CN111538826A - Routing invitation method and device based on problems - Google Patents
Routing invitation method and device based on problems Download PDFInfo
- Publication number
- CN111538826A CN111538826A CN202010666491.9A CN202010666491A CN111538826A CN 111538826 A CN111538826 A CN 111538826A CN 202010666491 A CN202010666491 A CN 202010666491A CN 111538826 A CN111538826 A CN 111538826A
- Authority
- CN
- China
- Prior art keywords
- users
- user
- alternative
- question
- invited
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/30—Routing of multiclass traffic
Abstract
The present disclosure provides a problem-based route invitation method, including: creating a problem to be solved, acquiring the characteristics of the problem to be solved, screening out alternative users matched with the problem to be solved from a user index library according to the characteristics of the problem to be solved, sequencing the alternative users according to user images of the alternative users, selecting a part of the alternative users as invited users invited to answer the problem to be solved, and sending a message for inviting to answer the problem to be solved to the invited users. The problem-based route invitation method can effectively solve the problems that the route invitation method in the prior art cannot solve the long-tail problem, is poor in effectiveness and consumes more computing resources.
Description
Technical Field
The present disclosure relates to the field of computer internet technologies, and in particular, to a method and an apparatus for routing invitation based on a problem, an electronic device, and a storage medium.
Background
The question-answer community is an important way for users to share knowledge and obtain answers, and an efficient and accurate matching mechanism needs to be established between questions and users with answering ability and willingness, so that the questions of the users can be answered quickly and excellently.
Most of the traditional route inviting methods are based on the dimensionality of the user, and recommend interesting problems for the user according to the interest and personalized requirements of the user. However, this invitation method has various drawbacks: routing invitations based on users are prone to head problems with high popularity and large click quantity, so that a large number of cold or professional long-tail problems cannot be distributed and answered sufficiently; because the active time of the user is uncertain, the user cannot be touched in time after the problem is raised, and the effectiveness is poor; the number of users who are active in the question-and-answer community every day is generally 2-3 orders of magnitude higher than the number of questions, and the routing invitation method from the users also consumes more computing resources.
Therefore, a route invitation method which can give consideration to the solution of the long-tail problem, has high operation efficiency and saves computing resources is needed.
Disclosure of Invention
In view of this, the present disclosure provides a problem-based route invitation method and apparatus, which can effectively solve the problems that the route invitation method in the prior art cannot consider the solution of the long tail problem, has poor effectiveness, and consumes more computing resources.
The following presents a simplified summary of the disclosure in order to provide a basic understanding of some aspects of the disclosure. It should be understood that this summary is not an exhaustive overview of the disclosure. It is not intended to identify key or critical elements of the disclosure or to delineate the scope of the disclosure. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.
According to a first aspect of the present disclosure, there is provided a problem-based route invitation method, including:
creating a problem to be solved;
acquiring the characteristics of the problem to be solved;
screening out alternative users matched with the problem to be solved from the user index library according to the characteristics of the problem to be solved;
sorting the alternative users according to the user pictures of the alternative users, and selecting a part of the alternative users as invited users to be invited to answer the problem to be solved;
a message is sent to the invited user inviting answers to the question to be solved.
In some embodiments, after creating the problem to be solved, further comprising:
and judging whether the problem to be solved can be normally circulated or not, and if the problem to be solved can be normally circulated, acquiring the characteristics of the problem to be solved.
Further, judge whether the problem of waiting to solve can normally circulate, specifically include:
performing algorithm identification on the problem to be solved, and classifying the problem into three categories, namely normal, illegal and illegal, and difficult judgment on whether illegal and illegal exist;
and manually identifying the problem to be solved which is difficult to judge whether the violation is illegal.
In some embodiments, the characteristics of the question to be solved include at least one of topic, category, keyword, question time, question age, questioner registration time, questioner authority, questioner historical question condition, and questioner historical question solved condition.
In some embodiments, before screening out the alternative users matching the problem to be solved from the user index library according to the characteristics of the problem to be solved, the method further comprises establishing a user index library:
a user index is generated based on the user representation, the user index relating to a user's interest in answering questions.
In some embodiments, screening out alternative users matching the problem to be solved from the user index library according to the features of the problem to be solved specifically includes:
and searching out users with the interests of the users for answering the questions matched with the characteristics of the questions to be solved from the user index library by using a search engine.
In some embodiments, sorting the alternative users according to their user images specifically includes:
and scoring the alternative users based on the characteristics of the alternative users, the characteristics of the problems to be solved, the context characteristics and the combined characteristics, and sequencing the alternative users according to scoring results.
In some embodiments, selecting a part of the alternative users as invited users to be invited to answer the question to be solved specifically includes:
and reordering a part of selected alternative users, and selecting a plurality of alternative users ranked in the front after reordering as invited users.
Further, reordering the selected part of the candidate users specifically includes:
and reducing the ranking of the alternative users under the condition that the number of the received invitations of the alternative users in a period of time exceeds a preset value.
Further, reordering the selected part of the candidate users specifically includes:
and scoring the alternative users based on the number of the invitations received by the alternative users in a period of time and the authority degrees of the alternative users, and sequencing the alternative users according to scoring results.
In some embodiments, before sending the message inviting the invited user to answer the question to be solved, the method further comprises:
and screening the invited users and the problems to be solved, and filtering the invited users and the problems to be solved in abnormal states.
In some embodiments, sending a message to the invited user inviting answers to the question to be solved includes:
and sending a message for inviting to answer the question to be solved to the invited user in a message notification and/or push mode.
According to a second aspect of the present disclosure, there is provided a problem-based route invitation apparatus including:
a problem creation unit for creating a problem to be solved;
a feature acquisition unit configured to acquire a feature of a problem to be solved;
the user screening unit is used for screening out alternative users matched with the problems to be solved from the user index database according to the characteristics of the problems to be solved;
the user sorting unit is used for sorting the alternative users according to the user images of the alternative users and selecting a part of the alternative users as invited users to be invited to answer the questions to be solved;
and the message sending unit is used for sending a message for inviting the invited user to answer the question to be solved.
In some embodiments, the problem creation unit is further configured to, after creating the problem to be solved,
and judging whether the problem to be solved can be normally circulated or not, and if the problem to be solved can be normally circulated, acquiring the characteristics of the problem to be solved.
Further, the problem creating unit determines whether the problem to be solved can circulate normally, and specifically includes:
performing algorithm identification on the problem to be solved, and classifying the problem into three categories, namely normal, illegal and illegal, and difficult judgment on whether illegal and illegal exist;
and manually identifying the problem to be solved which is difficult to judge whether the violation is illegal.
In some embodiments, the features of the question to be solved acquired by the feature acquisition unit include at least one of a topic, a category, a keyword, a question time, a question aging, a questioner registration time, a questioner authority, a questioner historical question condition, and a questioner historical question solved condition.
In some embodiments, the user screening unit is further configured to, before screening out the alternative users matching the problem to be solved from the user index library according to the features of the problem to be solved, establish a user index library:
a user index is generated based on the user representation, the user index relating to a user's interest in answering questions.
In some embodiments, the screening unit screens, according to the features of the problem to be solved, alternative users matching the problem to be solved from the user index library, and specifically includes:
and searching out users with the interests of the users for answering the questions matched with the characteristics of the questions to be solved from the user index library by using a search engine.
In some embodiments, the user sorting unit is configured to sort the alternative users according to the user images of the alternative users, and specifically includes:
and scoring the alternative users based on the characteristics of the alternative users, the characteristics of the problems to be solved, the context characteristics and the combined characteristics, and sequencing the alternative users according to scoring results.
In some embodiments, the selecting, by the user ranking unit, a part of the alternative users as invited users who are invited to answer the question to be solved specifically includes:
and reordering a part of selected alternative users, and selecting a plurality of alternative users ranked in the front after reordering as invited users.
Further, the reordering of the selected part of the alternative users by the user ordering unit specifically includes:
and reducing the ranking of the alternative users under the condition that the number of the received invitations of the alternative users in a period of time exceeds a preset value.
Further, the reordering of the selected part of the alternative users by the user ordering unit specifically includes:
and scoring the alternative users based on the number of the invitations received by the alternative users in a period of time and the authority degrees of the alternative users, and sequencing the alternative users according to scoring results.
In some embodiments, the message sending unit, prior to sending the invited user a message inviting answering the question to be solved, is further configured to:
and screening the invited users and the problems to be solved, and filtering the invited users and the problems to be solved in abnormal states.
In some embodiments, the message sending unit sends a message to the invited user inviting answering the question to be solved, including:
and sending a message for inviting to answer the question to be solved to the invited user in a message notification and/or push mode.
According to a third aspect of the present disclosure, there is provided an electronic device comprising:
one or more processors;
a memory for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a computer readable medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to the first aspect.
The disclosure provides a problem-based route invitation method and device, effectively solves the problem that the existing route invitation method cannot give consideration to long-tail problem solution, improves the efficiency of route invitation, and saves computing resources.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts. The foregoing and other objects, features and advantages of the application will be apparent from the accompanying drawings. Like reference numerals refer to like parts throughout the drawings. The drawings are not intended to be to scale as practical, emphasis instead being placed upon illustrating the subject matter of the present application.
Fig. 1 is a flowchart of a user-based route invitation method commonly used in the prior art according to an embodiment of the present disclosure.
Fig. 2 is a flowchart of a problem-based route invitation method according to an embodiment of the disclosure.
Fig. 3 is a system configuration diagram of a problem-based routing invitation device according to an embodiment of the present disclosure.
Fig. 4 is a schematic structural diagram of an electronic device provided according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, relational terms such as "first," "second," and the like may be used solely in the description herein to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Further, the term "and/or" in the present application is only one kind of association relationship describing the associated object, and means that three kinds of relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone.
Exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings. In the interest of clarity and conciseness, not all features of an actual embodiment are described in the specification. It will of course be appreciated that in the development of any such actual embodiment, numerous implementation-specific decisions may be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which will vary from one implementation to another.
Here, it should be further noted that, in order to avoid obscuring the present disclosure with unnecessary details, only the device structure closely related to the scheme according to the present disclosure is shown in the drawings, and other details not so related to the present disclosure are omitted.
It is to be understood that the disclosure is not limited to the described embodiments, as described below with reference to the drawings. In this context, embodiments may be combined with each other, features may be replaced or borrowed between different embodiments, one or more features may be omitted in one embodiment, where feasible.
Fig. 1 is a flowchart illustrating a user-based route invitation method 100 that is commonly used in the related art, and specifically includes:
step 110: when a user browses contents in an App, a route recommendation process is triggered;
step 120: recommending questions which may be interested for the user through screening and sequencing according to the interest and the historical behaviors of the user, and filtering questions which are provided by the user, answered, browsed and blacked;
step 130: the recommended question is sent to the user.
The route invitation method based on the user provided in the prior art is based on the user, and each recommendation starts from the request of the user, and the user is matched with the interest according to the interest and the personalized demand of the user. However, this route invitation method faces the following series of problems: the real-time performance is not high, the route invitation is triggered by the active browsing behavior of the user, the active browsing behavior of the user is not necessarily matched with the question asking time of a questioner, and the problem is particularly prominent for news problems with high timeliness requirements; the routing invitation system based on the user is biased to the head question, and a large number of long-tail questions cannot be distributed and answered sufficiently; the number of users who are active in the question-answering community every day is generally 2-3 orders higher than the number of questions, and the invitation from the users also consumes more computing resources; those users who do not access the App cannot be reached.
In order to solve the above problem, the embodiments of the present disclosure provide a method for route invitation based on problem, and a specific description is provided below for the method for route invitation based on problem provided by the embodiments of the present disclosure.
Fig. 2 is a flowchart illustrating a method 200 for problem-based route invitation according to an embodiment of the present disclosure, where the method specifically includes:
step 210: a problem to be solved is created.
In the embodiment of the disclosure, the user can create the problem to be solved in any question and answer community App. For example, a user may create a question in a community of known questions and answers, so that the question is sent to other users to obtain the answers of the other users.
In the embodiment of the disclosure, after the problem to be solved is created, in order to prevent illegal contents from being introduced into the question-and-answer community, whether the problem to be solved can be normally circulated is determined, and if the problem to be solved can be normally circulated, the next step is performed.
In the embodiment of the present disclosure, whether the problem to be solved can circulate normally may be determined according to whether the problem to be solved violates a rule, and the specific implementation method may be: firstly, identifying problems to be solved through an intelligent algorithm, for example, semantic analysis, a dictionary and the like can be adopted, and the possibility score of illegal violation is calculated for each problem, so that the problems to be solved are identified as three types, namely normal, illegal violation and illegal violation which is difficult to judge; and then, manually identifying the problem to be solved which is difficult to judge the illegal violation, and manually identifying the problem to be solved which is difficult to judge the illegal violation as a normal problem or an illegal violation problem. And (4) regarding the normal problem obtained after the intelligent algorithm identification and the manual identification as a problem to be solved which can be normally circulated. In the embodiment of the present disclosure, the method for determining whether the problem to be solved can be normally circulated is not limited to the foregoing method, and other methods that can determine whether the problem to be solved violates a law are all within the scope of the present disclosure, which can be easily conceived by those skilled in the art.
Step 220: the characteristics of the problem to be solved are obtained.
In the embodiment of the disclosure, the information of topics, categories, keywords, question asking time, question timeliness and the like of the problem to be solved can be extracted by performing semantic analysis on the problem to be solved by acquiring the characteristics of the problem to be solved. For example, when the problem to be solved is "which in-ear headphones are worth recommending", topics that can be extracted from the problem to be solved are "headphones", the category is "number", and the keywords are "in-ear headphones", "recommendation"; the question asking time is the time when the user initiates the question in the question and answer community; since the problem to be solved does not belong to a hot spot problem or other problem that needs to be solved, it is determined to have a long timeliness. In embodiments of the present disclosure, timeliness may be represented by a timeliness score (e.g., an initial score of 100 when a question was just raised); the time efficiency score, which has the problem of longer time efficiency, may have a slower decay rate.
In addition, the characteristics of the questions to be solved can also comprise the information of the questioners, specifically comprising the registration time of the questioners, the authority of the questioners, the historical questioning conditions of the questioners, the answering conditions of the questioners and the like. In the embodiment of the disclosure, the historical question condition of the questioner may include the number of questions that the questioner has initiated, the topics and categories involved in the questions, and the like; the history question-solved situation of the questioner may include the number of questions asked by the questioner, the topic and category related to the questions asked by the questioner. In the embodiment of the present disclosure, the historical question condition of the questioner and the historical question answered condition of the questioner may further include other information, which is not specifically limited herein.
Step 230: and screening out alternative users matched with the problem to be solved from the user index library according to the characteristics of the problem to be solved.
Here, before screening out the alternative users matching with the problem to be solved from the user index library according to the characteristics of the problem to be solved, establishing a user index library. In the embodiment of the disclosure, the method for establishing the user index library may be to generate a user index based on the user portrait, where the user index is related to the interest of the user in answering the question. The user portrait is a basic storage system, and can include originally acquired questioning, answering, browsing, paying attention to and collecting data of the user, historical invited and invited answer records, and also can include data which can embody the authority of the user and long-term interest, real-time interest, creation interest and interest of answering questions and is obtained after being processed by a certain algorithm according to the acquired behaviors of the user.
In the embodiment of the disclosure, users can be classified based on data related to interests of the users in user portraits for answering questions, and user indexes are generated based on the classification conditions. For example, topics and categories of questions answered by the user can be extracted to reflect interests of the user in answering the questions, registered users are classified according to the topics of the questions answered by the user, and corresponding topic user indexes are generated, wherein the topic user indexes comprise user IDs matched with each topic; meanwhile, the registered users can be classified according to the categories of questions answered by the users, and corresponding category user indexes are generated, wherein the category user indexes comprise user IDs matched with each category.
In the embodiment of the present disclosure, the candidate users matched with the problem to be solved are screened from the user index library according to the feature of the problem to be solved, and specifically, the search engine may be used to search the user index library for the users whose interests in answering the problem are matched with the feature of the problem to be solved.
For example, when the problem to be solved is "which ones of the left-ear earphones are worth recommending", the topic extracted from the problem to be solved is "earphone", and the category is "number", then the search engine may be used to search the user ID of which the interest of the user in answering the problem is "earphone" from the topic user index in the user index library, and at the same time, the search engine may be used to search the user ID of which the interest of the user in answering the problem is "number" from the category user index in the user index library, and the logic and operation may be performed on the searched user IDs corresponding to different user indexes, so that the user whose interest in answering the problem matches the feature of "which ones of the left-ear earphones are worth recommending" of the problem to be solved may be searched.
The method for screening the alternative users from the user index library according to the characteristics of the problems to be solved, which is provided by the embodiment of the disclosure, can search hundreds of users which are most matched with the characteristics of the problems to be solved from a large number of user indexes by using a search engine, and can greatly reduce the calculation amount of the subsequent process, thereby effectively saving the calculation resources.
Further, in the embodiment of the present disclosure, in order to improve the processing speed during matching, a search engine may be further used to perform multi-channel parallel screening on matched users from the user index database according to the characteristics of the problem to be solved, and then the multi-channel screening results are summarized, so as to obtain a final candidate user. For example, in the embodiment of the present disclosure, a search engine may be used to screen matching users from a user index library according to different user indexes. It should be noted that the method for screening matching users from the user index library according to the features of the problem to be solved is not limited to the above method provided by the embodiments of the present disclosure, and other screening methods easily conceivable by those skilled in the art are within the scope of the present disclosure.
Step 240: and sequencing the alternative users according to the user pictures of the alternative users, and selecting a part of the alternative users as invited users who are invited to answer the questions to be solved.
In the embodiment of the present disclosure, sorting the alternative users according to the user images of the alternative users may include:
and scoring the alternative users based on the characteristics of the alternative users, the characteristics of the problems to be solved, the context characteristics and the combined characteristics, and sequencing the alternative users according to scoring results.
In the embodiment of the present disclosure, the characteristics of the alternative user may be obtained from the user representation, including the user's question, answer, browse, concern, and collection behavior, the user's long-term interest, real-time interest, creation interest, interest in answering questions, and historical invited and invited answer records; the contextual characteristics include a current date and time; the combined features comprise similarity of the alternative users and the problems to be solved in dimensions of topics, classifications, keywords and the like.
In the embodiment of the present disclosure, the features of the alternative users, the features of the problem to be solved, the context features, and the combined features may be packaged, an external ranking service is requested, so as to obtain a score of each alternative user, and the alternative users are ranked according to the score, where the score may reflect the probability that the alternative users answer the problem to be solved. In the embodiment of the disclosure, the external ranking service loads the ranking model, calculates the score of the alternative user by using a machine learning algorithm according to various input characteristics, and ranks the alternative user according to the score.
In the embodiment of the present disclosure, the sorting service is not limited to an external sorting service, and may be an internal sorting service or another sorting service capable of implementing the sorting function in the embodiment of the present disclosure. In the embodiment of the present disclosure, the machine learning algorithm used by the ranking model may be a traditional machine learning model, such as a linear model or a tree model, or may also be a neural network model or other machine learning models capable of implementing a ranking function, which is not limited in the embodiment of the present disclosure.
In the embodiment of the present disclosure, to further improve the efficiency of obtaining the question answer, selecting a part of the alternative users as invited users who are invited to answer the question to be solved may be:
and reordering a part of selected alternative users, and selecting a plurality of alternative users ranked in the front after reordering as invited users.
For example, when the candidate users are ranked from high to low according to the scores, the top 100 candidate users may be selected first as needed, then the 100 candidate users may be ranked, and a plurality of ranked candidate users (for example, 20) that are ranked top after ranking may be selected as invited users.
Because the authoring capability and the authoring willingness of the user are limited, too many invitations are received in a period of time, which does not contribute to the improvement of the answer quantity and the answer quality, and can cause excessive disturbance to the user. Therefore, if a user receives more than one invitation within a period of time, sending the invitation to the user again or reducing the number of invitations sent to the user should be avoided.
Based on the above, in the embodiment of the present disclosure, the method for reordering the selected part of the alternative users may be: and reducing the ranking of the alternative users under the condition that the number of the received invitations of the alternative users in a period of time exceeds a preset value.
For example, under the condition that the candidate users are sorted from high to low according to the scores, the number of the invitations received by each candidate user in one day is counted, if the number of the invitations received by the candidate user in one day exceeds a preset value, the score of the candidate user is multiplied by a coefficient k to obtain a secondary score of the candidate user, wherein k is a positive number smaller than 1 and is negatively related to the number of the invitations received by the candidate user, and therefore the rank of the candidate user is reduced.
In the embodiment of the present disclosure, the period of time is not limited to one day, and may be other suitable periods of time recognized by those skilled in the art.
In the embodiment of the present disclosure, the method for reducing the rank of the alternative user is not limited to the above method, and may also be that the score of the alternative user is subtracted by a fixed score, or another method capable of reducing the rank of the alternative user.
From the perspective of improving the quality of answer to questions, in the embodiment of the present disclosure, a part of selected candidate users is reordered, and a plurality of candidate users ranked in front after reordering are selected as invited users, and on the basis of considering the frequency of the invited users, the authority of the candidate users is also considered. At this time, the selected part of the candidate users is reordered, and a plurality of candidate users ranked in the front after reordering are selected as invited users, which may be: and scoring the alternative users based on the number of the invitations received by the alternative users in a period of time and the authority degrees of the alternative users, and sequencing the alternative users according to scoring results.
For example, in the case of ranking the alternative users from high to low according to the scores, the number of the invitations received by each alternative user in one day is counted, and the authority of the alternative users is obtained at the same time. If the authority of the alternative user exceeds the preset value, the score of the alternative user is multiplied by a coefficient k1, if the number of the invitations received by the alternative user in one day exceeds the preset value, the score of the alternative user is multiplied by a coefficient k2,
wherein k1 is an integer greater than 1, and k2 is a positive number less than 1, thereby obtaining the secondary score of the alternative user, and sorting the alternative users from high to low according to the secondary score.
It should be noted that the method for scoring the alternative users based on the number of invitations received by the alternative users in a period of time and the authority of the alternative users and ranking the alternative users according to the scoring result provided in the embodiment of the present disclosure is not limited to the method in the above example. Other methods that may be implemented to score the alternative users based on the number of invitations received by the alternative users over a period of time and the authority of the alternative users and rank the alternative users according to the scoring result, which are easily conceivable by those skilled in the art, are within the scope of the present disclosure.
In the embodiment of the present disclosure, the method for ranking the alternative users is not limited to ranking the alternative users according to the rule that the score is from high to low, and a person skilled in the art may also rank the alternative users according to the actual situation by using the rule that the score is from low to high or other rules. When the alternative users are ranked according to the rule that the score is from low to high or other rules, and when a part of the selected alternative users are reordered, other corresponding reordering methods may be selected, which is not limited in the embodiment of the present disclosure.
Step 250: a message is sent to the invited user inviting answers to the question to be solved.
In this embodiment of the disclosure, before sending the message inviting the invited user to answer the question to be solved, the method may further include:
and screening the invited users and the problems to be solved, and filtering the invited users and the problems to be solved in abnormal states.
In the embodiment of the present disclosure, the invited user and the problem to be solved in the abnormal state mainly refer to an illegal invited user and a problem to be solved. The method and the device can screen the invited users according to whether the user behaviors violate rules and filter the invited users with violations.
In the embodiment of the disclosure, after the problem to be solved is created, whether the problem to be solved can be normally circulated is judged, the illegal violation problem is filtered, and only the normal problem is reserved to enter the subsequent flow. However, since some users may modify the problem to be solved after the problem to be solved is created, thereby causing the illegal violation content to circulate in the question-and-answer community, the embodiment of the present disclosure may also screen the problem to be solved again and filter the illegal violation content before sending the message inviting the user to answer the problem to be solved.
In the embodiment of the present disclosure, after an invited user in an abnormal state and a problem to be solved are filtered, a message inviting to answer the problem to be solved may be sent to the invited user in a message notification manner, for example, the message inviting to answer the problem to be solved is sent to the invited user in a message notification manner, for example, to a mobile terminal of the invited user, and when the user opens a corresponding App for a question and answer community, prompt information may be seen at the message notification location.
Optionally, because the user score obtained after the alternative user is ranked according to the user drawing of the alternative user in step 240 provided by the embodiment of the present disclosure can reflect the probability that the alternative user answers the problem to be solved, for an invited user whose score exceeds a preset value, the message inviting to answer the problem to be solved may be sent to the invited user in a push manner, for example, to a mobile terminal of the invited user, and displayed in real time on a current interface of the mobile terminal of the user in the form of a message frame, so that the invited user can know the invitation information without opening a question and answer community App, thereby improving the efficiency of routing invitation.
The problem-based routing invitation method provided by the embodiment of the disclosure can rapidly match a sufficient number of high-quality creators after the problem to be solved is created, avoids the phenomenon that the traditional routing invitation is too concentrated to the head problem, can effectively improve the answering speed and the answering quality of the problem to be solved, and better meets the request of the questioner for knowing and asking.
Corresponding to the foregoing problem-based route invitation method according to the embodiment of the present disclosure, a problem-based route invitation apparatus according to the embodiment of the present disclosure is introduced below. Fig. 3 is a system configuration diagram of a problem-based routing invitation device 300 according to an embodiment of the disclosure.
The problem-based route invitation device 300 provided by the embodiment of the present disclosure includes: a question creation unit 301, a feature acquisition unit 302, a user filtering unit 303, a user ranking unit 304, and a message sending unit 305.
Wherein the problem creating unit 301 is used for creating a problem to be solved. In this embodiment of the present disclosure, after the problem creating unit 301 creates the problem to be solved, it may further determine whether the problem to be solved can flow normally, and the determining method is described in detail in the foregoing problem-based routing invitation method in this embodiment of the present disclosure, and details are not repeated here. If the problem to be solved can be circulated normally, the problem creating unit 301 sends the problem to be solved to the feature acquiring unit 302 by means of kafka message. In the embodiment of the present disclosure, the transmission of the problem to be solved by the kafka message is a default mode of the system, but the questioner cannot know which users the problem to be solved is sent to by the mode.
In the embodiment of the present disclosure, if the questioner triggers the RPC interface through the virtual button on the interface when the question is created, the question to be solved may also be sent to the feature obtaining unit 302 in the RPC interface manner, and the questioner may know which users to send the question to be solved to subsequently answer.
A feature obtaining unit 302, configured to obtain a feature of the problem to be solved. In the embodiment of the present disclosure, the feature obtaining unit 302 may monitor the to-be-solved problem creation information of the problem creation unit 301, and is configured to obtain the feature of the to-be-solved problem after receiving the to-be-solved problem.
And the user screening unit 303 is configured to screen out, from the user index library, an alternative user matched with the problem to be solved according to the characteristic of the problem to be solved.
And a user sorting unit 304, configured to sort the alternative users according to the user images of the alternative users, and select a part of the alternative users as invited users to answer the to-be-solved question.
A message sending unit 305 for sending a message inviting the invited user to answer the question to be solved.
According to the problem-based route invitation device provided by the embodiment of the disclosure, each unit is independently responsible for respective operation, so that the problem can be rapidly positioned when a fault occurs, and the function expansion is facilitated.
Fig. 4 shows a schematic structural diagram of an electronic device 400 according to an embodiment of the disclosure. As shown in fig. 4, the electronic apparatus 400 includes a Central Processing Unit (CPU) 401 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the electronic apparatus are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including a display device such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as necessary, so that a computer program read out therefrom is mounted into the storage section 408 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer-readable medium bearing instructions that, in such embodiments, may be downloaded and installed from a network via communication portion 409 and/or installed from removable media 411. The instructions, when executed by a Central Processing Unit (CPU) 401, perform the various method steps described in the present invention.
The above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the exemplary embodiments of the present disclosure, and should be construed as being included therein.
Claims (15)
1. A method for problem-based routing invitation, comprising:
creating a problem to be solved;
acquiring the characteristics of the problem to be solved;
screening out alternative users matched with the problem to be solved from the user index library according to the characteristics of the problem to be solved;
sorting the alternative users according to the user pictures of the alternative users, and selecting a part of the alternative users as invited users to be invited to answer the problem to be solved;
a message is sent to the invited user inviting answers to the question to be solved.
2. The problem-based route invitation method of claim 1, further comprising, after said creating a to-be-solved problem:
and judging whether the problem to be solved can be normally circulated or not, and if the problem to be solved can be normally circulated, acquiring the characteristics of the problem to be solved.
3. The method for problem-based route invitation according to claim 2, wherein said determining whether the problem to be solved can flow normally comprises:
performing algorithm identification on the problem to be solved, and classifying the problem into three categories, namely normal, illegal and illegal, and difficult judgment on whether illegal and illegal exist;
and manually identifying the problem to be solved which is difficult to judge whether the violation is illegal.
4. The question-based routing invitation method of claim 1, said characteristics of the question to be solved comprising at least one of topic, category, keyword, question time, question age, questioner registration time, questioner authority, questioner historical question condition and questioner historical question solved condition.
5. The problem-based routing invitation method of claim 1, further comprising, before screening the alternative users matching the problem to be solved from the user index database according to the characteristics of the problem to be solved, establishing a user index database, specifically comprising:
a user index is generated based on the user representation, the user index relating to a user's interest in answering questions.
6. The problem-based routing invitation method according to claim 1, wherein the step of screening the alternative users matching the problem to be solved from the user index database according to the characteristics of the problem to be solved specifically comprises the steps of:
and searching out users with the interests of the users for answering the questions matched with the characteristics of the questions to be solved from the user index library by using a search engine.
7. The problem-based routing invitation method of claim 1, wherein said ordering the alternative users according to their user images specifically comprises:
and scoring the alternative users based on the characteristics of the alternative users, the characteristics of the problems to be solved, the context characteristics and the combined characteristics, and sequencing the alternative users according to scoring results.
8. The question-based routing invitation method according to claim 1, wherein said selecting a part of the alternative users as invited users to be invited to answer the question to be solved, specifically comprises: and reordering a part of selected alternative users, and selecting a plurality of alternative users ranked in the front after reordering as invited users.
9. The problem-based route invitation method according to claim 8, wherein said reordering of the selected portion of the alternative users comprises:
and reducing the ranking of the alternative users under the condition that the number of the received invitations of the alternative users in a period of time exceeds a preset value.
10. The problem-based route invitation method according to claim 8, wherein said reordering of the selected portion of the alternative users comprises:
and scoring the alternative users based on the number of the invitations received by the alternative users in a period of time and the authority degrees of the alternative users, and sequencing the alternative users according to scoring results.
11. The question-based routing invitation method of claim 1, further comprising, prior to said sending a message to the invited user inviting an answer to the question to be solved:
and screening the invited users and the problems to be solved, and filtering the invited users and the problems to be solved in abnormal states.
12. The question-based routing invitation method of claim 1, said sending a message to an invited user inviting an answer to a question to be solved, comprising:
and sending a message for inviting to answer the question to be solved to the invited user in a message notification and/or push mode.
13. A problem-based routing invitation apparatus comprising:
a problem creation unit for creating a problem to be solved;
a feature acquisition unit configured to acquire a feature of a problem to be solved;
the user screening unit is used for screening out alternative users matched with the problems to be solved from the user index database according to the characteristics of the problems to be solved;
the user sorting unit is used for sorting the alternative users according to the user images of the alternative users and selecting a part of the alternative users as invited users to be invited to answer the questions to be solved;
and the message sending unit is used for sending a message for inviting the invited user to answer the question to be solved.
14. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs;
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-12.
15. A computer readable medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010666491.9A CN111538826B (en) | 2020-07-13 | 2020-07-13 | Routing invitation method and device based on problems |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010666491.9A CN111538826B (en) | 2020-07-13 | 2020-07-13 | Routing invitation method and device based on problems |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111538826A true CN111538826A (en) | 2020-08-14 |
| CN111538826B CN111538826B (en) | 2021-01-29 |
Family
ID=71974717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010666491.9A Active CN111538826B (en) | 2020-07-13 | 2020-07-13 | Routing invitation method and device based on problems |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111538826B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114328842A (en) * | 2021-12-30 | 2022-04-12 | 北京百度网讯科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101257512A (en) * | 2008-02-02 | 2008-09-03 | 黄伟才 | Inquiry answer matching method used for inquiry answer system as well as inquiry answer method and system |
| CN102184225A (en) * | 2011-05-09 | 2011-09-14 | 北京奥米时代生物技术有限公司 | Method for searching preferred expert information in question-answering system |
| CN103365899A (en) * | 2012-04-01 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Question recommending method and question recommending system both in questions-and-answers community |
| CN104065564A (en) * | 2014-06-10 | 2014-09-24 | 网易公司 | Method and device used for questioning and answering |
| CN105335447A (en) * | 2014-08-14 | 2016-02-17 | 北京奇虎科技有限公司 | Computer network-based expert question-answering system and construction method thereof |
| CN107783970A (en) * | 2016-08-25 | 2018-03-09 | 武汉聚蜗网络科技有限公司 | A kind of expert's question answering system and its operating method |
| CN107845429A (en) * | 2017-10-16 | 2018-03-27 | 李洪波 | A kind of method and system of online medical advice |
| CN109034402A (en) * | 2018-06-14 | 2018-12-18 | 深圳市轱辘汽车维修技术有限公司 | Information processing method, apparatus and system |
| CN109189897A (en) * | 2018-07-27 | 2019-01-11 | 什伯（上海）智能技术有限公司 | One kind being based on the matched chat method of data content and chat device |
| CN109271499A (en) * | 2018-09-18 | 2019-01-25 | 广州神马移动信息科技有限公司 | Recommended method, device and the terminal device of answer user in a kind of knowledge question |
| CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通（北京）科技有限公司 | The petrochemical field answering method and system of knowledge based map |
| CN110275951A (en) * | 2019-06-27 | 2019-09-24 | 百度在线网络技术（北京）有限公司 | Answering method, device, equipment and computer readable storage medium |
| CN110322959A (en) * | 2019-05-24 | 2019-10-11 | 山东大学 | A kind of Knowledge based engineering depth medical care problem method for routing and system |
| CN110474880A (en) * | 2019-07-22 | 2019-11-19 | 李静妤 | The consulting system of real-time interactive question and answer and method |
| CN110717105A (en) * | 2019-10-12 | 2020-01-21 | 浙江大学 | Personalized active pushing method for scientific and technological resources |
| CN110879858A (en) * | 2019-11-13 | 2020-03-13 | 上海易点时空网络有限公司 | Data processing method and device for problem distribution |
-
2020
- 2020-07-13 CN CN202010666491.9A patent/CN111538826B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101257512A (en) * | 2008-02-02 | 2008-09-03 | 黄伟才 | Inquiry answer matching method used for inquiry answer system as well as inquiry answer method and system |
| CN102184225A (en) * | 2011-05-09 | 2011-09-14 | 北京奥米时代生物技术有限公司 | Method for searching preferred expert information in question-answering system |
| CN103365899A (en) * | 2012-04-01 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Question recommending method and question recommending system both in questions-and-answers community |
| CN104065564A (en) * | 2014-06-10 | 2014-09-24 | 网易公司 | Method and device used for questioning and answering |
| EP3157204A1 (en) * | 2014-06-10 | 2017-04-19 | Netease, Inc. | Method and device for questioning and answering |
| CN105335447A (en) * | 2014-08-14 | 2016-02-17 | 北京奇虎科技有限公司 | Computer network-based expert question-answering system and construction method thereof |
| CN107783970A (en) * | 2016-08-25 | 2018-03-09 | 武汉聚蜗网络科技有限公司 | A kind of expert's question answering system and its operating method |
| CN107845429A (en) * | 2017-10-16 | 2018-03-27 | 李洪波 | A kind of method and system of online medical advice |
| CN109034402A (en) * | 2018-06-14 | 2018-12-18 | 深圳市轱辘汽车维修技术有限公司 | Information processing method, apparatus and system |
| CN109189897A (en) * | 2018-07-27 | 2019-01-11 | 什伯（上海）智能技术有限公司 | One kind being based on the matched chat method of data content and chat device |
| CN109271499A (en) * | 2018-09-18 | 2019-01-25 | 广州神马移动信息科技有限公司 | Recommended method, device and the terminal device of answer user in a kind of knowledge question |
| CN109492077A (en) * | 2018-09-29 | 2019-03-19 | 北明智通（北京）科技有限公司 | The petrochemical field answering method and system of knowledge based map |
| CN110322959A (en) * | 2019-05-24 | 2019-10-11 | 山东大学 | A kind of Knowledge based engineering depth medical care problem method for routing and system |
| CN110275951A (en) * | 2019-06-27 | 2019-09-24 | 百度在线网络技术（北京）有限公司 | Answering method, device, equipment and computer readable storage medium |
| CN110474880A (en) * | 2019-07-22 | 2019-11-19 | 李静妤 | The consulting system of real-time interactive question and answer and method |
| CN110717105A (en) * | 2019-10-12 | 2020-01-21 | 浙江大学 | Personalized active pushing method for scientific and technological resources |
| CN110879858A (en) * | 2019-11-13 | 2020-03-13 | 上海易点时空网络有限公司 | Data processing method and device for problem distribution |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114328842A (en) * | 2021-12-30 | 2022-04-12 | 北京百度网讯科技有限公司 | Information recommendation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111538826B (en) | 2021-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9646079B2 (en) | Method and apparatus for identifiying similar questions in a consultation system | |
| US9460458B1 (en) | Methods and system of associating reviewable attributes with items | |
| US8463791B1 (en) | Method and apparatus for creation of web document titles optimized for search engines | |
| US11176142B2 (en) | Method of data query based on evaluation and device | |
| US8374885B2 (en) | People engine optimization | |
| CN107341268B (en) | Hot searching ranking method and system | |
| US20160267169A1 (en) | Systems And Methods For Classifying Electronic Documents | |
| US8122371B1 (en) | Criteria-based structured ratings | |
| US20100058204A1 (en) | Methods and systems for web site categorisation and filtering | |
| US20170098165A1 (en) | Method and Apparatus for Establishing and Using User Recommendation Model in Social Network | |
| Liu et al. | When web search fails, searchers become askers: Understanding the transition | |
| US20080294625A1 (en) | Item recommendation system | |
| JP2013517563A (en) | User communication analysis system and method | |
| WO2008083324A1 (en) | Seeking answers to questions | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| CN110991189A (en) | Method and system for generating decision result according to data acquired by acquisition module | |
| US20190012376A1 (en) | Preference visualization system and censorship system | |
| CN107977678A (en) | Method and apparatus for output information | |
| CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
| CN111538826B (en) | Routing invitation method and device based on problems | |
| CN114491149A (en) | Information processing method and apparatus, electronic device, storage medium, and program product | |
| AU2018429394B2 (en) | Media source measurement for incorporation into a censored media corpus | |
| CN111523068A (en) | Page configuration method, device, server and storage medium | |
| CN110990673B (en) | Method and system for obtaining questionnaire focus | |
| Willever-Farr et al. | Tell me about my family: A study of cooperative research on Ancestry. com |
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 |