigger _ ACTIVE _ USER _ NUM), the feature vector of the message tag (keyword data feature), the feature vector of the number of the group message, the feature vector of the notified number, the feature vector of the notification number, time interval feature vectors for reply to group messages, time interval feature vectors for notification, and the like, at least one or more combinations of the feature vectors as data features, although the data features are not limited to the above, and data related to groups and group members may be used as data features.

secondly, extracting the data characteristics of the current group message, and inputting the data characteristics of the current group message into a trained SVM classifier as test data.

Finally, according to the SVM classifier, predicting the probability of association between the current group message and the group member according to the stored training data and the received test data (the current group message), namely: obtaining an association evaluation value between the current group message and the group member; the prediction process may be implemented by comparing the training data with the test data (the current group message).

it should be noted that, because the SVM classifier belongs to the existing machine learning model, the description is short.

step S102-3: and endowing the relevance evaluation value to the corresponding relation between the current group message and the group member, and determining the relevance between the current group message and the group member.

the purpose of step S102-3 is to establish a correlation correspondence table between data features and each group member for the stored training data, where the data features are assigned to each group member with a correlation evaluation value before the current group message and the group member are obtained by using an SVM classifier. And inquiring the data characteristics of the training data which are the same as or similar to the data characteristics of the current group message in the corresponding relation table, and further obtaining a corresponding relevance evaluation value.

step S103: and prompting the current group message to the group member according to the relevance between the current group message and the group member.

The purpose of step S103 is to send different levels of prompts to the group members according to the determined relevance between the current group message and the group members, where the prompt may be understood as a prompt for prompting the group members to view the current group message, and because the degree of relevance between the current group message and each group member is different, or in other words, the level of relevance between the current group message and each group member is different, prompt information corresponding to different levels may be sent to the group members according to the relevance levels.

it is understood that the prompting message may be the same message, and the prompting times are set for the same message according to different relevance levels, for example: when the relevance evaluation value or the relevance probability value or the relevance grade value is higher, the prompting times are more; correspondingly, when the relevance evaluation value or the relevance probability value or the relevance grade value is lower, the prompting times are fewer; or different types of prompts are sent according to the higher relevance evaluation value, the higher relevance probability value or the higher relevance grade value, and the prompt type or the prompt mode may include at least one of the following:

Sending a prompt for viewing the current group message to the group members in a short message form; the prompted data information can be a short message text.

sending a prompt to the group members to view the current group message in a vibratory form; the prompted data information can be data for realizing vibration.

Sending a prompt to the group members to view the current group message in a flashing form; the prompted data information can be data realizing flickering.

sending a prompt to the group members in highlighted form to view the current group message; the prompted data information can be data with a highlight device screen.

Sending a prompt to the group members in the form of a notification bar to view the current group message; the prompted data information can be data of a device notification bar.

Sending a prompt to the group members to view the current group message in a screen-locked manner; the prompted data information can be data of screen locking of the equipment.

Sending a prompt to the group members in voice form to view the current group message; the prompted data information may be voice data of the device.

the flashing may be implemented by a notification lamp on the terminal device where the group member is located, for example: a breathing lamp. Other prompt types or prompt modes may also be realized by the terminal device, and certainly, the prompt may also be realized by other devices having a connection relationship with the terminal device where the group member is located, for example: when the terminal device of the group member is a mobile phone, the electronic product such as a computer, a wearable device, or a television, which has a connection relationship with the mobile phone, may also be used as a terminal device for receiving the prompt message, that is, the prompt message may be transmitted to the group member through a carrier.

the data content of the prompt may include a prompt mode and/or the current group message, that is, the prompt may be sent to the group member according to different prompt modes, or the content of the current group message may be sent. For example: after the group member prompted is determined according to the relevance evaluation value, the current group message can be cached, and then the current group message is sent together by sending prompted information, or the current group message enters the cache region according to the operation behavior of the group member on the prompted information, and the current group message corresponding to the prompted information is referred to, or the current group message is referred to by directly entering the current interface of the application platform according to the operation behavior of the group member on the prompted information.

in order to avoid the disturbance of the group member by the group message with low relevance grade to the group member, or because the group member sets a disturbance-free function to avoid the disturbance by the group message, and further causes the missing of the important related group message, when the step S103 prompts the group member with the current group message, the group member may set a prompt according to the relevance grade between the current group message and the group member, for example: and when the relevance evaluation value or the relevance probability value is more than or equal to 50%, giving out a prompt.

When the current group message is presented to the group member in step S103, the presentation information may be not only information of the above presentation type, but also information of relevance between the group member and the current group message, for example: and prompting the group members in a mode of flickering, vibrating and the like on the terminal equipment where the group members are located according to the relevance evaluation value or the relevance grade value, or displaying the relevance evaluation value or the relevance grade value between the current group message and the group members on the terminal equipment where the group members are located to prompt, wherein the group members can visually see the relevance degree between the current group message and the group members, and further determine whether the current group message needs to be checked. The ways for the group members to view the group messages can be various, and the group members can directly view the current group message pages entering the group according to the prompt, and can also jump to the current group message pages in the group to view the current group message pages according to the operation of the relevance degree of the prompt. According to different prompts, different modes for viewing the current group message can be provided, and the details are not repeated again.

The above is a specific description of an embodiment of a group message prompting method provided in the present application, and a specific application scenario of the group message prompting method provided in the present application is described below with reference to the foregoing contents.

based on a group in an instant messaging application platform, the group can be a work group, namely the group is established based on work, members in the group are workers, the group can be a whole company, and the group members are all the workers; or may be a part of a company where the group members are the staff of the department. The method comprises the steps of obtaining a current group message of a group, wherein the current group message is a message sent by a group member in the group, the message can be sent to a device application platform of the group member in the group to be displayed, the group member can set the received group message, and when the association degree of the group message and the group member reaches more than 50%, a prompt is sent. When the group member A sends a message about attendance late in the group, machine learning predicts the attendance late message, predicts the relevance between the attendance late message and each group member in the group, when the relevance evaluation value between the attendance late message and the group member B is predicted to be 6.2, and the relevance evaluation value between the attendance late message and the group member C is predicted to be 5.0, the relevance between the group member B and the group member C and the attendance late message is strong, the terminal equipment where the group member B and the group member C are located respectively receives prompts aiming at the attendance late message, the prompts can comprise the attendance late message content and can also be only a prompt for prompting to check, and the prompting frequency of the group member B can be more than that of the group member C because the relevance degree of the group member B is stronger than that of the group member C, namely: the strength of the cue to the group member B is higher than the strength of the cue to the group member C. It is to be understood that when the group member C sets a cue range, for example: and when the relevance evaluation value is greater than or equal to 5.5, sending a prompt, and the attendance late message does not send a prompt to the group member C.

the above is a description of an embodiment of a group message prompting method provided in the present application, and corresponds to the aforementioned embodiment of a group message prompting method provided in the present application, and the present application also discloses a group message prompting apparatus, please refer to fig. 3, since the apparatus embodiment is basically similar to the method embodiment, the description is relatively simple, and related points can be referred to partial description of the method embodiment. The device embodiments described below are merely illustrative.

as shown in fig. 3, the apparatus for prompting group messages provided in the present application includes:

an obtaining unit 301, configured to obtain a current group message, where the current group message is a current message sent to group members in a group, and the group includes at least two group members.

the specific process of the current group message obtained by the obtaining unit 301 may refer to the specific description of step S101 in the above method, and therefore, the details are not described herein again.

A determining unit 302, configured to determine an association between the current group message and the group member.

The specific implementation process of determining the relevance by the determining unit 302 may be combined with fig. 3, and refer to fig. 4, where fig. 4 is a schematic structural diagram of an embodiment of determining the relevance in a group message prompting device provided in the present application;

the determining unit 302 may include:

an obtaining unit 302-1, configured to obtain data characteristics of the cluster, where the data characteristics of the cluster include: data characteristics of the group members and data characteristics of the group itself;

A calculating unit 302-2, configured to calculate an association evaluation value between the current group message and the group member according to the data feature;

The calculating unit 302-2 calculates the association evaluation value of the current group message and the group member by using a machine learning algorithm.

a corresponding relationship establishing unit 302-3, configured to assign the relevance evaluation value to the corresponding relationship between the current group message and the group member, and determine the relevance between the current group message and the group member.

the obtaining unit 302-1 may obtain the data characteristics of the group by using at least one of the following obtaining subunits:

the text acquiring subunit acquires at least one text data characteristic of:

Obtaining a feature vector of the length of the text in the group;

acquiring URL (uniform resource locator) feature vectors in the texts in the group;

Acquiring picture characteristic vectors in the texts in the group;

And obtaining the expression feature vector in the group text.

and the importance acquiring subunit is used for acquiring the importance data characteristics of the group according to the importance of the group relative to the group members.

The text acquiring subunit acquires at least one text data characteristic of:

Obtaining a feature vector of the length of the text in the group;

acquiring picture characteristic vectors in the texts in the group;

and obtaining the expression feature vector in the group text.

And the keyword acquisition subunit is used for acquiring the keyword data characteristics according to the historical message segments of the group.

the keyword acquisition subunit includes:

The aggregation unit is used for aggregating the historical group message segments of the group members meeting the aggregation condition to obtain an aggregated group message; wherein the aggregation condition is the interval time of sending the historical messages in the group; the polymerization unit includes: and the judging unit is used for judging whether the time interval of the historical message segments meets a set time interval threshold value or not, and if so, aggregating the historical group message segments of the group members meeting the aggregation condition.

the behavior acquisition subunit acquires at least one behavior data characteristic of:

Acquiring a group message quantity characteristic vector sent by the group member in the group;

Acquiring a quantity characteristic vector which contains the notified quantity of the group member in the group message;

acquiring a group message which contains characteristic vectors of the number of the group members informing other group members;

Acquiring a time interval characteristic vector of the group member to the time nearest to the current group message acquisition time for recovering the group message;

and acquiring the time interval characteristic vector of the group member which is notified most recently to the acquisition current group message time.

a prompting unit 303, configured to prompt the group member with the current group message according to the association between the current group message and the group member.

the prompting unit 303 is specifically configured to send prompting information to the group member according to the level of the relevance evaluation value between the current group message and the group member.

the presentation unit 303 includes:

when the data characteristics of the group are at least two, the method further comprises: and the merging unit is used for merging the acquired data characteristics.

the above is a description of an embodiment of a group message prompting device provided in the present application, and the present application also discloses a group message prompting method corresponding to the aforementioned embodiment of the group message prompting method and device provided in the present application, please refer to fig. 5, since the embodiment of the prompting method is basically similar to the above embodiment of the method in fig. 1, the description is relatively simple, and related points can be referred to partial description of the method embodiment. The device embodiments described below are merely illustrative.

as shown in fig. 5, fig. 5 is a flowchart of an embodiment of a group message prompting method provided in the present application; the prompting method comprises the following steps:

Step S501: obtaining a current group message, wherein the current group message is a current message sent to group members in a group, and the group comprises at least two group members;

step S502: determining an association between the current group message and the group member;

Step S503: prompting the group member for the current group message and an association between the current group message and the group member.

the specific implementation process of step S503 may include:

the sending a prompt to view the current group message to the group member in a prompt mode set corresponding to different levels according to the level of the relevance between the current group message and the group member includes: the description of step S103 may be specifically referred to when the prompted data information is sent to the device that receives the current group message.

the prompting mode can comprise at least one of the following modes:

The data content of the alert may include an alert mode and/or the current group message.

For the specific description of the prompting manner, reference may also be made to the specific description of step S103, and details are not repeated here.

the step S503 is to prompt the group member that the association between the current group message and the group member includes at least one of the following data information:

prompting the relevance evaluation value between the current group message and the group member;

The prompting of the relevance evaluation value and/or the relevance level value may be displaying the relevance evaluation value and/or the relevance level value on the terminal device of the group member, that is: displaying the association evaluation value and/or the association level value of the group member and the current group message on the terminal device of the group member, which may be specifically displayed on an application platform of the terminal device, where a specific display position is not specifically limited, and may be in a form that the group member can know the association evaluation value or the level value.

the relevance evaluation value and/or the relevance grade value may be displayed in a text form or a graphic form, for example: when in text form, it may be a percentage, a number, etc.; when graphics are employed, they may be pie charts, graphs, bar charts, and the like. During specific display, the prompt can be displayed on the terminal device or an application platform of the terminal device in a pop-up mode when the prompt is received.

according to the prompting method of the group message, the group members can visually know the association degree of the current group message and the group members according to the prompting association condition, and then whether the group message needs to be checked or not is judged.

based on the above specific description of the embodiment of the group message prompting method provided by the present application, the present application further provides a group message prompting apparatus, and the apparatus corresponds to the description of the method, so that the description is simple, specific contents may refer to the description of the method in fig. 5 or the description of the method in fig. 1, and the following description of the group message prompting apparatus is only illustrative.

referring to fig. 6, fig. 6 is a schematic structural diagram of an embodiment of a group message prompting device provided in the present application, where the group message prompting device includes:

an obtaining unit 601, configured to obtain a current group message, where the current group message is a current message sent to group members in a group, and the group includes at least two group members;

a determining unit 602, configured to determine an association between the current group message and the group member;

a prompting unit 603, configured to prompt the group member with the current group message and the association between the current group message and the group member.

The prompting unit 603 is specifically configured to send a prompt for viewing the current group message to the group members in a prompting manner set according to different levels according to the level of the relevance between the current group message and the group members.

The prompting mode comprises at least one of the following modes:

the prompting unit 603 sends the prompted data information to the device that receives the current group message from the group member.

The prompting unit 603 for prompting the association between the current group message and the group member to the group member includes at least one of the following data information:

the prompting, by the prompting unit 603, to prompt the group member for the association between the current group message and the group member includes:

based on the above, the present application further provides a group message prompting method, please refer to fig. 7, where fig. 7 is a flowchart of an embodiment of the group message prompting method provided in the present application;

The prompting method comprises the following steps:

Step S701: obtaining a current group message, wherein the current group message is a message needing to be prompted to group members in a group, and the group comprises at least two group members;

step S702: and aiming at least two group members, prompting the group message to the at least two group members in different prompting modes respectively.

the specific implementation process of step S702 may include:

the prompting modes comprise at least the following two different modes which respectively prompt the different group members:

Fig. 7 shows a method for prompting a group message provided by the present application, which aims to prompt different group members in the group with a current group message in different prompting manners, for example: the group message which is vacated in 3 months and 8 days can be prompted to all the female members in the group in a vibration mode, and the group message which is vacated can be prompted to all the male members in the group in a flashing mode.

the above is a description of an embodiment of a group message prompting method provided in the present application, and corresponds to the aforementioned embodiment of a group message prompting method provided in the present application, and the present application also discloses a group message prompting apparatus, please refer to fig. 8. The device embodiments described below are merely illustrative.

As shown in fig. 8, fig. 8 is a schematic structural diagram of an embodiment of a group message prompting device provided in the present application, where the prompting device includes:

obtaining unit 801: for obtaining a current group message, the group message being a current message sent to group members within a group, the group comprising at least two group members;

A prompting unit 802, configured to respectively prompt at least two group members with the group message in different prompting manners.

The prompting unit 802 includes: at least two different ways are adopted to respectively prompt the different group members:

the prompting mode comprises at least one of the following modes:

the difference between the group message presentation methods provided in fig. 5 and 7 and the group message presentation apparatuses provided in fig. 6 and 8 is that the presented data information is different, and the group message presentation method provided in fig. 5 presents not only a reminder to present a view but also a reminder to know relevant data information, that is, presents two kinds of data information, to the group member based on the determined relevance. Fig. 6 provides only one type of data information, namely, a prompt to prompt group members to view the current group message.

based on the above, the present application further provides an electronic device, including:

a processor;

Based on the above, a storage device comprising: storing data generated by a network platform and a program for processing the data generated by the network platform;

based on the above, the present application further provides a data processing method, where after a message to be sent is obtained, the relevance between the message and a receiving object is determined, and the message is sent to an object meeting the relevance requirement in a targeted manner according to the relevance, specifically please refer to fig. 9, where fig. 9 is a flowchart of an embodiment of the data processing method provided in the present application.

The data processing method provided by the application comprises the following steps:

step S901: acquiring a message to be sent to an object in a first set, wherein the first set comprises a plurality of objects;

step S902: determining associations between the messages and the plurality of objects respectively;

the specific implementation process of step S902 may include:

wherein the data characteristics of the first set may be obtained in at least one of:

The text data features of the historical messages comprise at least one of the following text data features:

A feature vector of the historical message text length;

URL feature vectors in the history message text;

Picture feature vectors in the historical message text;

and expressing the characteristic vector in the historical message text.

the importance data characteristic of the object comprises at least one of the following importance data characteristics:

An identity feature vector of the object;

Adding the object to the duration feature vector of the first set;

a quantitative feature vector of the object;

an active number feature vector of the object.

The obtaining key data features according to the historical message segments of the first set comprises:

The aggregation condition is the interval time of two adjacent historical messages sent by the same object in the first set;

The historical behavior data characteristics comprise at least one of the following historical behavior data characteristics:

message quantity feature vectors sent by the same object in the first set;

further comprising:

The calculating of the association evaluation value between the current message and the object according to the data feature includes:

Step S903: and sending the message to the object meeting the relevance condition.

the specific implementation process of step S903 may include:

The above description is summarized, and specific contents may refer to specific description of a group message prompting method, which is not repeated herein.

the foregoing detailed description of an embodiment of a data processing method provided by the present application also provides a data processing apparatus, where the apparatus corresponds to the description of the method, and therefore, the description is simple, and the detailed content may refer to the description of the method in fig. 10 or the description of the method in fig. 1, and the following description of the group message prompting apparatus is only illustrative.

fig. 10 is a schematic structural diagram of an embodiment of a data processing apparatus provided in the present application, as shown in fig. 10. The device comprises:

A message obtaining unit 1001, configured to obtain a message to be sent to an object in a first set, where the first set includes multiple objects;

a determining unit 1002, configured to determine associations between the messages and the plurality of objects, respectively;

The determining unit 1002 includes:

the data characteristic acquiring subunit comprises at least one of the following subunits:

the text data acquiring subunit is specifically configured to acquire at least one text data feature including:

A feature vector of the historical message text length;

URL feature vectors in the history message text;

Picture feature vectors in the historical message text;

And expressing the characteristic vector in the historical message text.

the important data acquiring subunit is specifically configured to acquire at least one important data feature including:

An identity feature vector of the object;

adding the object to the duration feature vector of the first set;

a quantitative feature vector of the object;

An active number feature vector of the object.

the keyword acquisition subunit includes:

the polymeric subunits comprising:

the behavior obtaining subunit is specifically configured to obtain at least one of the following historical behavior data characteristics:

Message quantity feature vectors sent by the same object in the first set;

based on the data feature obtaining subunit, when the obtaining of the data features of the first set is at least two, the method may further include:

a merging subunit, configured to, when the number of the acquired data features of the first set is at least two, merge the acquired data features.

the calculation subunit calculates an association evaluation value of the current message with the object, specifically using a machine learning algorithm.

A sending unit 1003, configured to send the message to an object that satisfies the association condition.

the transmission unit includes:

in a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

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

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

Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application, and those skilled in the art can make variations and modifications without departing from the spirit and scope of the present application, therefore, the scope of the present application should be determined by the claims that follow.

Claims

1. a method for prompting a group message is characterized by comprising the following steps:

2. the method of claim 1, wherein the determining the association between the current group message and the group member comprises:

3. the method for prompting group message according to claim 2, characterized in that the data characteristic of the group is obtained according to at least one of the following modes:

4. The method for prompting group message according to claim 3, wherein the text data characteristic of the historical group message includes at least one of the following text data characteristics: a feature vector of the history group message text length;

URL feature vectors in the history group message text;

picture feature vectors in the historical group message text;

and expressing the characteristic vector in the historical group message text.

5. A method for prompting group message according to claim 3, wherein the importance data characteristics of the group members include at least one of the following importance data characteristics:

Identity feature vectors of the group members;

a time length feature vector for the group member to join the group;

a quantity feature vector of the group members;

an active number feature vector for the group member.

6. The method for prompting group message according to claim 3, wherein said obtaining key data characteristics according to the historical message segments of the group comprises:

7. the method for prompting group message according to claim 6, wherein the aggregation condition is an interval time between two adjacent history messages sent by the same group member in the group;

8. a method for prompting group message according to claim 3, wherein the historical behavior data characteristics include at least one of the following:

The group member replies a time interval characteristic vector of the current group message at the closest time to the current group message;

9. the method for prompting group message according to claim 2, wherein the acquiring the data characteristic of the group comprises:

10. the method for prompting group message according to claim 2 or 9, wherein the calculating the association evaluation value between the current group message and the group member according to the data feature comprises:

11. The method of claim 1, wherein the prompting the group member of the current group message according to the association between the current group message and the group member comprises:

12. The method according to claim 1, wherein the prompting the group message to the group member according to the association between the group message and the group member comprises:

13. a group message prompting apparatus, comprising:

14. a method for prompting a group message is characterized by comprising the following steps:

15. the method of claim 14, wherein the prompting the group member of the current group message comprises:

16. the method for prompting group message according to claim 15, wherein the prompting mode includes at least one of the following prompting modes:

17. The method for prompting group message according to claim 15, wherein the sending the prompt to view the current group message to the group member in the prompt mode set corresponding to different levels according to the level of the relevance of the current group message to the group member comprises: and sending the prompted data information to the equipment for receiving the current group message by the group members.

18. The method of claim 14, wherein the prompting the group member of the association between the current group message and the group member comprises:

19. the method for prompting a group message according to claim 16 or 18, wherein the prompting the association between the current group message and the group member to the group member comprises:

20. a group message prompting apparatus, comprising:

21. a method for prompting a group message is characterized by comprising the following steps:

22. the method according to claim 21, wherein the group message is presented to the at least two group members in different presentation manners, the presentation manners include at least the following two different manners:

23. a group message prompting apparatus, comprising:

24. an electronic device, comprising:

A processor;

25. a storage device, comprising: storing data generated by a network platform and a program for processing the data generated by the network platform;

26. a data processing method, comprising:

and sending the message to the object meeting the relevance condition.

27. The data processing method of claim 26, wherein the determining the association between the message and the plurality of objects, respectively, comprises:

28. The data processing method of claim 27, wherein the first set of data characteristics is obtained in at least one of:

29. The data processing method of claim 28, wherein the text data characteristic of the history message comprises at least one of the following text data characteristics:

A feature vector of the historical message text length;

URL feature vectors in the history message text;

picture feature vectors in the historical message text;

and expressing the characteristic vector in the historical message text.

30. the data processing method of claim 28, wherein the importance data characteristic of the object comprises at least one of the following importance data characteristics:

an identity feature vector of the object;

Adding the object to the duration feature vector of the first set;

a quantitative feature vector of the object;

an active number feature vector of the object.

31. the data processing method of claim 28, wherein said obtaining key data characteristics from said first set of historical message segments comprises:

32. The data processing method of claim 31, wherein the aggregation condition is an interval time between two adjacent history messages sent by the same object in the first set;

33. the data processing method of claim 28, wherein the historical behavior data characteristics comprise at least one of the following historical behavior data characteristics:

Message quantity feature vectors sent by the same object in the first set;

34. The data processing method of claim 27, wherein said obtaining the first set of data characteristics comprises:

35. The data processing method according to claim 27 or 34, wherein said calculating an association evaluation value between the current message and the object according to the data feature comprises:

36. the data processing method of claim 26, wherein sending the message to the object satisfying the association condition comprises:

37. a data processing apparatus, comprising: