CN107786414B - Data sending method, device and system - Google Patents
Data sending method, device and system Download PDFInfo
- Publication number
- CN107786414B CN107786414B CN201610718206.7A CN201610718206A CN107786414B CN 107786414 B CN107786414 B CN 107786414B CN 201610718206 A CN201610718206 A CN 201610718206A CN 107786414 B CN107786414 B CN 107786414B
- Authority
- CN
- China
- Prior art keywords
- weight
- emoticon
- interaction process
- data
- expression
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
- H04L51/046—Interoperability with other network applications or services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
- H04L51/10—Multimedia information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/21—Monitoring or handling of messages
- H04L51/214—Monitoring or handling of messages using selective forwarding
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention provides a data sending method, a device and a system, wherein the data sending method comprises the following steps: acquiring the weight of the category expression to which the emoticon used by the user belongs in an interaction process; when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression; and sending the recommended data to the user in the interaction process. According to the scheme, the emoticons used in the instant messaging interaction are analyzed, so that corresponding data can be recommended to the user according to different scenes.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a data transmission method, apparatus, and system.
Background
Most of the existing advertisement recommendation methods applied to the instant messaging system are based on keyword matching, or recommendation is performed after a search content of a user is acquired through a search engine, for example, a push advertisement of a certain chat software is an advertisement recommendation of a related product popped up or displayed in a reserved advertisement space by acquiring cookie (data stored on a local terminal) information stored when the user searches for a commodity in a browser. There are also chat tools that directly identify some words in the content input by the user during the chat process as keywords in a striking manner (e.g., underlined), and the user can obtain related information by clicking or sliding a mouse over the keywords.
The existing advertisement recommendation method applied to the instant communication system is based on the character content input by the user, or the input by the user in a browser and a search engine, or the input in the conversation and chatting processes. On the one hand, the acquisition of the keywords is limited by whether related information stored in a browser and a search engine can be acquired or not, and the randomness exists in the vocabulary input of a user in the searching or conversation process, which may cause that the recommended key information cannot be acquired or is inaccurate; on the other hand, with the development of network technologies and communication tools, interaction modes in the current instant communication system are more and more diversified, except for characters, users more and more communicate in a mode of using voice, expressions or even video messages, so that a single advertisement recommendation method for analyzing text contents is too single, and the interest points of the users cannot be comprehensively discovered.
In an instant messaging system, roles played and situations of a user when interacting with different objects may be greatly different, and the difference of user interest points in a segmentation scene is mostly not considered in the existing scheme.
Disclosure of Invention
The invention provides a data sending method, device and system. Corresponding data can be recommended to the user according to different scenes by analyzing the emoticons used in the instant messaging interaction.
To solve the above technical problem, an embodiment of the present invention provides the following solutions:
a method of transmitting data, comprising:
acquiring the weight of the category expression to which the emoticon used by the user belongs in an interaction process;
when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression;
and sending the recommended data to the user in the interaction process.
The method comprises the following steps of obtaining the weight of the category expression to which the emoticon used by a user belongs in an interaction process:
acquiring the weight of the emoticon used by the user in the interaction process;
and obtaining the weight of the category expression to which the expression symbol belongs according to the weight of the expression symbol.
In the interaction process, the step of obtaining the weight of the emoticon used by the user comprises the following steps:
acquiring basic data of the expression symbols used in a statistical duration before the interactive process starts;
and acquiring the weight of the emoticon used in the interaction process in the basic data, and taking the weight as the weight of the emoticon used by the user in the interaction process.
Wherein the statistical duration is: by the formula
The duration of the obtained numerical value by calculation, wherein the numerical value is rounded and is not less than 1;
wherein a is the basic statistical period, m is the number of times of continuously obtaining the basic data in the nxa time when the basic data is not obtained in the nxa time, a and n are positive integers, and a-nxm2>0。
Wherein the step of obtaining the weight of the emoticon used in the interaction process included in the basic data comprises:
acquiring a first weight of an emoticon used in the interaction process in the basic data with respect to a time distance; the time distance is as follows: the time distance between the use time of the emoticon used in the interaction process and the start time of the interaction process is included in the basic data;
acquiring a second weight of the emoticon used in the interaction process in the basic data; the times are as follows: the number of times of using the emoticon used in the interaction process included in the basic data;
and obtaining the weight of the emoticon used in the interaction process included in the basic data according to the first weight and the second weight.
Wherein the step of obtaining a first weight of an emoticon used in the interaction process included in the basic data with respect to a time distance includes:
by the formula
Obtaining a first weight of an emoticon used in the interaction process included in the basic data with respect to a time distance.
Wherein the step of obtaining a second weight of the emoticon used in the interaction process included in the basic data with respect to the number of times includes:
by the formula
Obtaining a second weight of an emoticon used in the interaction process included in the basic data;
wherein t is the number of times of using the emoticon used in the interaction process included in the basic data.
Wherein the step of obtaining the weight of the emoticon used in the interaction process included in the basic data according to the first weight and the second weight includes:
by the formula:
obtaining the weight of the expression symbol used in the interaction process in the basic data; wherein L is a positive integer.
The step of obtaining the weight of the category expression to which the expression symbol belongs according to the weight of the expression symbol comprises the following steps:
obtaining the sum of the weights of all the emoticons in the category emoticons to which the emoticons belong;
obtaining the sum of the weights of all the emoticons in the basic data;
and taking the ratio of the sum of the weights of all the emoticons in the category expressions to which the emoticons belong to and the sum as the weight of the category expressions to which the emoticons belong.
When the weight of the category expression is greater than a preset value, the step of obtaining recommendation data corresponding to the category expression comprises the following steps:
and when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression from a preset corresponding relation database of the weight of the category expression and the recommendation data.
In the interaction process, the emoticons used by the user are the emoticons which pass the audit and are divided into the category emoticons by category emoticons.
Wherein, the auditing of the emoticons used in the interaction process comprises: whether the emoticon has a label or not, whether the label of the emoticon meets the emoticon label standard or not, whether the emoticon conforms to the meaning expressed by the emoticon image or the animation or not and/or whether attribute information required for online of the emoticon in the instant messaging system is complete or not.
The classifying of the category expression to which the emoticon belongs comprises the following steps: and dividing the checked emoticons according to standard categories, and adding category labels to the emoticons according to the category expressions to which the emoticons belong after the emoticons are online in the instant communication system.
The recommendation data is advertisement data, and the interaction process is an interaction process for interacting by using an instant messaging system.
An embodiment of the present invention further provides a data sending apparatus, including:
the first acquisition module is used for acquiring the weight of the category expression to which the emoticon used by the user belongs in an interaction process;
the second acquisition module is used for acquiring recommendation data corresponding to the category expression when the weight of the category expression is greater than a preset value;
and the sending module is used for sending the recommended data to the user in the interaction process.
The first obtaining module is specifically configured to: acquiring the weight of the emoticon used by the user in the interaction process; and obtaining the weight of the category expression to which the expression symbol belongs according to the weight of the expression symbol.
When the first obtaining module obtains the weight of the emoticon, the first obtaining module is specifically configured to: acquiring basic data of the expression symbols used in a statistical duration before the interactive process starts; and acquiring the weight of the emoticon used in the interaction process in the basic data, and taking the weight as the weight of the emoticon used by the user in the interaction process.
Wherein the statistical duration is: by the formula
The duration of the obtained numerical value by calculation, wherein the numerical value is rounded and is not less than 1;
wherein a is the basic statistical period, m is the number of times of continuously obtaining the basic data in the nxa time when the basic data is not obtained in the nxa time, a and n are positive integers, and a-nxm2>0。
The first obtaining module is specifically configured to, when obtaining the weight of the emoticon:
acquiring a first weight of an emoticon used in the interaction process in the basic data with respect to a time distance; the time distance is as follows: the time distance between the use time of the emoticon used in the interaction process and the start time of the interaction process is included in the basic data;
acquiring a second weight of the emoticon used in the interaction process in the basic data; the times are as follows: the number of times of using the emoticon used in the interaction process included in the basic data;
and obtaining the weight of the emoticon used in the interaction process included in the basic data according to the first weight and the second weight.
Wherein the first obtaining module passes a formula
Obtaining a first weight of an emoticon used in the interaction process included in the basic data with respect to a time distance.
Wherein the first obtaining module passes a formula
Obtaining a second weight of an emoticon used in the interaction process included in the basic data;
wherein t is the number of times of using the emoticon used in the interaction process included in the basic data.
Wherein the first obtaining module is used for obtaining the first data through a formula:
obtaining the weight of the expression symbol used in the interaction process in the basic data; wherein L is a positive integer.
The first obtaining module is specifically configured to, when obtaining the weight of the category expression to which the expression symbol belongs according to the weight of the expression symbol: obtaining the sum of the weights of all the emoticons in the category emoticons to which the emoticons belong; obtaining the sum of the weights of all the emoticons in the basic data; and taking the ratio of the sum of the weights of all the emoticons in the category expressions to which the emoticons belong to and the sum as the weight of the category expressions to which the emoticons belong.
The second obtaining module is specifically configured to: and when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression from a preset corresponding relation database of the weight of the category expression and the recommendation data.
Wherein, the sending device of the data also includes:
the expression symbol management module is used for auditing the expression symbols used in the interaction process and dividing the category expressions to which the expression symbols belong;
wherein the auditing of the emoticons used in the interaction process comprises: whether the emoticon has a label or not, whether the label of the emoticon accords with the emoticon standard or not, whether the emoticon accords with the meaning expressed by the emoticon image or the animation or not and/or whether attribute information required by the emoticon to be online in the instant messaging system is complete or not;
the classification of the category expression to which the emoticon belongs includes: and dividing the checked emoticons according to standard categories, and adding category labels to the emoticons according to the category expressions to which the emoticons belong after the emoticons are online in the instant communication system.
The recommendation data is advertisement data, and the interaction process is an interaction process for interacting by using an instant messaging system.
An embodiment of the present invention further provides a data processing system, including: an instant messaging system and a device for sending data as described above.
The scheme of the invention at least comprises the following beneficial effects:
according to the scheme, the weight of the category expression to which the emoticon used by the user belongs in the interaction process is obtained; when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression; and sending the recommended data to the user in the interaction process. By analyzing the emoticons used in the instant messaging interaction, corresponding data can be recommended to the user according to different scenes, and the accuracy of sending the recommended data is improved.
Drawings
FIG. 1 is a flow chart of a method of sending data according to the present invention;
FIG. 2 is a flow chart of a data transmission apparatus according to the present invention;
FIG. 3 is a block diagram of a system according to the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention provides a data transmission method, including:
in the interaction process, the emoticons used by the user are the emoticons which pass the audit and are divided into the category emoticons.
Wherein, the auditing of the emoticons used in the interaction process comprises: whether the emoticon has a label or not, whether the label of the emoticon meets the emoticon label standard or not, whether the emoticon conforms to the meaning expressed by the emoticon image or the animation or not and/or whether attribute information required for online of the emoticon in the instant messaging system is complete or not.
The classifying of the category expression to which the emoticon belongs comprises the following steps: dividing the checked emoticons according to standard categories, and adding category labels to the emoticons according to category expressions to which the emoticons belong after the emoticons are online in the instant communication system;
the formulation of emoticons, labels of category emoticons, requires the use of a predominantly lexical, ideographic, unambiguous vocabulary, examples of which are as follows:
example of storage field for emoticon:
| field(s) | Description of the invention |
| emUrl | Identifying actual storage paths for emoticons |
| emName | Name for identifying emoticon |
| emTag | Label for identifying emoticon |
| emClass | Identifying categories of emoticons |
| emPrice | Identifying emoticon prices |
| emSource | Identifying emoticon sources or authors |
the recommendation data can be advertisement data but is not limited to the advertisement data, and the interaction process can be an interaction process of using an instant messaging system for interaction; but not limited to, instant messaging systems;
and step 13, sending the recommended data to the user in the interactive process.
According to the embodiment of the invention, the weight of the category expression to which the emoticon used by the user belongs in the interaction process is obtained; when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression; and sending the recommended data to the user in the interaction process. By analyzing the emoticons used in the instant messaging interaction, corresponding data can be recommended to the user according to different scenes, and the accuracy of sending the recommended data is improved.
In an embodiment of the present invention, the step 11 may include:
step 111, acquiring the weight of the emoticon used by the user in the interaction process;
and step 112, obtaining the weight of the category expression to which the expression symbol belongs according to the weight of the expression symbol.
The step 111 may specifically include:
1111, acquiring basic data of the expression symbols used within a statistical duration before the interactive process starts; wherein the statistical duration is: by the formula
The duration of the obtained numerical value by calculation, wherein the numerical value is rounded and is not less than 1;
wherein a is the basic statistical period, m is the number of times of continuously obtaining the basic data in the nxa time when the basic data is not obtained in the nxa time, a and n are positive integers, and a-nxm2>0；
For example, a basic statistical period is set to a days, the statistical period is adjusted to be integer multiples of a according to specific conditions, namely n × a days, all expression use conditions in n × a days ahead from the starting time of the current conversation are used as basic data, and if no conversation exists in n × a days, the basic statistical period is pushed forward
Days, where m is the forward reckoning number,
and the calculated value is rounded and is not less than 1. If no data exists after forward calculation for m times, the new relation is regarded as a new relation, and the new relation can be subjected to a first dialogue in a traditional data recommendation mode;
step 1112, obtaining weights of the emoticons used in the interaction process included in the basic data, as the weights of the emoticons used by the user in the interaction process;
specifically, the step 1112 may include:
step 11121, obtaining a first weight of an emoticon used in the interaction process in the basic data with respect to a time distance; the time distance is as follows: the time distance between the use time of the emoticon used in the interaction process and the start time of the interaction process is included in the basic data;
in the statistical period, the closer the time point of use of a certain expression symbol is to the start time of the current conversation, the greater the weight occupied by the expression is, and the forward calculation times m in the period calculation in the system are used as the calculation factor of the time distance;
by the formula
Obtaining a first weight of an emoticon used in the interaction process and included in the basic data, wherein the first weight is related to a time distance;
step 11122, obtaining a second weight of the emoticon used in the interaction process included in the basic data with respect to the number of times; the times are as follows: the number of times of using the emoticon used in the interaction process included in the basic data;
by the formula
Obtaining a second weight of an emoticon used in the interaction process included in the basic data;
wherein t is the number of times of using the emoticon used in the interaction process included in the basic data;
step 11123, obtaining the weight of the emoticon used in the interaction process included in the basic data according to the first weight and the second weight;
by the formula:
obtaining the weight of the expression symbol used in the interaction process in the basic data; wherein L is a positive integer.
Step 112 may specifically include:
step 1121, obtaining the sum of the weights of all the expression symbols in the category expressions to which the expression symbols belong;
step 1122, obtaining the sum of the weights of all the emoticons in the basic data;
step 1123, taking the ratio of the sum of the weights of all the emoticons in the category expressions to which the emoticons belong to and the sum as the weight of the category expressions to which the emoticons belong.
Specifically, the storage fields of the emoticon weight and the weight of the category emotion are as follows:
| field(s) | Description of the invention |
| emTag | Label for identifying emoticon |
| emClass | Identifying categories of emoticons |
| emWeight | Identifying weight values of certain emoticons over a statistical duration |
| emClassWeight | Representing the weight value of certain category expression in the whole statistical time length |
In an embodiment of the present invention, the step 12 may include: and when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression from a preset corresponding relation database of the weight of the category expression and the recommendation data.
If the expression weight classified as expressing love class is larger in the interaction process of the user A and the user B through calculation, the A can be used as a main body, and the 'love' component in the relation of the A to the B is judged to be larger.
If the expression weight of A classified as expression thank you is larger in the interaction process of A and C, then it can be judged that A receives some help from C and hopes to express thank you. If the weight of the expression type corresponding to the expression in the current interaction process is judged to be larger than a preset value, recommending the advertisement content corresponding to the expression type to the user;
if a is in a conversation with D, using an expression weight classified as expressing motion, health class is large, it can be inferred that a wants D to remain healthy or is more concerned about the life health issue of D.
According to factors such as product positioning, target users and the like in practical application, certain relationships or scenes can be emphasized, and results are more prone. If a communication product is used, a user mainly plays family relatives and cares about the life of the old, the weight of sports and health expression exceeds 0.1, namely the communication product is used as the most main recommendation basis.
The main output results of the relation and scenario judgment are as follows:
| field(s) | Description of the invention |
| userTarget | Identifying conversation objects |
| userRelation | There may be multiple relationships or dialog scenarios inferred by the identification system |
In the embodiment of the invention, different data contents are recommended according to different conversation relations and scenes. If the main relationship between the users A and B is 'love', the advertisement content of the user A is recommended to be related to 'love', such as a theme restaurant, a double tour, a holiday gift and the like, in a conversation interface between the user A and the user B. And in the conversation interface between A and C, because the analysis module judges that A pays more attention to the health problem of C, advertising contents related to health, such as health products, nutriments and the like, of A are recommended. Therefore, a more detailed content recommendation mode according to the user relationship and the situation is realized. And according to the consumption habit of the user using the expression, the value-added service and other related products can be recommended to the user.
According to the embodiment of the invention, the expression symbol names are marked, such as adding the expression symbol labels to the expression symbols, marking the categories to which the expression symbols belong, such as adding the type labels to the category expressions, and the expression symbols are checked, so that the accuracy of the expression symbols is ensured, the use analysis of the expression symbols is further ensured to be accurate, and accurate advertisement content recommendation is provided. In addition, the embodiment of the invention is used as a supplement to an advertisement content recommendation mode in an instant messaging system, and by analyzing the expression using condition of the user, the interest points of the user can be mastered more comprehensively, so that the advertisement recommendation content is more comprehensive.
As shown in fig. 2, an embodiment of the present invention further provides a data transmitting apparatus, including:
the first acquisition module is used for acquiring the weight of the category expression to which the emoticon used by the user belongs in an interaction process;
the second acquisition module is used for acquiring recommendation data corresponding to the category expression when the weight of the category expression is greater than a preset value;
and the sending module is used for sending the recommended data to the user in the interaction process.
Further, the apparatus further comprises:
the expression symbol management module is used for auditing the expression symbols used in the interaction process and dividing the category expressions to which the expression symbols belong;
wherein the auditing of the emoticons used in the interaction process comprises: whether the emoticon has a label or not, whether the label of the emoticon accords with the emoticon standard or not, whether the emoticon accords with the meaning expressed by the emoticon image or the animation or not and/or whether attribute information required by the emoticon to be online in the instant messaging system is complete or not;
the classification of the category expression to which the emoticon belongs includes: and dividing the checked emoticons according to standard categories, and adding category labels to the emoticons according to the category expressions to which the emoticons belong after the emoticons are online in the instant communication system.
The recommendation data is advertisement data, and the interaction process is an interaction process for interacting by using an instant messaging system.
The first obtaining module is specifically configured to: acquiring the weight of the emoticon used by the user in the interaction process; and obtaining the weight of the category expression to which the expression symbol belongs according to the weight of the expression symbol.
When the first obtaining module obtains the weight of the emoticon, the first obtaining module is specifically configured to: acquiring basic data of the expression symbols used in a statistical duration before the interactive process starts; and acquiring the weight of the emoticon used in the interaction process in the basic data, and taking the weight as the weight of the emoticon used by the user in the interaction process.
Wherein the statistical duration is: by the formula
The duration of the obtained numerical value by calculation, wherein the numerical value is rounded and is not less than 1;
wherein a is the basic statistical period, m is the number of times of continuously obtaining the basic data in the nxa time when the basic data is not obtained in the nxa time, a and n are positive integers, and a-nxm2>0。
The first obtaining module is specifically configured to, when obtaining the weight of the emoticon:
acquiring a first weight of an emoticon used in the interaction process in the basic data with respect to a time distance; the time distance is as follows: the time distance between the use time of the emoticon used in the interaction process and the start time of the interaction process is included in the basic data;
acquiring a second weight of the emoticon used in the interaction process in the basic data; the times are as follows: the number of times of using the emoticon used in the interaction process included in the basic data;
and obtaining the weight of the emoticon used in the interaction process included in the basic data according to the first weight and the second weight.
Wherein the first obtaining module passes a formula
Obtaining a first weight of an emoticon used in the interaction process included in the basic data with respect to a time distance.
Wherein the first obtaining module passes a formula
Obtaining a second weight of an emoticon used in the interaction process included in the basic data;
wherein t is the number of times of using the emoticon used in the interaction process included in the basic data.
Wherein the first obtaining module is used for obtaining the first data through a formula:
obtaining the weight of the expression symbol used in the interaction process in the basic data; wherein L is a positive integer.
The first obtaining module is specifically configured to, when obtaining the weight of the category expression to which the expression symbol belongs according to the weight of the expression symbol: obtaining the sum of the weights of all the emoticons in the category emoticons to which the emoticons belong; obtaining the sum of the weights of all the emoticons in the basic data; and taking the ratio of the sum of the weights of all the emoticons in the category expressions to which the emoticons belong to and the sum as the weight of the category expressions to which the emoticons belong.
The second obtaining module is specifically configured to: and when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression from a preset corresponding relation database of the weight of the category expression and the recommendation data.
In a specific implementation, when the apparatus interacts with an instant messaging system, as shown in fig. 3, the apparatus includes:
the emoticon management module is mainly used for managing emoticons which can be used in the instant communication system. The method comprises online examination of the emoticons, classification of the category expressions and the like.
Information acquisition module (i.e., the first acquisition module described above): the method is mainly responsible for docking the communication function of the instant communication system, realizing the statistics of the emoticons used by the user in the interaction process and obtaining basic data.
Expression use analysis module (i.e., the second obtaining module described above): and the system is responsible for analyzing the use conditions of various types of emoticons counted in the information acquisition module and deducing the relationships among users, the current chat scene, the emotion use preference, the consumption habits and the like.
Advertisement content recommendation module (i.e. the sending module): and matching the appropriate recommendation data according to the result obtained by the analysis module, and recommending to the user.
The detailed functions of the modules in the system are explained as follows:
the expression symbol management module: the emoticon used by the instant communication system is checked and on-line through the module, and the checking content mainly comprises:
1. whether the emoticon has a label;
2. whether the emoticon labels meet relevant specifications;
3. whether the expression meaning of the expression label is consistent with that of the expression image or the animation;
4. whether other information required by the online emoticon is complete or not, such as whether the information is charged or not, price, author and the like;
in addition, the emoticons management module can also divide the audited emoticons into a plurality of categories according to standard categories, classify the emoticons expressing similar emotions into a category, shield subtle differences for the next advertisement content recommendation work while ensuring the richness of the emoticons, and facilitate analysis and processing. The classification can be determined according to the requirements of each product, and category labels are added on the expression symbols on line or in subsequent maintenance according to the expression labels.
The business flexibility is ensured by the multilayer corresponding relation of the name to the label and the category, and the division mode more suitable for product positioning can be customized in different instant messaging systems.
The formulation of the expression labels and the category labels requires the use of main-stream vocabularies with clear ideographical meanings and no ambiguity, and the instant messaging products using the system can be customized according to product positioning and target users, and the simple examples are as follows:
| expression label | Category of belongings label |
| Thank you, thank you and thank you | Expressing the category of metabolic disorders |
| Good night, turning off light, rest and dreaming | Expressing resting classes |
| Thinking, thinking and thinking of you | Expressing thoughts |
Example of attribute field storing emoticon:
and the information acquisition module is used for counting the use conditions of all the emoticons of the user in the interaction process. For each dialog relationship, it is recorded separately. For example, the use conditions of the emoticons in all the interaction processes in the period of time A and B, and the use conditions of the emoticons in all the interaction processes in the period of time A and C are recorded respectively.
The expression symbol use condition in the information acquisition module, the example of the main statistical field is as follows:
| field(s) | Description of the invention |
| emTag | Label for identifying emoticon |
| emTime | Identifying a point in time in the conversation at which the emoticon was first used |
| emTarget | Identifying with which object the emoticon was used in a conversation |
| enCount | Identifying the number of times the emoticon was used in the session |
The expression use analysis module deduces the relationship and the situation in the user interaction, the preference of the user, the consumption habit and the like according to the statistical data of the information acquisition module and the combination of the attribute of the expression.
In the information acquisition module, a basic statistical period is set as a days, and the statistical period can be adjusted to be an integral multiple of a according to specific conditions, namely n × a days.
Using all expression use conditions in n x a days ahead from the start time of the conversation as basic data, and if no conversation exists in n x a days, then pushing forward
Days, where m is the forward reckoning number,
and the calculated value is rounded and is not less than 1. If no data exists, the relationship is regarded as a new relationship. The new relationship adopts a traditional data recommendation mode.
In the statistical period, the closer the time point of a certain expression is used to the current conversation time, the greater the weight of the expression is. The forward estimation number m is used as the calculation factor of the time and distance in the system, and the weight is set to be
In the counting period, the more times of using a certain expression, the greater the weight of the expression. Let t denote the number of times a certain expression is used in a certain dialog, the weight is set to
Obtaining the weight of each emoticon about the using times in the basic data, and obtaining the weight of a certain emoticon in the mth expansion as
If the total calculation is carried out forward for L times, the weight of a certain expression symbol in the whole statistical duration is as follows:
and the proportion of the weighted values of all the expression symbols in a certain category of expressions to the sum of the weighted values of all the expressions is the weight of the category of expressions.
After obtaining the weight of an emoticon and the weight of an expression of a certain category in the basic data,
the weight calculation output results of the expression symbols and the category expressions are as follows:
| field(s) | Description of the invention |
| emTag | Label for identifying emoticon |
| emClass | Identifying categories of emoticons |
| emWeight | Identifying a weighted value of a certain expression within a whole statistical duration |
| emClassWeight | Representing the weight value of a certain type of expression within the whole statistical time length |
If it is found through calculation that the expression weight classified as expressing love class is large when the user A uses the dialogue with the user B, the relation of the user A to the user B can be judged that the love component is large by taking the user A as the main body.
If a is in a dialogue with C and the expression weight classified as expression thank you is large, it can be judged that a receives some help from C and wants to express thank you. If the weight of the expression type corresponding to the expression in the current conversation is judged to be larger than a preset value, recommending the advertisement content corresponding to the expression type to the user;
if A is in a conversation with D, the expression weight classified as expressing motion, health class is large, then it can be inferred that A wants D to remain healthy or is more concerned about D's health problems;
according to factors such as product positioning, target users and the like in practical application, certain relationships or scenes can be emphasized, and results are more prone. If a communication product is used, a user mainly plays family relatives and cares about the life of the old, the weight of sports and health expression exceeds 0.1, namely the communication product is used as the most main recommendation basis.
The main output results of the relation and scenario judgment are as follows:
| field(s) | Description of the invention |
| userTarget | Identifying conversation objects |
| userRelation | There may be multiple relationships or dialog scenarios inferred by the identification system |
In addition, if the fact that the weight of using certain type of expressions is larger in the conversation process of using a certain communication product is found, the fact that the user prefers to use the type of expressions can be judged, the type of expressions can be recommended to the user in the content recommending module, user experience is improved, the user is guided to use more expression symbols, and therefore the accuracy of the system based on expression judgment is improved.
Simple judgment on the consumption habits, if the user uses the pay expression, the user can be known to have the use habits of purchasing value-added products or consuming on the Internet, and the use habits can be used as reference factors for recommending the advertisement content.
And adding categories corresponding to the expression categories for each piece of advertisement content in the advertisement content database, and recommending the advertisement content under the corresponding categories to the user according to the output result of the analysis module. The specific recommendation mode and the number of the pieces can be determined according to the design of the instant messaging product.
The system recommends different contents according to different conversation relations and scenes. If the main relationship between the users A and B is 'love' obtained in the analysis module, the advertisement content of the users A is recommended to be related to 'love' in a conversation interface between the users A and B, such as a theme restaurant, a double tour, a holiday gift and the like. And in the conversation interface between A and C, because the analysis module judges that A pays more attention to the health problem of C, advertising contents related to health, such as health products, nutriments and the like, of A are recommended. Therefore, a more detailed content recommendation mode according to the user relationship and the situation is realized. And according to the consumption habit of the user using the expression, the value-added service and other related products can be recommended to the user.
As shown in fig. 3, an embodiment of the present invention further provides a data processing system, including: an instant messaging system and a device for sending data as described above.
The system provided by the invention is used as a supplement of an advertisement content recommendation mode in an instant messaging system, and by analyzing the condition that the user uses the emoticon, the interest points of the user can be mastered more comprehensively, so that the advertisement recommendation content is more comprehensive. The method analyzes the mutual relation and the change of the conversation scene when the subject has a conversation with different objects, realizes that the user more pertinently pushes different contents in the interaction process with different objects, and realizes a more efficient and more personalized advertisement content recommendation mode.
The expressions which can be downloaded and used in the system can be basically marked in a file name mode, and then the file names can be corresponding to a set of relatively standardized labels to form the basis of expression analysis, further, the relationship among chat users, the current interaction situation, the user preference and even the user consumption habit and other information can be deduced according to the expression, the deficiency that recommendation key information is obtained only by means of texts is supplemented, the user preference is better grasped, and the user relationship and the interaction scene are combined, and the consumption habit and other factors are considered to carry out more targeted recommendation of the advertisement content of the scene is further subdivided.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (19)
1. A method for transmitting data, comprising:
acquiring basic data of the expression symbols used in a statistical duration before the start of the interactive process; acquiring the weight of the emoticon used in the interaction process in the basic data, wherein the weight of the emoticon used by the user in the interaction process comprises the following steps: acquiring a first weight of an emoticon used in the interaction process in the basic data with respect to a time distance; the time distance is the time distance between the use time of the emoticon used in the interaction process and the start time of the interaction process, wherein the use time of the emoticon is included in the basic data; acquiring a second weight of the emoticon used in the interaction process in the basic data; the times are the use times of the emoticons used in the interaction process and included in the basic data; obtaining the weight of the emoticon used in the interaction process included in the basic data according to the first weight and the second weight;
obtaining the weight of the category expression to which the expression symbol used by the user belongs according to the weight of the expression symbol, wherein the weight comprises the following steps: obtaining the sum of the weights of all the emoticons in the category emoticons to which the emoticons belong; obtaining the sum of the weights of all the emoticons in the basic data; taking the ratio of the sum of the weights of all the emoticons in the category expressions to which the emoticons belong to and the sum as the weight of the category expressions to which the emoticons belong;
when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression;
and sending the recommended data to the user in the interaction process.
2. The method according to claim 1, wherein the statistical duration is: by the formula
The duration of the obtained numerical value by calculation, wherein the numerical value is rounded and is not less than 1;
wherein a is the basic statistical period, m is the number of times of continuously obtaining the basic data in the nxa time when the basic data is not obtained in the nxa time, a and n are positive integers, and a-nxm2>0。
3. The data transmission method according to claim 1, wherein the step of obtaining a first weight of an emoticon used in the interaction process included in the basic data with respect to a time distance includes:
by the formula
Obtaining a first weight of an emoticon used in the interaction process included in the basic data with respect to a time distance.
4. The data transmission method according to claim 3, wherein the step of obtaining a second weight of an emoticon used in the interaction process included in the basic data with respect to a number of times includes:
by the formula
Obtaining a second weight of an emoticon used in the interaction process included in the basic data;
wherein t is the number of times of using the emoticon used in the interaction process included in the basic data.
5. The data transmission method according to claim 4, wherein the step of obtaining the weight of the emoticon used in the interaction process included in the basic data according to the first weight and the second weight includes:
by the formula:
obtaining the weight of the expression symbol used in the interaction process in the basic data; wherein L is a positive integer.
6. The data transmission method according to claim 1, wherein when the weight of the category expression is greater than a preset value, the step of obtaining the recommendation data corresponding to the category expression comprises:
and when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression from a preset corresponding relation database of the weight of the category expression and the recommendation data.
7. The data transmission method according to claim 1, wherein in the interaction process, the emoticon used by the user is an emoticon that is approved and classified into category emoticons.
8. The data transmission method according to claim 7, wherein the auditing of the emoticon used in the interaction process includes: whether the emoticon has a label or not, whether the label of the emoticon meets the emoticon label standard or not, whether the emoticon conforms to the meaning expressed by the emoticon image or the animation or not and/or whether attribute information required for online of the emoticon in the instant messaging system is complete or not.
9. The data transmission method according to claim 7, wherein the classifying of the category expression to which the emoticon belongs includes: and dividing the checked emoticons according to standard categories, and adding category labels to the emoticons according to the category expressions to which the emoticons belong after the emoticons are online in the instant communication system.
10. The method according to any one of claims 1 to 9, wherein the recommended data is advertisement data, and the interactive process is an interactive process for interacting using an instant messaging system.
11. An apparatus for transmitting data, comprising:
the first acquisition module is used for acquiring basic data of the expression symbols used within a statistical duration before the interactive process starts; acquiring the weight of the emoticon used in the interaction process in the basic data, and taking the weight as the weight of the emoticon used by the user in the interaction process; the method comprises the following steps: acquiring a first weight of an emoticon used in the interaction process in the basic data with respect to a time distance; the time distance is the time distance between the use time of the emoticon used in the interaction process and the start time of the interaction process, wherein the use time of the emoticon is included in the basic data; acquiring a second weight of the emoticon used in the interaction process in the basic data; the times are the use times of the emoticons used in the interaction process and included in the basic data; obtaining the weight of the emoticon used in the interaction process included in the basic data according to the first weight and the second weight;
the first obtaining module is specifically configured to, when obtaining the weight of the category expression to which the expression symbol belongs according to the weight of the expression symbol: obtaining the sum of the weights of all the emoticons in the category emoticons to which the emoticons belong; obtaining the sum of the weights of all the emoticons in the basic data; taking the ratio of the sum of the weights of all the emoticons in the category expressions to which the emoticons belong to and the sum as the weight of the category expressions to which the emoticons belong;
the second acquisition module is used for acquiring recommendation data corresponding to the category expression when the weight of the category expression is greater than a preset value;
and the sending module is used for sending the recommended data to the user in the interaction process.
12. The apparatus for transmitting data according to claim 11, wherein the statistical duration is: by the formula
The duration of the obtained numerical value by calculation, wherein the numerical value is rounded and is not less than 1;
wherein a is the basic statistical period, m is the number of times of continuously obtaining the basic data in the nxa time when the basic data is not obtained in the nxa time, a and n are positive integers, and a-nxm2>0。
13. The apparatus for transmitting data according to claim 11,
the first obtaining module passes a formula
Obtaining a first weight of an emoticon used in the interaction process included in the basic data with respect to a time distance.
14. The apparatus for transmitting data according to claim 13,
the first obtaining module passes a formula
Obtaining a second weight of an emoticon used in the interaction process included in the basic data;
wherein t is the number of times of using the emoticon used in the interaction process included in the basic data.
15. The apparatus for transmitting data according to claim 14,
the first obtaining module is used for obtaining the first data through a formula:
obtaining the weight of the expression symbol used in the interaction process in the basic data; wherein L is a positive integer.
16. The apparatus for sending data according to claim 11, wherein the second obtaining module is specifically configured to: and when the weight of the category expression is larger than a preset value, obtaining recommendation data corresponding to the category expression from a preset corresponding relation database of the weight of the category expression and the recommendation data.
17. The apparatus for transmitting data according to claim 11, further comprising:
the expression symbol management module is used for auditing the expression symbols used in the interaction process and dividing the category expressions to which the expression symbols belong;
wherein the auditing of the emoticons used in the interaction process comprises: whether the emoticon has a label or not, whether the label of the emoticon accords with the emoticon standard or not, whether the emoticon accords with the meaning expressed by the emoticon image or the animation or not and/or whether attribute information required by the emoticon to be online in the instant messaging system is complete or not;
the classification of the category expression to which the emoticon belongs includes: and dividing the checked emoticons according to standard categories, and adding category labels to the emoticons according to the category expressions to which the emoticons belong after the emoticons are online in the instant communication system.
18. The apparatus according to any one of claims 11 to 17, wherein the recommendation data is advertisement data, and the interactive process is an interactive process for interacting using an instant messaging system.
19. A system for processing data, comprising: an instant messaging system and a device for transmitting data as claimed in any one of claims 11 to 18.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610718206.7A CN107786414B (en) | 2016-08-24 | 2016-08-24 | Data sending method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610718206.7A CN107786414B (en) | 2016-08-24 | 2016-08-24 | Data sending method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107786414A CN107786414A (en) | 2018-03-09 |
| CN107786414B true CN107786414B (en) | 2021-01-15 |
Family
ID=61393191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610718206.7A Active CN107786414B (en) | 2016-08-24 | 2016-08-24 | Data sending method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107786414B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109412935B (en) * | 2018-10-12 | 2021-12-07 | 北京达佳互联信息技术有限公司 | Instant messaging sending method, receiving method, sending device and receiving device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1996362A (en) * | 2006-01-01 | 2007-07-11 | 腾讯科技（深圳）有限公司 | System and method for playing advertisement data in course of instant communication |
| CN102523502A (en) * | 2011-12-15 | 2012-06-27 | 四川长虹电器股份有限公司 | Intelligent television interaction system and interaction method |
| CN102946491A (en) * | 2012-11-23 | 2013-02-27 | 广东欧珀移动通信有限公司 | Method and system for automatically adjusting wallpaper according to user mood |
| CN104574005A (en) * | 2015-02-15 | 2015-04-29 | 蔡耿新 | Advertisement display management system integrating augmented reality, somatic sense and green screening technology and advertisement display management method integrating augmented reality, somatic sense and green screening technology |
| CN104917669A (en) * | 2015-05-29 | 2015-09-16 | 北京搜狗科技发展有限公司 | Information processing method and device |
| CN105095286A (en) * | 2014-05-14 | 2015-11-25 | 腾讯科技（深圳）有限公司 | Page recommendation method and device |
| CN105512945A (en) * | 2015-12-24 | 2016-04-20 | 小米科技有限责任公司 | Social network interaction information processing method and device |
| CN105763431A (en) * | 2016-05-06 | 2016-07-13 | 腾讯科技（深圳）有限公司 | Information pushing method, device and system |
-
2016
- 2016-08-24 CN CN201610718206.7A patent/CN107786414B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1996362A (en) * | 2006-01-01 | 2007-07-11 | 腾讯科技（深圳）有限公司 | System and method for playing advertisement data in course of instant communication |
| CN102523502A (en) * | 2011-12-15 | 2012-06-27 | 四川长虹电器股份有限公司 | Intelligent television interaction system and interaction method |
| CN102946491A (en) * | 2012-11-23 | 2013-02-27 | 广东欧珀移动通信有限公司 | Method and system for automatically adjusting wallpaper according to user mood |
| CN105095286A (en) * | 2014-05-14 | 2015-11-25 | 腾讯科技（深圳）有限公司 | Page recommendation method and device |
| CN104574005A (en) * | 2015-02-15 | 2015-04-29 | 蔡耿新 | Advertisement display management system integrating augmented reality, somatic sense and green screening technology and advertisement display management method integrating augmented reality, somatic sense and green screening technology |
| CN104917669A (en) * | 2015-05-29 | 2015-09-16 | 北京搜狗科技发展有限公司 | Information processing method and device |
| CN105512945A (en) * | 2015-12-24 | 2016-04-20 | 小米科技有限责任公司 | Social network interaction information processing method and device |
| CN105763431A (en) * | 2016-05-06 | 2016-07-13 | 腾讯科技（深圳）有限公司 | Information pushing method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107786414A (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109684478B (en) | Classification model training method, classification device, classification equipment and medium | |
| US10579717B2 (en) | Systems and methods for identifying and inserting emoticons | |
| Li et al. | Sentiment analysis of danmaku videos based on naïve bayes and sentiment dictionary | |
| Hornik et al. | Advertising appeals, moderators, and impact on persuasion: A quantitative assessment creates a hierarchy of appeals | |
| Cvijikj et al. | Understanding social media marketing: a case study on topics, categories and sentiment on a Facebook brand page | |
| CN103365867B (en) | It is a kind of that the method and apparatus for carrying out sentiment analysis are evaluated to user | |
| CN111177538B (en) | User interest label construction method based on unsupervised weight calculation | |
| KR20160058895A (en) | System and method for analyzing and synthesizing social communication data | |
| CA2954330A1 (en) | System and method for identifying and suggesting emoticons | |
| CN108009297B (en) | Text emotion analysis method and system based on natural language processing | |
| CN107103093B (en) | Short text recommendation method and device based on user behavior and emotion analysis | |
| KR102322668B1 (en) | Systme for providing multi-platform service for stimulating creative activity of contents creator | |
| CN113868526A (en) | Information pushing method and device and non-transitory computer readable storage medium | |
| CN107786414B (en) | Data sending method, device and system | |
| Shayegan et al. | A method for identifying personality traits in telegram | |
| CN110427620B (en) | Service quality optimization management system based on community system | |
| JP6457986B2 (en) | Message classification system, message classification method and program | |
| CN115456676A (en) | Game advertisement visual delivery data analysis management method and system | |
| CN114359813A (en) | Depression emotion detection method and device | |
| CN109190106A (en) | Sentiment dictionary constructs system and construction method | |
| CN109558546A (en) | A kind of the microblog topic expression model generating method and device of Behavior-based control analysis | |
| Najafi et al. | Comparing analysis of social media content with traditional survey methods of predicting opening night box-office revenues for motion pictures | |
| Asriguna et al. | Sentiment Analysis of Live. on Digital Provider Application Using Naive Bayes Classifier Method | |
| KR20190104745A (en) | Issue interest based news value evaluation apparatus and method, storage media storing the same | |
| Loglisci et al. | Analyzing microblogging posts for tracking collective emotional trajectories |
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 |