CN112417124A

CN112417124A - Community question-answer processing method, device and medium

Info

Publication number: CN112417124A
Application number: CN202011317017.1A
Authority: CN
Inventors: 周元笙; 蒋佳惟; 马龙; 梁宸; 陈思姣; 李炫�
Original assignee: Ping An Life Insurance Company of China Ltd
Current assignee: Ping An Life Insurance Company of China Ltd
Priority date: 2020-11-20
Filing date: 2020-11-20
Publication date: 2021-02-26

Abstract

The application relates to a community question-answer processing method, a device and a medium, wherein the method comprises the following steps: receiving answers replied by the first user aiming at the questions; acquiring behavior data of the first user in a community question-answer application corresponding to the question and the answer; acquiring a target evaluation value of the answer according to the behavior data; and when the target evaluation value is greater than or equal to a first threshold value, storing the answer and the question in a correlation mode, and sending the answer to a second user who uploads the question. By adopting the method and the device, the reference value of the answer can be improved.

Description

Community question-answer processing method, device and medium

Technical Field

The application relates to the technical field of data processing, and mainly relates to a community question and answer processing method, device and medium.

Background

The Community Question Answering (CQA) application is a mainstream knowledge sharing platform in recent years, and the user scale and the number of questions are exponentially increased, so that fragmented knowledge in multiple fields can be provided for learners. However, due to differences in professional levels of the providers of the questions and answers in the community question-and-answer application, the quality of the questions and the quality of the answers in the community question-and-answer application are uneven, and it is difficult to determine the reference value of the answers.

Disclosure of Invention

The embodiment of the application provides a community question and answer processing method, device and medium, which can improve the reference value of answers and facilitate the improvement of the question and answer management effect.

In a first aspect, an embodiment of the present application provides a community question and answer processing method, where:

receiving answers replied by the first user aiming at the questions;

acquiring behavior data of the first user in a community question-answer application corresponding to the question and the answer;

acquiring a target evaluation value of the answer according to the behavior data;

and when the target evaluation value is greater than or equal to a first threshold value, storing the answer and the question in a correlation mode, and sending the answer to a second user who uploads the question.

In a second aspect, an embodiment of the present application provides a community question and answer processing apparatus, wherein:

the communication unit is used for receiving answers replied by the first user for the questions;

the processing unit is used for acquiring behavior data of the first user in a community question-answer application corresponding to the question and the answer; acquiring a target evaluation value of the answer according to the behavior data;

a storage unit, configured to store the answer in association with the question when the target evaluation value is greater than or equal to a first threshold;

the communication unit is further configured to send the answer to a second user who uploads the question.

In a third aspect, an embodiment of the present application provides another community question-answering processing apparatus, including a processor, a memory, a communication interface, and one or at least one program, where the one or at least one program is stored in the memory and configured to be executed by the processor, and the program includes instructions for some or all of the steps described in the first aspect.

In a fourth aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, where the computer program makes a computer execute to implement part or all of the steps described in the first aspect.

The embodiment of the application has the following beneficial effects:

after the community question-answer processing method, the community question-answer processing device and the community question-answer processing medium are adopted, answers replied by the first user for questions are received, and then behavior data of the first user are obtained in the community question-answer application. And then acquiring the target evaluation value of the answer according to the behavior data of the first user. And when the target evaluation value is greater than or equal to the first threshold value, storing the answer and the question in a correlation manner, and sending the answer to a second user uploading the question, so that the second user or a user in the community question-answering application can obtain the answer to the question through the community question-answering application, and the answer is obtained through evaluation, so that the reference value of the answer is improved, and the question-answering management effect is convenient to improve.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Wherein:

fig. 1 is a schematic flow chart of a community question-answer processing method according to an embodiment of the present application;

fig. 2 is a schematic diagram of a logic structure of a community question and answer processing device according to an embodiment of the present application;

fig. 3 is a schematic entity structure diagram of a community question and answer processing device according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art without any inventive work according to the embodiments of the present application are within the scope of the present application.

The terms "first," "second," and the like in the description and claims of the present application and in the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

The network architecture applied by the embodiment of the application comprises a server and electronic equipment. The electronic device may be a Personal Computer (PC), a notebook computer, or a smart phone, and may also be an all-in-one machine, a palm computer, a tablet computer (pad), a smart television playing terminal, a vehicle-mounted terminal, or a portable device. The operating system of the PC-side electronic device, such as a kiosk or the like, may include, but is not limited to, operating systems such as Linux system, Unix system, Windows series system (e.g., Windows xp, Windows 7, etc.), Mac OS X system (operating system of apple computer), and the like. The operating system of the electronic device at the mobile end, such as a smart phone, may include, but is not limited to, an operating system such as an android system, an IOS (operating system of an apple mobile phone), a Window system, and the like.

The server is used for providing services for the electronic equipment. The electronic device in the embodiment of the application can install and run the application program, and the server can be a server corresponding to the application program installed in the electronic device and provide application service for the application program. The application program may be a single integrated application program, or an applet embedded in other applications, or a system on a web page, and the application program in the electronic device and the server is not limited in the present application, and the application program related to the community question and answer function may be referred to as a community question and answer application.

The number of the electronic devices and the number of the servers are not limited in the embodiment of the application, and the servers can provide services for the electronic devices at the same time. The server may be implemented as a stand-alone server or as a server cluster of multiple servers. The electronic device can be used as a device used by a questioning user and can also be used as a device used by a replying user.

In the embodiment of the application, the server can store behavior data of the user in the community question-answering application in advance. The behavior data is used to describe the user's behavior in the community question-and-answer application, such as browsing questions or answers, uploading questions, replying to questions, making opinions or suggestions, and the like. It can be understood that by analyzing the behavior data of the user, the knowledge hunting range and the interested direction of the user can be determined, which is convenient for improving the reference value for obtaining the answer questions of the user.

In one possible example, the behavior data may be divided into positive behavior data and negative behavior data. The positive behavior data may be positive behavior or positive energy behavior for the community question-and-answer application, such as question-and-answer good behavior, access good behavior, and the like. The negative behavior data may be negative behaviors or negative energy behaviors for the community question-answering application, such as a forced exit behavior, a behavior of maliciously evaluating reply content, a maliciously promoted behavior, and the like. It can be understood that the positive behavior data and the negative behavior data can be used for monitoring the behaviors of the users in the community question-answering application, and the environment of the question-answering community can be improved conveniently.

The server may also store, in advance, an evaluation rule or an evaluation model or the like for scoring a question or an answer in the community question-and-answer application, or an evaluation rule or an evaluation model or the like for analyzing behavior data of the user, which is not limited herein.

The behavior data of the user, the scoring rules or the evaluation models can be stored in a block created on the block chain network. The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer. Therefore, data are stored in a distributed mode through the block chain, data security is guaranteed, and meanwhile data sharing of information among different platforms can be achieved.

The method for processing the community questions and answers provided by the embodiment of the application can be executed by a community question and answer processing device, wherein the device can be realized by software and/or hardware, can be generally integrated in a server or electronic equipment, and can improve the reference value of answers in the community question and answer application.

Referring to fig. 1, fig. 1 is a schematic flow chart of a community question-answering processing method provided in the present application. Taking the application of the method to a server as an example for illustration, the method includes the following steps S101-S104, wherein:

s101: receiving answers to the question replies from the first user.

In this embodiment of the application, the first user is not limited, and may be any registered user in the community question and answer application, and is not limited herein. The method and the device for the question answering are not limited to the question answered by the first user, and the question answered by the first user can be uploaded by any user in the community question answering application. In the embodiment of the present application, the second user is referred to as a user who uploads a question in the community question and answer application. That is to say, after the second user uploads the question in the community question and answer application, the first user answers the question posed by the second user and uploads the answer to the community question and answer application, so that the server receives the answer replied by the first user to the question.

The answer of the first user to the question reply can be understood as the information input by the first user in the reply bar of the question. The comment column may be directly displayed below the question, or may be a text box that is expanded below the question after the first user clicks the reply function component.

S102: and acquiring the behavior data of the first user in the community question-answer application corresponding to the question and the answer.

In an embodiment of the application, the community answering application is an application for uploading a question for the second user and an application for replying a question for the first user. The first user performs reply operation in the community question and answer application, and the behavior data of the first user in the community question and answer application can be obtained according to the history record of the community question and answer application, wherein the reply operation indicates that the first user is registered in the community question and answer application. The content of the behavior data of the first user can be referred to the foregoing, and is not described herein again. It can be understood that by analyzing the behavior data of the first user, the knowledge hunting range and the interested question-answer direction of the first user can be determined, which is convenient for improving the reference value for obtaining the answer questions of the first user.

S103: and acquiring a target evaluation value of the answer according to the behavior data.

In the embodiment of the present application, the target evaluation value is used to describe the reference value of the answer. The present application is not limited to the method for acquiring the target evaluation value, and in one possible example, the step S103 includes the following steps a1 to a4, where:

a1: and acquiring a reference value for the first user to reply the question according to the behavior data.

In the embodiment of the present application, the reference value may be used to describe a probability that the first user can reply to the question positively, and may also be used to describe a success rate that the answer replied by the first user can solve the question. The method for obtaining the reference value is not limited, and the behavior data can be analyzed to obtain the probability that the first user can answer the problem positively and the success rate that the answer answered by the first user can solve the problem; obtaining a reference value based on the probability and the success rate, and the like. In one possible example, step A1 includes the following steps A11-A3, wherein:

a11: the technical area of the problem is determined.

The technical field may be a computer, a digital processing, a program, or a further technical branch, and is not limited herein. The method for determining the technical field is not limited, and the problem label can be passed; or analyzing the problem to obtain a plurality of keywords, and determining the technical field according to the technical characteristics corresponding to the keywords.

A12: and determining the front behavior probability of the first user and the acquaintance of the technical field according to the behavior data.

The positive behavior probability is used to describe a success rate at which the first user can answer or solve the problem positively, the success rate of the solution corresponding to the historical reply record of the first user can be obtained from the behavior data of the first user, and the positive behavior probability of the first user is determined according to the success rate, which is not limited herein. In one possible example, the behavior data includes a plurality of historical reply records, and step a12 includes the following steps a 121-a 123, wherein:

a121: and obtaining a quality score corresponding to each historical reply record in the plurality of historical reply records to obtain a plurality of quality scores.

The historical reply records are records of the first user replying to the questions in the community question-answering application, namely, each historical reply record comprises at least one answer of the question. The quality score is used for describing the response quality in each history response record, and can be understood as whether the answer can solve the problem, whether the expression of the answer is popular and easy to understand, whether ambiguity exists and the like.

The method for obtaining the quality score is not limited, the click rate of the answer and the comment information can be obtained, it can be understood that the answer with the high click rate has a certain credible value, the comment information can reflect whether the answer is accurately expressed, the quality score of the answer is determined based on the click rate and the comment information, and the accuracy rate of obtaining the quality score can be improved. The quality score can also be obtained by obtaining answers of all users to the historical reply records in the community answering application and comparing the answers according to the answers of all the users, so that different users can obtain different answers for the same question, the quality score corresponding to the historical reply record of the first user is obtained based on the answers of all the users to the questions corresponding to the same historical reply record, and the fairness of obtaining the quality score can be improved.

A122: calculating a weighted average of the plurality of quality scores.

A123: and determining the positive behavior probability of the first user according to the weighted average.

The weighted average value is obtained by weighting the weight and the quality score of each historical reply record, the weight of the historical reply record is not limited, and the weighted average value can be determined according to the click rate, the technical field, the audience range of users and the like of the historical reply record.

It can be understood that, in steps a121 to a123, the quality scores corresponding to the historical reply records are obtained, then the weighted average of the quality scores is calculated, and the positive behavior probability of the first user is determined according to the weighted average. That is to say, the positive behavior probability of the first user for replying to the question is obtained according to the weighted evaluation value of the quality score of the first user, so that the accuracy of determining the positive behavior probability can be further improved.

In the embodiments of the present application, the familiarity value is used to describe the degree of familiarity of the first user with the technical field of the problem. The method for determining the acquaintance is not limited, and a behavior record set corresponding to the technical field of the problem can be obtained from the behavior data of the first user, and the acquaintance of the first user to the technical field is determined according to the behavior record set. In one possible example, where the behavioral data includes a plurality of historical reply records, step a12 may further include the following steps a 124-a 126, where:

a124: and analyzing each historical reply record in the plurality of historical reply records to obtain a plurality of technical characteristics.

The technical features may be a subject or a keyword of the history reply record, or a technical point corresponding to the subject or the keyword, and the like, which is not limited herein. For example, if the question is an N-Gram model, the answer in the history reply record may be that "N-Gram is an algorithm based on a statistical language model. The basic idea is to perform a sliding window operation with the size of N on the content in the text according to bytes, and form a byte fragment sequence with the length of N. Each byte segment is called as a gram, the occurrence frequency of all the grams is counted, and filtering is performed according to a preset threshold value to form a key gram list, namely a vector feature space of the text, wherein each gram in the list is a feature vector dimension. ", technical features may be n-gram models, statistical language models, byte fragments, sequences, probabilities, frequencies, feature vectors, vector spaces, etc.

A125: determining the number of technical features belonging to the technical field in the plurality of technical features.

A126: determining a learned familiarity of the first user with the technical field based on a ratio between the number and a total number of the plurality of technical features.

It is understood that in steps a124 to a126, the technical features related to each historical reply record are obtained, then the number of the technical features belonging to the technical field is determined, and the familiarity of the first user with the technical field is determined according to the ratio between the number and the total number of the technical features. That is, the familiarity of the first user with the technical field is determined according to the ratio of the information answered by the first user to the technical field, so that the accuracy of determining the familiarity can be improved.

A13: and acquiring a reference value of the first user for replying the question according to the positive behavior probability and the familiar value.

The method for obtaining the reference value by the front behavior probability and the familiar value is not limited in the application, and the reference value can be obtained by weighting according to the familiar value and the front behavior probability, or by selecting the maximum value or the minimum value between the front behavior probability and the familiar value.

It can be understood that in a 11-a 13, the positive behavior probability of the first user and the familiarity of the first user with the technical field of the question are determined according to the behavior data, and then the reference value of the first user for answering the question is obtained according to the familiarity and the positive behavior probability, so that the accuracy of obtaining the reference value can be improved, and the accuracy of processing operation on the answer answered by the first user can be improved.

A2: and acquiring the reply quality of the answer according to the reference value.

The reply quality can be used for describing whether the expression of the answer is accurate or not and describing whether the answer can solve the problem or not. The method for acquiring the reply quality by the reference value is not limited, and the matching value between the answer and the question can be obtained by weighting according to the reference value. In one possible example, step A2 includes the following steps A21-A23, wherein:

a21: a question depth of the question and an answer depth of the answer are determined.

The problem depth is used for describing the technical level defined by the problem, and can be understood as a shallow problem or a deep problem. The answer depth may be understood as whether it is a general answer or a specific answer.

A22: and acquiring a matching value between the question and the answer according to the answer depth and the question depth.

Wherein the matching value is used for the success rate at which the answer can solve the problem. The method for obtaining the matching value is not limited, and the matching value can be obtained according to the difference between the answer depth and the question depth.

Further, the problem is divided to obtain a plurality of sub-problems; determining the question depth of the sub-question and the answer depth of answer information corresponding to the sub-question in the answer; acquiring sub-matching values between each sub-question and answer information corresponding to each sub-question according to the question depth of each sub-question and the answer depth of the answer information corresponding to each sub-question in the answer; and acquiring a matching value between the question and the answer according to a sub-matching value between the sub-question and the answer information corresponding to the sub-question. It can be understood that from the perspective of the sub-question, obtaining the matching value between the question and the answer can improve the accuracy of obtaining the matching value.

A23: and acquiring the reply quality of the answer according to the reference value and the matching value.

The method for acquiring the reply quality by the reference value and the matching value is not limited, and the reply quality can be acquired by weighting according to the reference value and the matching value, or by selecting the maximum value or the minimum value between the reference value and the matching value.

It is to be understood that, in steps a 21-a 23, a matching value between the question and the answer is obtained according to the question depth of the question and the answer depth of the answer, and then the answer quality is obtained according to the reference value and the matching value. That is, the reply quality is obtained according to the matching value obtained by analyzing whether the answer can fundamentally solve the problem and the reference value obtained by behavior data, and the accuracy rate of obtaining the reply quality can be improved.

A3: and obtaining the statement quality of the answer.

The statement quality is used for describing whether the expression of the answer is accurate, and can include the aspects of completeness, readability, compliance and the like. The method for obtaining the statement quality is not limited, and the statement quality can be obtained based on a preset statement analysis model, and can also be obtained by comparing answers with reference answers of questions, wherein the reference answers can be obtained by inputting the questions into a pre-established question-answer model, or answers given by experts in the technical field corresponding to the answers, and the like.

In one possible example, step A3 includes steps a31 and a32, wherein:

a31: and acquiring the completeness, complexity and smoothness of the answer.

Wherein the completeness is used to describe the completeness of the answer. The completeness can be determined by detecting whether an abbreviation exists in the answer, such as a move-guest phrase, a centering phrase, etc.; if an abbreviation exists, the completeness may be determined based on the number of abbreviations and the ratio between the character length and the total character length of the answer. Completeness may also be determined by detecting whether the last punctuation in the answer is an end symbol (e.g., a period, exclamation point); if not, it can analyze whether it is a complete sentence; if the answer is determined to be an incomplete sentence, the number of the elements which require answer in the answer and the number of the elements which require answer in the question can be determined.

The integrity can also be labeled based on the attributes of the part of speech and the syntax in the answer to obtain the dependency relationship; and then counting the obtained integrity based on a pre-established part-of-speech model (such as n-gram). Where n-gram is an algorithm based on a statistical language model. The basic idea is to perform a sliding window operation with the size of N on the content in the text according to bytes, and form a byte fragment sequence with the length of N. For Chinese, we refer to the Chinese Language Model (CLM), which uses the collocation information between adjacent words in the context, when needing to convert continuous space-free pinyin, strokes, or numbers representing letters or strokes into Chinese character strings (i.e. sentences), the CLM can calculate the sentences with the maximum probability, thereby realizing the automatic conversion to Chinese characters, without manual selection of users, avoiding the problem of duplication code that many Chinese characters correspond to one same pinyin (or stroke string, or number string).

The integrity can also be combined with semantic role labeling to identify predicates-arguments in the sentence, and combined with syntactic analysis to analyze words with dependency relationships such as subject, preposed object and the like in the sentence; and identifying the central language of the centered structural phrase which accords with a specific range, and checking whether a corresponding fixed language exists.

Complexity is used to describe the complexity of the answer, and may be understood as the ease with which the answer is understood. The complexity can be determined by detecting the uncommon word and the number of the uncommon word in the answer, the length of the number of words in the answer, the number of strokes of the character and the like, or the business vocabulary in a specific field in the answer. It can be understood that uncommon words are difficult for most users to understand, and when the number of strokes of a character is large, the character can be a uncommon word. Answers with a large number of words or long sentences are more difficult to understand than short sentences. Domain-specific business vocabularies are difficult for domain-unspecified users to understand.

The popularity is used for describing whether the answer is popular or not, and can be obtained by judging whether interrupted, missing or misspelled words exist in the answer or not.

The completeness, complexity and compliance may be described in terms of a percentage or a decimal number, and are not limited thereto. The method for acquiring the integrity, the complexity and the compliance is not limited.

A32: and obtaining the sentence quality of the answer according to the completeness, the complexity and the currency.

The method for acquiring the sentence quality of the answer by the integrity, the complexity and the currency is not limited, and the maximum value or the minimum value among the integrity, the complexity and the currency or the weighted average value among the integrity, the complexity and the currency can be acquired.

It can be understood that, in step a31 and step a32, the completeness, complexity, and compliance of the answer are respectively obtained, and then the sentence quality of the answer is obtained based on the completeness, complexity, and compliance of the answer, that is, the sentence quality of the answer is obtained from the degree of whether the expression of the answer is complete, difficult to understand, and smooth, so that the accuracy of obtaining the sentence quality can be improved.

A4: and acquiring a target evaluation value of the answer according to the statement quality and the reply quality.

The method for acquiring the target evaluation value of the sentence quality and the reply quality is not limited in the present application, and the maximum value or the minimum value between the sentence quality and the reply quality, or the weighted average value between the sentence quality and the reply quality, etc. may be acquired.

It is understood that in steps a 1-a 4, a reference value for the first user to answer the question is obtained according to the behavior data of the first user, and then the answer quality of the answer is obtained according to the reference value. And then obtaining the sentence quality of the answer, and obtaining the target evaluation value of the answer according to the sentence quality and the reply quality. That is to say, the target evaluation value of the answer is obtained from the sentence quality described by the answer and the reply quality obtained according to the behavior data of the user, and the accuracy of obtaining the target evaluation value can be improved.

S104: and when the target evaluation value is greater than or equal to a first threshold value, storing the answer and the question in a correlation mode, and sending the answer to a second user who uploads the question.

The first threshold is not limited in the present application, and may be set by the technical field of the question, or may be set by a reference answer to the question, or a target evaluation value of an answer to the question sent by another user, for example, an average value of a plurality of target evaluation values. It is to be understood that when the target evaluation value is greater than or equal to the first threshold value, the question replied by the first user has a certain reference value, and the answer may be stored in association with the question as a possible answer, so that the second user or a user in the community question-and-answer application refers to the answer when browsing the question.

It is to be understood that, in steps S101-S104, the answer to the question reply from the first user is received, and then the behavior data of the first user is obtained in the community question and answer application. And then acquiring the target evaluation value of the answer according to the behavior data of the first user. And when the target evaluation value is greater than or equal to the first threshold value, storing the answer and the question in a correlation manner, and sending the answer to a second user uploading the question, so that the second user or a user in the community question-answering application can obtain the answer to the question through the community question-answering application, and the answer is obtained through evaluation, so that the reference value of the answer is improved, and the question-answering management effect is convenient to improve.

In one possible example, the method further comprises: and deleting the answer when the target evaluation value is smaller than the first threshold value. It can be understood that when the target evaluation value is smaller than the first threshold, the reference value indicating that the first user replies to the question is small, and the answer is not uploaded to the community question and answer application, so that the reference value of the question and answer is improved, and the effect of managing the reply questions of the community question and answer application is facilitated to be improved. When the target evaluation value is smaller than the first threshold value, the first user can be prompted to modify the answer or provide some opinions for the first user to refer to. And when the first user does not modify the answer, executing the step of deleting the answer, so that the writing attitude of the user for answering the question is improved.

In one possible example, before step S101, the method further comprises the following step B1 and step B2, wherein:

b1: and acquiring a reference evaluation value of the problem.

The reference evaluation value is used for describing a reference value uploaded to the community question and answer application by the question, and may include audience range of users in the community question and answer application, whether the question is repeated in the community question and answer application, whether the question is a question of a positive behavior, and the like. The method for acquiring the reference evaluation value is not limited, and the reference evaluation value can be acquired by referring to the sentence quality of the answer and the sentence quality is used as the reference evaluation value. It can be understood that the statement quality of the question, which embodies the language expression of the question, is easy for the user in the community answering application to reply or think when the language expression is simple and clear and popular. The reference evaluation value may be checked for duplicate according to the technical field and the problem depth, and it can be understood that a problem with a high repetition rate indicates that the same problem is involved in the current community problem application, and in order to avoid occupying a memory, the problem may not be uploaded, but an answer to the same or similar problem is sent to a second user for questioning. The reference evaluation value may alternatively determine whether the problem has a positive behavior probability or the like from a reference value corresponding to the behavior data of the second user. It will be appreciated that the direction and scope of knowledge involvement of the second user may be determined from the second user's behavioral data, and thus whether the question is a question that the second user has positive meaning to ask.

B2: and when the reference evaluation value is larger than or equal to a second threshold value, uploading the question in a community question-answering application corresponding to the question.

The second threshold value is not limited, and can be determined according to the level of the second user in the community question-answering application, the difficulty degree of the problem and the like.

It can be understood that, in steps B1 and B2, the reference evaluation value of the question is obtained, and when the reference evaluation value is greater than or equal to the second threshold, it indicates that uploading the question in the current community question-answering application has a certain reference value, so that uploading the question in the community question-answering application can improve the reference value of the question, and facilitate to improve the effect of managing the question-answering.

In one possible example, the method further comprises: deleting the problem when the reference evaluation value is smaller than the second threshold. It can be understood that when the reference evaluation value is smaller than the second threshold, it indicates that the reference value brought by uploading the question by the second user in the community question-and-answer application is small, so that the question is deleted, so that the question is not uploaded to the community question-and-answer application, and the reference value of the question is conveniently improved.

It should be noted that, when the reference evaluation value is smaller than the second threshold, the second user may also be prompted to modify the question, or some questions may be provided for the second user to select. And when the second user does not modify or select, executing the step of deleting the question, thereby being convenient for improving the attitude of the user for writing the question and the positivity of asking the question.

The method of the embodiments of the present application is set forth above in detail and the apparatus of the embodiments of the present application is provided below.

Referring to fig. 2, fig. 2 is a schematic structural diagram of a community question-answering processing device according to the present application, and as shown in fig. 2, the community question-answering processing device 200 includes:

a communication unit 202, configured to receive an answer returned by the first user to the question;

the processing unit 201 is configured to obtain behavior data of the first user in a community question-and-answer application corresponding to the question and the answer; acquiring a target evaluation value of the answer according to the behavior data;

a storage unit 203, configured to store the answer in association with the question when the target evaluation value is greater than or equal to a first threshold;

the communication unit 202 is further configured to send the answer to a second user who uploads the question.

In a possible example, the processing unit 201 is specifically configured to obtain, according to the behavior data, a reference value for the first user to reply to the question; acquiring the reply quality of the answer according to the reference value; obtaining statement quality of the answer; and acquiring a target evaluation value of the answer according to the statement quality and the reply quality.

In a possible example, the processing unit 201 is specifically configured to determine a technical field corresponding to the problem; determining the front behavior probability of the first user and the acquaintance of the first user to the technical field according to the behavior data; and acquiring a reference value of the first user for replying the question according to the positive behavior probability and the familiar value.

In a possible example, the behavior data includes a plurality of historical reply records, and the processing unit 201 is specifically configured to obtain a quality score corresponding to each of the plurality of historical reply records, so as to obtain a plurality of quality scores; calculating a weighted average of the plurality of quality scores; determining the positive behavior probability of the first user according to the weighted average value; analyzing each historical reply record in the plurality of historical reply records to obtain a plurality of technical characteristics; determining the number of technical features belonging to the technical field in the plurality of technical features; determining a learned familiarity of the first user with the technical field based on a ratio between the number and a total number of the plurality of technical features.

In one possible example, the processing unit 201 is specifically configured to determine a question depth of the question, and an answer depth of the answer; obtaining a matching value between the question and the answer according to the answer depth and the question depth; and acquiring the reply quality of the answer according to the reference value and the matching value.

In one possible example, the processing unit 201 is specifically configured to obtain the completeness, complexity, and compliance of the answer; and obtaining the sentence quality of the answer according to the completeness, the complexity and the currency.

In one possible example, the processing unit 201 is further configured to obtain a reference evaluation value for the second user to ask the question; uploading the question in the community question-and-answer application when the reference evaluation value is greater than or equal to a second threshold value.

For detailed processes executed by each unit in the community question-answering processing device 200, reference may be made to the execution steps in the foregoing method embodiments, which are not described herein again.

Referring to fig. 3, fig. 3 is a schematic structural diagram of another community question-answering processing device according to an embodiment of the present application, where the community question-answering processing device may be a server. As shown in fig. 3, the community question-answering processing device 300 includes a processor 310, a memory 320, a communication interface 330, and one or at least one program 340. The related functions implemented by the communication unit 202 shown in fig. 2 can be implemented by the communication interface 330, the related functions implemented by the storage unit 203 shown in fig. 2 can be implemented by the memory 320, and the related functions implemented by the processing unit 201 shown in fig. 2 can be implemented by the processor 310.

The one or more programs 340 are stored in the memory 320 and configured to be executed by the processor 310, the programs 340 including instructions for:

receiving answers replied by the first user aiming at the questions;

In one possible example, in terms of the target evaluation value of the answer obtained according to the behavior data, the program 340 is specifically configured to execute the following steps:

acquiring a reference value of the first user for replying the question according to the behavior data;

acquiring the reply quality of the answer according to the reference value;

obtaining statement quality of the answer;

and acquiring a target evaluation value of the answer according to the statement quality and the reply quality.

In one possible example, in terms of the obtaining the reference value for the first user to reply to the question according to the behavior data, the program 340 is specifically configured to execute the following steps:

determining the technical field corresponding to the problem;

determining the front behavior probability of the first user and the acquaintance of the first user to the technical field according to the behavior data;

acquiring a reference value of the first user for replying the question according to the positive behavior probability and the familiar value;

analyzing each historical reply record in the plurality of historical reply records to obtain a plurality of technical characteristics;

determining the number of technical features belonging to the technical field in the plurality of technical features;

determining a learned familiarity of the first user with the technical field based on a ratio between the number and a total number of the plurality of technical features.

In one possible example, the behavior data includes a plurality of historical reply records, and in the determining the probability of positive behavior of the first user based on the behavior data, the program 340 is specifically configured to execute the following steps:

obtaining a quality score corresponding to each historical reply record in the plurality of historical reply records to obtain a plurality of quality scores;

calculating a weighted average of the plurality of quality scores;

and determining the positive behavior probability of the first user according to the weighted average.

In one possible example, in terms of the quality of the answer obtained according to the reference value, the program 340 is specifically configured to execute the following steps:

determining a question depth of the question and an answer depth of the answer;

obtaining a matching value between the question and the answer according to the answer depth and the question depth;

and acquiring the reply quality of the answer according to the reference value and the matching value.

In one possible example, in terms of the quality of the statement for obtaining the answer, the program 340 is specifically configured to execute the following steps:

acquiring the completeness, complexity and smoothness of the answer;

and obtaining the sentence quality of the answer according to the completeness, the complexity and the currency.

In one possible example, prior to the receiving the first user's answer to the question reply, the program 340 is further for executing the instructions of:

acquiring a reference evaluation value for the second user to ask the question;

uploading the question in the community question-and-answer application when the reference evaluation value is greater than or equal to a second threshold value.

Embodiments of the present application also provide a computer storage medium, where the computer storage medium stores a computer program for causing a computer to execute to implement part or all of the steps of any one of the methods described in the method embodiments, and the computer includes an electronic device and a server.

Embodiments of the application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform to implement some or all of the steps of any of the methods recited in the method embodiments. The computer program product may be a software installation package, the computer comprising an electronic device and a server.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art will also appreciate that the embodiments described in this specification are presently preferred and that no particular act or mode of operation is required in the present application.

In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, at least one unit or component may be combined or integrated with another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may also be distributed on at least one network unit. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a hardware mode or a software program mode.

The integrated unit, if implemented in the form of a software program module and sold or used as a stand-alone product, may be stored in a computer readable memory. With such an understanding, the technical solution of the present application may be embodied in the form of a software product, which is stored in a memory and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned memory comprises: various media capable of storing program codes, such as a usb disk, a read-only memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and the like.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash disk, ROM, RAM, magnetic or optical disk, and the like.

The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A community question-answer processing method is characterized by comprising the following steps:

receiving answers replied by the first user aiming at the questions;

2. The method of claim 1, wherein obtaining the target evaluation value of the answer from the behavior data comprises:

acquiring the reply quality of the answer according to the reference value;

obtaining statement quality of the answer;

3. The method according to claim 2, wherein the obtaining a reference value for the first user to answer the question according to the behavior data comprises:

determining the technical field corresponding to the problem;

and acquiring a reference value of the first user for replying the question according to the positive behavior probability and the familiar value.

4. The method of claim 3, wherein the behavior data comprises a plurality of historical reply records, wherein determining the positive behavior probability of the first user from the behavior data and the familiarity value of the first user with the technology domain comprises:

calculating a weighted average of the plurality of quality scores;

determining the positive behavior probability of the first user according to the weighted average value;

5. The method according to claim 2, wherein said obtaining the answer quality of the answer according to the reference value comprises:

determining a question depth of the question and an answer depth of the answer;

6. The method of claim 2, wherein obtaining the statement quality of the answer comprises:

acquiring the completeness, complexity and smoothness of the answer;

7. The method of any of claims 1-6, wherein prior to the receiving the first user's answer to the question reply, the method further comprises:

acquiring a reference evaluation value of the problem;

8. A community question-answering processing apparatus, comprising:

9. A community question-answer processing apparatus comprising a processor, a memory, a communications interface and one or at least one program, wherein the one or at least one program is stored in the memory and configured to be executed by the processor, the program comprising instructions for carrying out the steps in the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, the computer program causing a computer to execute to implement the method of any one of claims 1-7.