Question and answer response method and device

By obtaining and combining Q&A data from different channels, calculating answer similarity and updating weights, answer sorting problems in the prior art are solved, and the accuracy and efficiency of Q&A responses are improved.

CN111782794BActive Publication Date: 2024-11-26BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010474990.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-05-29
Publication Date
2024-11-26
Estimated Expiration
2040-05-29

AI Technical Summary

Technical Problem

Existing Q&A response methods are difficult to effectively obtain the answers users really want. Users need to find the correct answers in a large amount of data, and the accuracy and weight of the answers are difficult to sort.

Method used

By obtaining the first and second key value pair sets from different channels, combining and calculating the similarity of the answers, sorting and updating the answers based on preset weights and accuracy thresholds, and pushing them to the user.

Benefits of technology

Improves the accuracy and effectiveness of answers, saves users time to find answers, and ensures that higher-weighted answers are ranked first.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111782794B_ABST
    Figure CN111782794B_ABST
Patent Text Reader

Abstract

The present application discloses a question-answer response method and device: based on the query question raised by the questioner, a first key-value pair set and a second key-value pair set determined from different channels are obtained, wherein the first key-value pair set is composed of at least one first answer-first preset weight key-value pair, and the second key-value pair set is composed of at least one second answer-second preset weight key-value pair; based on the first key-value pair set and the second key-value pair set, a third key-value pair set is determined, and the third key-value pair set is composed of at least one third answer-third preset weight key-value pair; based on each third preset weight in the third key-value pair set, each third answer-third preset weight key-value pair is sorted, and each third answer in the sorted third key-value pair set is pushed to the questioner. This method effectively improves the effectiveness of the answers pushed to the user and saves the user time in finding the correct answer.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, specifically to the field of information processing, and in particular to a question-and-answer response method and device. Background Art

[0002] There are two main existing question-answer response methods:

[0003] 1. When searching for a question, a large amount of data will appear directly. Some of the searched data are sorted by bidding ranking, some by page views, some by number of comments, and some by likes, etc. It is difficult for users to get the answers they really want.

[0004] Second, users are divided into different levels according to the correctness of their answers, and then people of different levels answer questions of different levels. Summary of the invention

[0005] Embodiments of the present application provide a question-and-answer response method, apparatus, device, and storage medium.

[0006] According to a first aspect, a question-answer response method is provided, the method comprising: based on a query question raised by a questioner, obtaining a first key-value pair set and a second key-value pair set determined from different channels, the first key-value pair set consisting of at least one first answer-first preset weight key-value pair, and the second key-value pair set consisting of at least one second answer-second preset weight key-value pair; based on the first key-value pair set and the second key-value pair set, determining a third key-value pair set, the third key-value pair set consisting of at least one third answer-third preset weight key-value pair; based on each third preset weight in the third key-value pair set, sorting each third answer-third preset weight key-value pair, and pushing each third answer in the sorted third key-value pair set to the questioner.

[0007] In some embodiments, each first answer in the first key-value pair set is obtained based on at least one answer corresponding to the query question found in the entire network data; each second answer in the second key-value pair set is obtained based on at least one answer given by the respondent to the query question in the entire network data.

[0008] In some embodiments, each first preset weight in the first key-value pair set is determined based on the professionalism of the source website that provides the first answer corresponding to the first preset weight; each second preset weight in the second key-value pair set is determined based on the accuracy of the second answer corresponding to the second preset weight given by the respondent in the entire network data.

[0009] In some embodiments, each second preset weight in the second key-value pair set is determined based on the accuracy of the second answer given by the respondent in the whole network data and corresponding to the second preset weight, including: each second preset weight in the second key-value pair set is determined based on the following data in the whole network data: whether the accuracy of the answers historically given by the respondent is greater than or equal to a preset accuracy threshold; whether the second answer given by the respondent and corresponding to the second preset weight is adopted by the questioner; whether the second answer given by the respondent and corresponding to the second preset weight is adopted by the visitor and the number of times it is adopted by the visitor.

[0010] In some embodiments, based on the first key-value pair set and the second key-value pair set, determining the third key-value pair set includes: merging the first key-value pair set and the second key-value pair set to obtain an initial third key-value pair set, the initial third key-value pair set consisting of at least one initial third answer-initial third preset weight key-value pair; calculating the similarity between each pair of initial third answers in the initial third key-value pair set; in response to the presence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, updating the initial third key-value pair set to obtain a third key-value pair set.

[0011] In some embodiments, in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, updating the initial third key-value pair set includes: for the initial third key-value pair set, in response to the existence of two initial third answers whose similarity is greater than or equal to the preset similarity threshold, adding the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain the added weights, and using the added weights as the weights of the two initial third answers whose similarity is greater than or equal to the preset similarity threshold.

[0012] In some embodiments, in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, updating the initial third key-value pair set includes: for the initial third key-value pair set, in response to the existence of two initial third answers whose similarity is greater than or equal to the preset similarity threshold, merging the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain a merged initial third answer; adding the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain an added weight, and using the added weight as the weight of the merged initial third answer.

[0013] In some embodiments, based on each third preset weight in the third key-value pair set, each third answer-third preset weight key-value pair is sorted, and each third answer in the sorted third key-value pair set is pushed to the questioner, including: based on the third preset weight corresponding to each third answer in the third key-value pair set and the verification message received by the manual verification interface, each third answer in the third key-value pair set is sorted, and each third answer in the sorted third key-value pair set is pushed to the questioner.

[0014] According to a second aspect, a question-answer response device is provided, which includes: an acquisition module, configured to acquire a first key-value pair set and a second key-value pair set determined from different channels based on a query question raised by a questioner, the first key-value pair set consisting of at least one first answer-first preset weight key-value pair, and the second key-value pair set consisting of at least one second answer-second preset weight key-value pair; a determination module, configured to determine a third key-value pair set based on the first key-value pair set and the second key-value pair set, the third key-value pair set consisting of at least one third answer-third preset weight key-value pair; a push module, configured to sort each third answer-third preset weight key-value pair based on each third preset weight in the third key-value pair set, and push each third answer in the sorted third key-value pair set to the questioner.

[0015] In some embodiments, each first answer in the first key-value pair set is obtained based on at least one answer corresponding to the query question found in the entire network data; each second answer in the second key-value pair set is obtained based on at least one answer given by the respondent to the query question in the entire network data.

[0016] In some embodiments, each first preset weight in the first key-value pair set is determined based on the professionalism of the source website that provides the first answer corresponding to the first preset weight; each second preset weight in the second key-value pair set is determined based on the accuracy of the second answer corresponding to the second preset weight given by the respondent in the entire network data.

[0017] In some embodiments, each second preset weight in the second key-value pair set is determined based on the accuracy of the second answer given by the respondent in the whole network data and corresponding to the second preset weight, including: each second preset weight in the second key-value pair set is determined based on the following data in the whole network data: whether the accuracy of the answers historically given by the respondent is greater than or equal to a preset accuracy threshold; whether the second answer given by the respondent and corresponding to the second preset weight is adopted by the questioner; whether the second answer given by the respondent and corresponding to the second preset weight is adopted by the visitor and the number of times it is adopted by the visitor.

[0018] In some embodiments, the determination module includes: a merging unit, configured to merge the first key-value pair set and the second key-value pair set to obtain an initial third key-value pair set, wherein the initial third key-value pair set is composed of at least one initial third answer-initial third preset weight key-value pair; a calculation unit, configured to calculate the similarity between each pair of initial third answers in the initial third key-value pair set; and an updating unit, configured to update the initial third key-value pair set in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, to obtain a third key-value pair set.

[0019] In some embodiments, the updating unit is further configured to: for the initial third key-value pair set, in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, add the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain the added weights, and use the added weights as the weights of the two initial third answers whose similarity is greater than or equal to the preset similarity threshold.

[0020] In some embodiments, the update unit is further configured to: for the initial third key-value pair set, in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, merge the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain a merged initial third answer; add the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain the added weight, and use the added weight as the weight of the merged initial third answer.

[0021] In some embodiments, the push module is further configured to: sort the third answers in the third key-value pair set based on the third preset weight corresponding to each third answer in the third key-value pair set and the verification message received by the manual verification interface, and push the third answers in the sorted third key-value pair set to the questioner.

[0022] According to a third aspect, an electronic device is provided, which includes one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement a question and answer response method as in any embodiment of the first aspect.

[0023] According to a fourth aspect, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the question-and-answer response method of any embodiment of the first aspect is implemented.

[0024] The present application obtains a first key-value pair set and a second key-value pair set determined from different channels based on a query question raised by a questioner, and determines a third key-value pair set based on the first key-value pair set and the second key-value pair set, thereby effectively expanding the range of answers obtained, and at the same time, sorts each third answer-third preset weight key-value pair based on each third preset weight in the third key-value pair set, and pushes each third answer in the sorted third key-value pair set to the questioner, so that answers with higher weights, i.e., answers with higher accuracy, are sorted higher and are easier to be obtained by the questioner who raises the query question, thereby improving the effectiveness of the pushed answers while saving the user's time in finding the correct answers.

[0025] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0027] Figure 2 is a flowchart of an embodiment of a question-answer response method according to the present application;

[0028] Figure 3 is a schematic diagram of an application scenario of the question-answer response method according to the present application;

[0029] Figure 4 is a flowchart of another embodiment of the question-answer response method according to the present application;

[0030] Figure 5 is a schematic diagram of an embodiment of a question-answer response device according to the present application;

[0031] Figure 6 It is a structural diagram of a computer system suitable for implementing a server of an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0033] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0034] Figure 1 An exemplary system architecture 100 is shown to which embodiments of the question-answer response method of the present application may be applied.

[0035] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0036] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications, such as search applications, question-and-answer applications, etc., can be installed on terminal devices 101, 102, 103.

[0037] Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules (for example, to provide question-and-answer response services), or they can be implemented as a single software or software module. No specific limitation is made here.

[0038] Server 105 can be a server that provides various services, such as processing query questions uploaded by terminal devices 101, 102, and 103, obtaining a first key-value pair set and a second key-value pair set determined from different channels based on the query question raised by the questioner, determining a third key-value pair set based on the first key-value pair set and the second key-value pair set, sorting each third answer-third preset weight key-value pair based on each third preset weight in the third key-value pair set, and pushing each third answer in the sorted third key-value pair set to the questioner.

[0039] It should be noted that the question and answer response method provided in the embodiment of the present application is generally executed by the server 105 , and accordingly, the question and answer response device is generally set in the server 105 .

[0040] It should also be noted that the terminal devices 101, 102, 103 may also be installed with question-and-answer response applications, and the terminal devices 101, 102, 103 may also process based on the query questions raised by the questioner. In this case, the question-and-answer response method may also be executed by the terminal devices 101, 102, 103, and accordingly, the question-and-answer response device may also be set in the terminal devices 101, 102, 103. In this case, the exemplary system architecture 100 may also not include the server 105 and the network 104.

[0041] It should be noted that the server 105 can be hardware or software. When the server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, for providing question-answer response services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0042] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0043] Figure 2 A flowchart 200 of an embodiment of a question-answer response method that can be applied to the present application is shown. The question-answer response method includes the following steps:

[0044] Step 201 : based on a query question raised by a questioner, a first key-value pair set and a second key-value pair set determined from different channels are obtained.

[0045] In this embodiment, the execution subject (for example, Figure 1 The server 101 or the terminal devices 101, 102, 103) may first receive a query question sent by a questioner through the terminal device, and then obtain a first key-value pair set and a second key-value pair set determined from different channels.

[0046] Here, various communication applications may be installed on the terminal device, such as search applications, question-and-answer applications, and the like.

[0047] The first key-value pair set consists of at least one first answer-first preset weight key-value pair, and the second key-value pair set consists of at least one second answer-second preset weight key-value pair.

[0048] It should be pointed out that the execution entity may obtain the first key-value pair set and the second key-value pair set through a variety of channels, such as question-and-answer websites, question-and-answer knowledge bases, answer sets provided by respondents, data from the entire network, etc. This application does not limit this.

[0049] Among them, the first preset weight corresponding to each first answer in the first key-value pair set obtained from different channels and the second preset weight corresponding to each second answer in the second key-value pair set can be set according to experience, specific application scenarios and actual needs. For example, the first preset weight corresponding to each first answer in the first key-value pair obtained from the question-and-answer website can be determined according to the working time limit in the relevant field of the answerer who provides the first answer. The longer the working time limit, the greater the weight; the second preset weight corresponding to each second answer in the second key-value pair obtained from the question-and-answer knowledge base can be determined according to the historical visits of each second answer. The higher the historical visits, the greater the weight.

[0050] In some optional methods, each first answer in the first key-value pair set is obtained based on at least one answer corresponding to the query question found in the entire network data; each second answer in the second key-value pair set is obtained based on at least one answer given by the respondent to the query question in the entire network data.

[0051] In this implementation, each first answer in the first key-value pair set may be an answer obtained by the execution subject through searching the entire network data according to the query question, and the answer is more comprehensive and theoretical.

[0052] Each first answer in the second key-value pair set may be an answer given by the respondent to the query question in the entire network data. Here, the answer given by the respondent combines the respondent's understanding of the query question and the knowledge related to the query question that the respondent knows, making the answer more practical.

[0053] In some optional embodiments, each first preset weight in the first key-value pair set is determined based on the professionalism of the source website that provides the first answer corresponding to the first preset weight; each second preset weight in the second key-value pair set is determined based on the accuracy of the second answer corresponding to the second preset weight given by the respondent in the entire network data.

[0054] In this implementation, each first preset weight in the first key-value pair set is determined based on the professionalism of the source website that provides the first answer corresponding to the first preset weight. Generally, the higher the professionalism of the source website, the higher the corresponding weight, and the lower the professionalism of the source website, the lower the corresponding weight. For example, the weight of the answer provided by a professional paper website is higher, while the weight of the answer provided by an ordinary search website is lower.

[0055] Each second preset weight in the second key-value pair set is determined based on the accuracy of the second answer given by the answerer in the whole network data and corresponding to the second preset weight. Generally, the higher the accuracy of the answer given by the answerer, the higher the corresponding weight, and the lower the accuracy of the answer given by the answerer, the lower the corresponding weight.

[0056] Here, the accuracy of the answer given by the respondent can be determined in a variety of ways, such as the number of times the respondent has historically answered questions related to the query question, the degree of relevance of the answer given by the respondent to the query question, whether the respondent is an active user, etc.

[0057] In some optional embodiments, each second preset weight in the second key-value pair set is determined based on the accuracy of the second answer given by the respondent in the entire network data and corresponding to the second preset weight, including: each second preset weight in the second key-value pair set is determined based on the following data in the entire network data: whether the accuracy of the answers historically given by the respondent is greater than or equal to a preset accuracy threshold; whether the second answer given by the respondent and corresponding to the second preset weight is adopted by the questioner; whether the second answer given by the respondent and corresponding to the second preset weight is adopted by the visitor and the number of times it is adopted by the visitor.

[0058] In this implementation, each second preset weight in the second key-value pair set is determined based on the following data in the whole network data:

[0059] (1) Whether the accuracy of the answers given by the respondent in the past is greater than or equal to the preset accuracy threshold. Specifically, the execution subject sets the accuracy threshold of the answers given by the respondent in the past. If the accuracy of the answers given by the respondent in the past is greater than or equal to the preset accuracy threshold, the second preset weight corresponding to the second answer given by the respondent can be increased according to actual needs. For example, the preset accuracy threshold is 80%, and the respondent has answered 100 questions in the past, that is, 100 answers were given, of which 82 were identified as accurate answers by relevant professionals or artificial intelligence in related fields, that is, the accuracy of the respondent's historical answers to questions is greater than the preset accuracy threshold, so the second preset weight corresponding to the second answer given by the respondent can be appropriately increased.

[0060] (2) Whether the second answer given by the answerer and corresponding to the second preset weight is accepted by the questioner. If the answer given by the answerer is accepted by the questioner, that is, the questioner approves the answer given by the answerer, the second preset weight corresponding to the second answer given by the answerer can be appropriately increased according to actual needs.

[0061] (3) Whether the second answer given by the respondent corresponding to the second preset weight is adopted by the interviewer and the number of times it is adopted by the interviewer. If the answer given by the respondent is adopted by the interviewer, that is, the interviewer approves the answer given by the respondent, the second preset weight corresponding to the second answer given by the respondent can be appropriately increased according to actual needs. Furthermore, if the number of times the answer given by the respondent is adopted by the interviewer exceeds the preset number threshold, the second preset weight corresponding to the second answer given by the respondent can be further increased according to actual needs.

[0062] It should be pointed out here that since the questioner is more certain of the answer to the query question than the visitor, the degree to which the second preset weight corresponding to the second answer given by the respondent increases when the questioner adopts the answer provided by the respondent is greater than the degree to which the second preset weight corresponding to the second answer given by the respondent increases when the visitor adopts the answer provided by the respondent.

[0063] This implementation method determines each second preset weight in the second key-value pair set based on whether the accuracy of the respondent's historical answers to questions is greater than or equal to a preset accuracy threshold, whether the second answer given by the respondent corresponding to the second preset weight is adopted by the questioner, whether the second answer given by the respondent corresponding to the second preset weight is adopted by the visitor, and the number of times the answer is adopted by the visitor. This method fully considers the degree of recognition of the answer by the respondent, the questioner and the visitor, and effectively improves the accuracy of each second preset weight in the second key-value pair set.

[0064] Step 202: Determine a third key-value pair set based on the first key-value pair set and the second key-value pair set.

[0065] In this embodiment, the execution entity may directly merge the first key-value pair set and the second key-value pair set to obtain a third key-value pair set, or may perform a preset processing operation, such as an update operation, a deletion operation, etc., on the merged key-value pair set obtained by merging the first key-value pair set and the second key-value pair set to obtain a third key-value pair set. This application does not limit this.

[0066] The answer in each key-value pair in the third key-value pair set is the third answer, and the preset weight corresponding to the third answer in each key-value pair is the third preset weight. The third key-value pair set consists of at least one third answer-third preset weight key-value pair.

[0067] Step 203: sort the third answer-third preset weight key-value pairs based on the third preset weights in the third key-value pair set, and push the third answers in the sorted third key-value pair set to the questioner.

[0068] In this embodiment, the execution entity can sort the third answer-third preset weight key-value pairs in the third key-value pair set from large to small, and push the third answers in the sorted third key-value pair set to the questioner.

[0069] In some optional methods, based on each third preset weight in the third key-value pair set, each third answer-third preset weight key-value pair is sorted, and each third answer in the sorted third key-value pair set is pushed to the questioner, including: based on the third preset weight corresponding to each third answer in the third key-value pair set and the verification message received by the manual verification interface, each third answer in the third key-value pair set is sorted, and each third answer in the sorted third key-value pair set is pushed to the questioner.

[0070] In this implementation, the execution entity sorts the third answers in the third key-value pair set in descending order according to the third preset weights corresponding to the third answers, to obtain an initial sorted third key-value pair set. At the same time, the third preset weights corresponding to the third answers in the initial sorted third key-value pair set can be further corrected according to the verification message received by the manual verification interface, and the sorting of the third answers in the initial sorted third key-value pair set can be adjusted according to the third preset weights corresponding to the corrected third answers, to obtain a sorted third key-value pair set, and each third answer in the sorted third key-value pair set can be pushed to the questioner.

[0071] Among them, the verification message can be provided by technical experts or artificial intelligence in fields related to the query question.

[0072] In a specific example of the present implementation, the initial third key-value pair set includes 3 initial third answer-initial third preset weight key-value pairs, namely A1-0.1, A2-0.3, and A3-0.5. The execution entity sorts the third preset weights corresponding to each third answer in the third key-value pair set from large to small to obtain an initial sorted third key-value pair set (A3-0.5, A2-0.5, A1-0.1). Further, according to the verification message received by the manual verification interface, the third preset weights corresponding to each third answer of the initial sorted third key-value pair set are corrected and the sorting is adjusted to obtain a sorted third key-value pair set (A2-0.7, A3-0.5, A1-0.1).

[0073] This implementation method, on the basis of sorting each third answer in the third key-value pair set by the third preset weight corresponding to each third answer in the third key-value pair set, adds verification messages provided by technical experts in the field related to the query question or intelligent recognition robots to correct the weight of each third answer in the third key-value pair set and adjust the sorting, thereby further ensuring the validity and accuracy of the answers pushed to users.

[0074] Continue to see Figure 3 , Figure 3 It is a schematic diagram of an application scenario of the question and answer response method according to this embodiment.

[0075] exist Figure 3 In the application scenario, the execution entity 301 first obtains the query question raised by the questioner from the terminal device 302, and obtains the first key-value pair set (A1-0.1, A2-0.3, A3-0.5) 303 and the second key-value pair set (B1-0.4, B2-0.8, B3-0.7) 304 determined from different channels based on the query question, wherein the three first answer-first preset weight key-value pairs in the first key-value pair set are A1-0.1, A2-0.3, and A3-0.5, respectively, and the three first answer-first preset weight key-value pairs in the first key-value pair set are B1-0.4, B2-0.8, and B3-0.7, respectively. The execution entity merges the first key-value pair set (A1-0.1, A2-0.3, A3-0.5) and the second key-value pair set (B1-0.4, B2-0.8, B3-0.7) to obtain a third key-value pair set (A1-0.1, A2-0.3, A3-0.5, B1-0.4, B2-0.8, B3-0.7) 305, wherein the six third answer-third preset weight key-value pairs in the third key-value pair set are A1-0.1, A2-0.3, A3-0.5, B1-0.4, B2-0.8, B3-0.7, respectively. , A2-0.3, A3-0.5, B1-0.4, B2-0.8, B3-0.7, based on the third preset weights in the third key-value pair set, sort the third answer-third preset weight key-value pairs to obtain the sorted third key-value pair set (B2-0.8, B3-0.7, A3-0.5, B1-0.4, A2-0.3, A1-0.1) 306 and push the third answers in the sorted third key-value pair set to the questioner.

[0076] The question-and-answer response method provided by the embodiments of the present disclosure obtains a first key-value pair set and a second key-value pair set determined from different channels based on the query question raised by the questioner; determines a third key-value pair set based on the first key-value pair set and the second key-value pair set; sorts each third answer-third preset weight key-value pair based on each third preset weight in the third key-value pair set, and pushes each third answer in the sorted third key-value pair set to the questioner, thereby effectively improving the accuracy of the answers pushed to the user and saving the user's time in searching for answers.

[0077] Further references Figure 4 , which shows a process 400 of another embodiment of the question-answer response method. The process 400 of the question-answer response method of this embodiment may include the following steps:

[0078] Step 401: Based on the query question raised by the questioner, a first key-value pair set and a second key-value pair set determined from different channels are obtained.

[0079] In this embodiment, the implementation details and technical effects of step 401 can refer to the description of step 201 and will not be repeated here.

[0080] Step 402: merge the first key-value pair set and the second key-value pair set to obtain an initial third key-value pair set.

[0081] In this embodiment, the execution entity merges the first key-value pair set and the second key-value pair set to obtain an initial third key-value pair set, wherein the initial third key-value pair set includes an initial third answer-initial third preset weight key-value pair.

[0082] Step 403: Calculate the similarity between any two of the initial third answers in the initial third key-value pair set.

[0083] In this embodiment, the execution entity may calculate the semantic similarity between any two initial third answers in the initial third key-value pair set.

[0084] Among them, the method for calculating the semantic similarity between two answers can adopt the similarity calculation method in existing technology or future development technology, for example, DSSM (Deep Structured Models, semantic model based on deep network), LSTM-DSSM (Long-Short-Term Memory Deep Structured Models, deep network semantic model based on long short-term memory), etc., and this application does not limit this.

[0085] Step 404: in response to the existence of two initial third answers having a similarity greater than or equal to a preset similarity threshold, the initial third key-value pair set is updated to obtain a third key-value pair set.

[0086] In this embodiment, the execution entity compares the semantic similarities between the obtained pairwise initial third answers with the preset similarity threshold in turn. If there are two initial third answers whose similarity is greater than or equal to the preset similarity threshold, the initial third key-value pair set is updated, and the updated initial third key-value pair set is used as the third key-value pair set.

[0087] Among them, the execution subject may update the initial third key-value pair set in a variety of ways, for example, increasing the initial third preset weights corresponding to the two initial third answers in the initial third key-value pair set whose similarity is greater than or equal to a preset similarity threshold by a preset value, and the preset value may be determined according to actual needs and specific application scenarios; deleting any one of the two initial third answers whose similarity is greater than or equal to a preset similarity threshold and the corresponding initial third preset weight, etc., and the present application does not limit this.

[0088] Here, it should be pointed out that, in the process of updating the initial third key-value pair set, the execution subject does not process the two initial third answers whose similarity is less than the preset similarity threshold and the corresponding initial third preset weights.

[0089] In some optional embodiments, in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, updating the initial third key-value pair set includes: for the initial third key-value pair set, in response to the existence of two initial third answers whose similarity is greater than or equal to the preset similarity threshold, adding the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain the added weights, and using the added weights as the weights of the two initial third answers whose similarity is greater than or equal to the preset similarity threshold.

[0090] In this implementation, the execution subject calculates the semantic similarity between the two initial third answers in the initial third key-value pair set, and compares the obtained similarity with the preset similarity threshold in turn, and updates the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold. The two initial third answers whose similarity is greater than or equal to the preset similarity threshold and the two initial third answers whose initial third key-value pair set similarity is less than the preset similarity threshold and the corresponding initial third preset weights are not processed.

[0091] In a specific example of the present implementation, the initial third key-value pair set includes 3 initial third answer-initial third preset weight key-value pairs, namely A1-0.1, A2-0.3, and A3-0.5. The semantic similarities between the initial third answers A1 and A2, A2 and A3, and A1 and A3 are calculated respectively. If the semantic similarity between A1 and A2 is greater than or equal to the preset similarity threshold, the weights corresponding to A1 and A2 are added to obtain the added weight of 0.4, and the added weights are used as the weights of A1 and A2 respectively. The final third key-value pair set is (A1-0.4, A2-0.4, A3-0.5).

[0092] This implementation method obtains the added weight by adding the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold, and uses the added weights as the weights of the two initial third answers whose similarity is greater than or equal to the preset similarity threshold, thereby increasing the weights of similar answers, i.e., answers with higher accuracy, so that answers with higher accuracy are ranked higher, thereby further improving the accuracy and effectiveness of the answers pushed to users.

[0093] In some optional embodiments, in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, updating the initial third key-value pair set includes: for the initial third key-value pair set, in response to the existence of two initial third answers whose similarity is greater than or equal to the preset similarity threshold, merging the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain a merged initial third answer; adding the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain an added weight, and using the added weight as the weight of the merged initial third answer.

[0094] In this implementation, the execution entity may merge the entire contents of the two initial third answers whose similarity is greater than or equal to the preset similarity threshold, or may merge partial contents of the two initial third answers whose similarity is greater than or equal to the preset similarity threshold, and this application does not limit this.

[0095] Here, the two initial third answers and the corresponding initial third preset weights whose similarity of the initial third key-value pair set is less than the preset similarity threshold are not processed.

[0096] In a specific example of the present implementation, the initial third key-value pair set includes 3 initial third answer-initial third preset weight key-value pairs, namely A1-0.1, A2-0.3, and A3-0.5. The semantic similarities between the initial third answers A1 and A2, A2 and A3, and A1 and A3 are calculated respectively. If the similarity between A1 and A2 is greater than or equal to the preset similarity threshold, A1 and A2 are merged to obtain A4, and the weights corresponding to A1 and A2 are added to obtain the added weight of 0.4, and the added weight is used as the weight of A4, so the final third key-value pair set is (A4-0.4, A3-0.5).

[0097] This implementation method responds to the existence of two initial third answers with a similarity greater than or equal to a preset similarity threshold, merges the two initial third answers with a similarity greater than or equal to the preset similarity threshold, and obtains a merged initial third answer; adds the initial third preset weights corresponding to the two initial third answers with a similarity greater than or equal to the preset similarity threshold to obtain an added weight, and uses the added weight as the weight of the merged initial third answer, thereby increasing the weights of similar answers, so that answers with higher accuracy are ranked higher, and reducing the number of similar answers, thereby further improving the accuracy and effectiveness of the answers pushed to users, and reducing the time users spend searching for correct answers.

[0098] Step 405: sort the third answer-third preset weight key-value pairs based on the third preset weights in the third key-value pair set, and push the third answers in the sorted third key-value pair set to the questioner.

[0099] In this embodiment, the implementation details and technical effects of step 405 can refer to the description of step 203 and will not be repeated here.

[0100] The above-mentioned embodiment of the present application obtains an initial third key-value pair set by merging the first key-value pair set and the second key-value pair set, calculates the similarity between the two initial third answers in the initial third key-value pair set, and in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, updates the initial third key-value pair set to obtain a third key-value pair set, thereby achieving adjustment of similar third answers, i.e., third answers with higher accuracy and the corresponding third preset weights, and then sorting each third answer-third preset weight key-value pair, and pushing each third answer in the sorted third key-value pair set to the questioner, thereby further improving the effectiveness and accuracy of the answers pushed to the user.

[0101] Further references Figure 5 As an implementation of the methods shown in the above figures, the present application provides an embodiment of a question-answer response device. Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0102] like Figure 5 As shown, the question and answer response device 500 of this embodiment includes: an acquisition module 501, a determination module 502, and a push module 503.

[0103] The acquisition module 501 may be configured to acquire a first key-value pair set and a second key-value pair set determined from different channels based on a query question raised by a questioner.

[0104] The determination module 502 may be configured to determine a third key-value pair set based on the first key-value pair set and the second key-value pair set.

[0105] The push module 503 may be configured to sort the third answer-third preset weight key-value pairs based on the third preset weights in the third key-value pair set, and push the third answers in the sorted third key-value pair set to the questioner.

[0106] In some optional embodiments of the present embodiment, the determination module includes: a merging unit, configured to merge the first key-value pair set and the second key-value pair set to obtain an initial third key-value pair set; a calculating unit, configured to calculate the similarity between each pair of initial third answers in the initial third key-value pair set; and an updating unit, configured to update the initial third key-value pair set in response to the presence of two initial third answers having a similarity greater than or equal to a preset similarity threshold to obtain a third key-value pair set.

[0107] In some optional embodiments of the present embodiment, the updating unit is further configured to: for the initial third key-value pair set, in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, add the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain the added weights, and use the added weights as the weights of the two initial third answers whose similarity is greater than or equal to the preset similarity threshold.

[0108] In some optional modes of this embodiment, the update unit is further configured to: for the initial third key-value pair set, in response to the existence of two initial third answers whose similarity is greater than or equal to a preset similarity threshold, merge the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain a merged initial third answer; add the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold to obtain the added weight, and use the added weight as the weight of the merged initial third answer.

[0109] In some optional embodiments of this embodiment, the push module is further configured to: sort the third answers in the third key-value pair set based on the third preset weight corresponding to each third answer in the third key-value pair set and the verification message received by the manual verification interface, and push the third answers in the sorted third key-value pair set to the questioner.

[0110] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0111] like Figure 6 , is a block diagram of an electronic device according to the question and answer response method of an embodiment of the present application.

[0112] 600 is a block diagram of an electronic device according to the question-answer response method of an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0113] like Figure 6 As shown, the electronic device includes: one or more processors 601, a memory 602, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 601 is taken as an example.

[0114] The memory 602 is a non-transitory computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable the at least one processor to perform the question-answer response method provided in the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to perform the question-answer response method provided in the present application.

[0115] The memory 602 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the question-answer response method in the embodiment of the present application (for example, the attached Figure 5 The processor 601 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 602, that is, the question-answer response method in the above method embodiment is implemented.

[0116] The memory 602 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of the electronic device for question and answer response, etc. In addition, the memory 602 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 602 may optionally include a memory remotely arranged relative to the processor 601, and these remote memories may be connected to the electronic device for question and answer response via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0117] The electronic device of the question-answer response method may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0118] The input device 603 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device for quality monitoring of the live video stream, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator rod, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 604 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0119] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0121] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0122] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0123] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0124] According to the technical solution of the embodiment of the present application, the accuracy of the answers pushed to the users is effectively improved, saving the users' time in searching for answers.

[0125] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0126] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A question-answer response method, It is characterized in that include: Based on the query question raised by the questioner, a first key-value pair set and a second key-value pair set determined from different channels are obtained, wherein the first key-value pair set is composed of at least one first answer-first preset weight key-value pair, and the second key-value pair set is composed of at least one second answer-second preset weight key-value pair; Merging the first key-value pair set and the second key-value pair set to obtain an initial third key-value pair set; Calculate the similarity between the two initial third answers in the initial third key-value pair set; merge two initial third answers whose similarity is greater than or equal to a preset similarity threshold to obtain a merged initial third answer; Adding the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold, and using the added weights as the weights of the combined initial third answers, to obtain a third key-value pair set, wherein the third key-value pair set consists of at least one third answer-third preset weight key-value pair; Based on the third preset weight corresponding to each third answer in the third key-value pair set and the verification message received by the manual verification interface, the third answers in the third key-value pair set are sorted, and the third answers in the sorted third key-value pair set are pushed to the questioner, and the verification message is used to correct the third preset weight corresponding to each third answer, and the corrected third preset weights are different.

2. The method according to claim 1, in, Each first answer in the first key-value pair set is obtained according to at least one answer corresponding to the query question found in the whole network data; Each second answer in the second key-value pair set is obtained according to at least one answer given by the respondent to the query question in the entire network data.

3. The method according to claim 1, in, Each first preset weight in the first key-value pair set is determined based on the professionalism of a source website that provides a first answer corresponding to the first preset weight; Each second preset weight in the second key-value pair set is determined based on the accuracy of the second answer corresponding to the second preset weight given by the respondent in the whole network data.

4. The method according to claim 3, in, The second preset weights in the second key-value pair set are determined based on the accuracy of the second answers corresponding to the second preset weights given by the respondents in the whole network data, including: Each second preset weight in the second key-value pair set is determined based on the following data in the whole network data: Whether the accuracy of the answers given by the respondent in the past is greater than or equal to the preset accuracy threshold; Whether the second answer given by the answerer and corresponding to the second preset weight is adopted by the questioner; Whether the second answer given by the respondent and corresponding to the second preset weight is adopted by the interviewer and the number of times it is adopted by the interviewer.

5. A question-answering response device, It is characterized in that include: an acquisition module, configured to acquire, based on a query question raised by a questioner, a first key-value pair set and a second key-value pair set determined from different channels, wherein the first key-value pair set consists of at least one first answer-first preset weight key-value pair, and the second key-value pair set consists of at least one second answer-second preset weight key-value pair; The determination module includes a merging unit, a calculating unit and an updating unit, wherein the merging unit is configured to merge the first key-value pair set and the second key-value pair set to obtain an initial third key-value pair set, the calculating unit is configured to calculate the similarity between two initial third answers in the initial third key-value pair set, and the updating unit is configured to merge two initial third answers whose similarity is greater than or equal to a preset similarity threshold to obtain a merged initial third answer; Adding the initial third preset weights corresponding to the two initial third answers whose similarity is greater than or equal to the preset similarity threshold, and using the added weights as the weights of the combined initial third answers, to obtain a third key-value pair set, wherein the third key-value pair set consists of at least one third answer-third preset weight key-value pair; The push module is configured to sort the third answers in the third key-value pair set based on the third preset weights corresponding to the third answers in the third key-value pair set and the verification message received by the manual verification interface, and push the third answers in the sorted third key-value pair set to the questioner, wherein the verification message is used to correct the third preset weights corresponding to the third answers, and the corrected third preset weights are different.

6. The device according to claim 5, in, Each first answer in the first key-value pair set is obtained according to at least one answer corresponding to the query question found in the whole network data; Each second answer in the second key-value pair set is obtained according to at least one answer given by the respondent to the query question in the entire network data.

7. The device according to claim 5, in, Each first preset weight in the first key-value pair set is determined based on the professionalism of a source website that provides a first answer corresponding to the first preset weight; Each second preset weight in the second key-value pair set is determined based on the accuracy of the second answer corresponding to the second preset weight given by the respondent in the whole network data.

8. The device according to claim 7, in, The second preset weights in the second key-value pair set are determined based on the accuracy of the second answers corresponding to the second preset weights given by the respondents in the whole network data, including: Each second preset weight in the second key-value pair set is determined based on the following data in the whole network data: Whether the accuracy of the answers given by the respondent in the past is greater than or equal to the preset accuracy threshold; Whether the second answer given by the answerer and corresponding to the second preset weight is adopted by the questioner; Whether the second answer given by the respondent and corresponding to the second preset weight is adopted by the interviewer and the number of times it is adopted by the interviewer.

9. An electronic device, It is characterized in that include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, It is characterized in that The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 4.