Standard determination method, device, equipment and computer readable storage medium

Abstract

The present application discloses a method, apparatus, device and computer-readable storage medium for determining a standard question, wherein the method comprises: obtaining a first set of questions to be analyzed and a preset set of reference questions for a target answer, wherein the similarity between the target answer and the reference answer corresponding to the reference question set is less than a preset threshold; using the first set of questions to be analyzed and the reference question set to determine a set of alternative standard questions corresponding to the target answer; wherein the set of alternative standard questions is used to determine the target standard question corresponding to the user question when the user question is obtained, which can improve the accuracy of the question answer recall result.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and in particular, relates to a standard determination method, device, equipment and computer-readable storage medium. Background Art

[0002] Currently, when determining a standard question for a certain answer, one of the questions corresponding to the same answer is generally directly selected as the standard question. The accuracy of the recall result corresponding to the standard question determined by this method is relatively low. Summary of the invention

[0003] The embodiment of the present application provides an implementation scheme different from the prior art to solve the technical problem of low accuracy of question answer recall results caused by the standard question determination method in the prior art.

[0004] In a first aspect, the present application provides a method for determining a standard question, comprising: obtaining a first set of questions to be analyzed and a preset set of reference questions for a target answer, wherein the similarity between the target answer and the reference answer corresponding to the reference question set is less than a preset threshold; using the first set of questions to be analyzed and the reference question set to determine a set of alternative standard questions corresponding to the target answer; wherein the set of alternative standard questions is used to determine the target standard question corresponding to the user question when the user question is obtained.

[0005] In a second aspect, the present application provides a data processing method, comprising: obtaining a user question input by a user; sending an answer acquisition request to a server device based on the user question, so that the server device determines a set of alternative standard questions corresponding to the user question based on the answer acquisition request, filters out a target standard question corresponding to the user question from the set of alternative standard questions, determines a target answer corresponding to the target standard question, and feeds back the target answer; wherein the set of alternative standard questions is obtained by the server device through obtaining a first set of questions to be analyzed and a preset reference question set for the target answer, wherein the similarity between the target answer and the reference answer corresponding to the reference question set is less than a preset threshold; determined using the first set of questions to be analyzed and the reference question set; receiving the target answer fed back by the server device; and displaying the target answer.

[0006] In a third aspect, the present application provides a standard question determination device, comprising: an acquisition module, used to acquire a first set of questions to be analyzed and a preset reference question set for a target answer, wherein the similarity between the target answer and the reference answer corresponding to the reference question set is less than a preset threshold; a determination module, used to determine a set of alternative standard questions corresponding to the target answer using the first set of questions to be analyzed and the reference question set; wherein the set of alternative standard questions is used to determine the target standard question corresponding to the user question when the user question is acquired.

[0007] In a fourth aspect, the present application provides an electronic device, including:

[0008] Processor; and

[0009] A memory, configured to store executable instructions of the processor;

[0010] The processor is configured to execute the method described in any one of the first aspect, the second aspect, each possible implementation of the first aspect, and each possible implementation of the second aspect by executing the executable instructions.

[0011] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method described in the first aspect, the second aspect, each possible implementation method of the first aspect, and any one of the possible implementation methods of the second aspect is implemented.

[0012] In a sixth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the first aspect, the second aspect, each possible implementation method of the first aspect, and any method described in each possible implementation method of the second aspect.

[0013] The above-mentioned scheme provided by the present application obtains a first set of questions to be analyzed and a preset set of reference questions for a target answer, wherein the similarity between the target answer and the reference answer corresponding to the reference question set is less than a preset threshold; and uses the first set of questions to be analyzed and the reference question set to determine a set of alternative standard questions corresponding to the target answer; wherein the set of alternative standard questions is used to determine the target standard questions corresponding to the user questions when the user questions are obtained, which not only takes into account the representativeness of the standard questions for similar questions, but also introduces a reference question set for reducing the probability of ambiguity of the selected standard questions, thereby improving the accuracy of the question answer recall results. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0015] Figure 1 A schematic diagram of the structure of a standard determination system provided in an embodiment of the present application;

[0016] Figure 2A schematic diagram of a flow chart of a standard determination method provided in an embodiment of the present application;

[0017] Figure 3a A schematic diagram of a flow chart of a standard determination method provided in an embodiment of the present application;

[0018] Figure 3b A flowchart of a data processing method provided in one embodiment of the present application;

[0019] Figure 4 A schematic diagram of the structure of a standard determination device provided in an embodiment of the present application;

[0020] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, but cannot be understood as limiting the present application.

[0022] The terms "first" and "second" etc. in the specification, claims and drawings of the embodiments of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0023] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0024] Figure 1 A schematic diagram of a standard determination system provided by an exemplary embodiment of the present application, the structure includes: a client device 11 and a server device 12, wherein: the client device 11 is used to:

[0025] Obtaining a user question input by a user; sending an answer acquisition request to a server device based on the user question, receiving a target answer fed back by the server device according to the answer acquisition request; and displaying the target answer;

[0026] The server device 12 is used to determine, after receiving an answer acquisition request, a set of alternative standard questions corresponding to the user question according to the user question carried in the answer acquisition request, and determine a target standard question corresponding to the user question from the set of alternative standard questions, and determine the answer corresponding to the target standard question according to a preset corresponding relationship, and feed back the answer as the target answer to the client device 11, wherein the set of alternative standard questions can be obtained by obtaining a first set of questions to be analyzed and a preset reference question set for the target answer, wherein the similarity between the target answer and the reference answer corresponding to the reference question set is less than a preset threshold; and the result is determined by using the first set of questions to be analyzed and the reference question set.

[0027] Specifically, the server device 12 may determine the alternative standard question set according to the user question based on a preset correspondence, or may pre-classify the user question and determine the alternative standard question set corresponding to the user question based on the classification result and the correspondence between the preset question type and the standard question set.

[0028] The execution principles and interaction processes of the various components in the system embodiment, such as the client device 11 and the server device 12, can be found in the description of the following method embodiments.

[0029] Figure 2 A flowchart of a standard determination method provided by an exemplary embodiment of the present application is provided. The execution subject of the method may be a server device, and the method at least includes the following steps:

[0030] S201, obtaining a first set of questions to be analyzed and a preset set of reference questions for a target answer, wherein the similarity between the target answer and the reference answers corresponding to the reference question set is less than a preset threshold;

[0031] S202, using the first set of questions to be analyzed and the reference set of questions to determine a set of candidate standard questions corresponding to the target answer;

[0032] The candidate standard question set is used to determine the target standard question corresponding to the user question when the user question is obtained.

[0033] Specifically, the target answer may be an answer selected or set by a relevant person, and the first set of questions to be analyzed may be a set of questions that can use the target answer as the answer to the question. For example, when the supermarket in Park A is Supermarket B, the first set of questions to be analyzed corresponding to the target answer Supermarket B may include the following questions: What is the supermarket in Park A? What is the name of the supermarket in Park A? What is the supermarket in Park A?

[0034] Furthermore, the aforementioned reference question set is a collection of questions whose answers can be reference answers, and the similarity between the target answer and the reference answer corresponding to the reference question set is less than a preset threshold. The number of reference answers can be one or more, but the similarity between the target answer and each reference answer cannot be less than a preset threshold. The aforementioned preset threshold can be set by relevant personnel.

[0035] Furthermore, in the aforementioned step S202, determining the candidate standard question set corresponding to the target answer by using the first set of questions to be analyzed and the reference question set may specifically include:

[0036] S2021, determining a first similarity result set of a plurality of first questions in the first set of questions to be analyzed with respect to the first set of questions to be analyzed;

[0037] S2022, determining a second similarity result set of the plurality of first questions with respect to the reference question set;

[0038] S2023: Determine the candidate standard question set by using the first similarity result set and the second similarity result set.

[0039] Specifically, the aforementioned multiple first questions may be at least part of the questions in the first set of questions to be analyzed, and the multiple first questions correspond to the multiple first similarity results in the first similarity result set one by one. Determining the first similarity result set of the multiple first questions in the first set of questions to be analyzed for the first set of questions to be analyzed includes:

[0040] respectively determining a first similarity result of each of the plurality of first questions with respect to the first set of questions to be analyzed, to obtain a plurality of first similarity results;

[0041] Determining the first similarity result set according to the multiple first similarity results; determining the first similarity result set according to the multiple first similarity results includes: taking a set consisting of the multiple first similarity results as the first similarity result set.

[0042] In some optional embodiments of the present application, for each of the aforementioned multiple first questions, determining a first similarity result of the first question with respect to the first set of questions to be analyzed may specifically include:

[0043] S01, obtaining a plurality of remaining questions of the first question for the first set of questions to be analyzed;

[0044] S02, calculating a plurality of first similarities between the first question and the plurality of remaining questions;

[0045] S03, determining a first number of first similarities that meet a first preset condition among the plurality of first similarities;

[0046] S04. Determine the first similarity result using the first number.

[0047] Specifically, the first question for the plurality of remaining questions of the first set of questions to be analyzed may be a plurality of other first questions in the first set of questions to be analyzed except the first question;

[0048] In some optional embodiments of the present application, the number of remaining questions may also be 1.

[0049] Furthermore, the aforementioned calculation of multiple first similarities between the first question and the multiple remaining questions includes: calculating the similarity between the first question and each of the remaining questions in turn to obtain multiple first similarities corresponding to the multiple remaining questions, and the multiple remaining questions correspond to the multiple first similarities one-to-one.

[0050] Furthermore, the first preset condition may be that the similarity is greater than a first threshold, and the first similarity may be a specific similarity value.

[0051] Further, using the first number to determine the first similarity result may include: using the first number as the first similarity result.

[0052] After performing the analysis of the aforementioned steps S01 to S04 on each of the aforementioned multiple first questions, a first similarity result set corresponding to the multiple first questions can be obtained.

[0053] Furthermore, in the aforementioned step S2022, determining a second similarity result set of the plurality of first questions with respect to the reference question set includes:

[0054] respectively determining a second similarity result of each of the plurality of first questions with respect to the reference question set, to obtain a plurality of second similarity results;

[0055] Determining the second similarity result set according to the multiple second similarity results; determining the second similarity result set according to the multiple second similarity results includes: taking a set consisting of the multiple second similarity results as the second similarity result set.

[0056] In some optional embodiments of the present application, for each first question among the plurality of first questions, determining a second similarity result of the first question with respect to the reference question set includes:

[0057] S001, obtaining a plurality of reference questions of the first question with respect to the reference question set;

[0058] S002, calculating a plurality of second similarities between the first question and the plurality of reference questions;

[0059] S003, determining a second number of second similarities that meet a second preset condition among the plurality of second similarities;

[0060] S004. Determine the second similarity result using the second number.

[0061] Specifically, the first question may be directed to the multiple reference questions of the reference question set, which may be all the questions included in the reference question set;

[0062] The aforementioned calculation of multiple second similarities between the first question and multiple reference questions includes: calculating the similarity between the first question and each reference question in turn to obtain multiple second similarities corresponding to the multiple reference questions, and the multiple reference questions correspond to the multiple second similarities one by one.

[0063] Furthermore, the second preset condition may be that the similarity is greater than a second threshold, and the second similarity may be a specific similarity value.

[0064] Further, using the second number to determine the second similarity result may include: using the second number as the second similarity result.

[0065] After performing the analysis of the aforementioned steps S001 to S004 on each of the aforementioned multiple first questions, a second similarity result set corresponding to the multiple first questions can be obtained.

[0066] Furthermore, in the aforementioned step S2023, determining the candidate standard question set using the first similarity result set and the second similarity result set includes:

[0067] S0231. Obtaining preset evaluation rules;

[0068] S0232, determining a first standard question by using the evaluation rule, the first similarity result set, and the second similarity result set;

[0069] S0233. Determine the set of candidate standard questions based on the first standard question.

[0070] Specifically, the aforementioned evaluation rule may be a preset determination formula, and determining the first standard question by using the evaluation rule, the first similarity result set, and the second similarity result set includes:

[0071] Determine a plurality of result pairs based on the first similarity result set and the second similarity result set;

[0072] Determine a plurality of first evaluation results using the plurality of result pairs and the evaluation rules;

[0073] The first standard question is determined according to the plurality of first evaluation results.

[0074] Optionally, the plurality of result pairs correspond one-to-one to the plurality of first evaluation results, and determining the first evaluation result corresponding to each result pair may include: determining the first evaluation result corresponding to the result pair according to the result pair and the evaluation rule. Specifically, determining the first evaluation result corresponding to the result pair according to the result pair and the evaluation rule may include:

[0075] Determine a first similarity result and a second similarity result in the result pair;

[0076] Determining a first evaluation parameter and a second evaluation parameter corresponding to the evaluation rule;

[0077] The first evaluation result is determined using the first similarity result, the first evaluation parameter, the second similarity result, and the second evaluation parameter.

[0078] Determining the first evaluation result by using the first similarity result, the first evaluation parameter, the second similarity result, and the second evaluation parameter includes:

[0079] Determining a first product of the first similarity result and the first evaluation parameter;

[0080] determining a second product of the second similarity result and the second evaluation parameter;

[0081] The first evaluation result is determined according to a difference between the first product and the second product.

[0082] Specifically, determining the first evaluation result using the first similarity result, the first evaluation parameter, the second similarity result, and the second evaluation parameter may be achieved in the following manner:

[0083] Score=α*N-β*M

[0084] Among them, N is the first similarity result, M is the second similarity result, α is the first evaluation parameter, β is the second evaluation parameter, the first evaluation parameter and the second evaluation parameter can be set by relevant personnel, Score is the first evaluation result, and the aforementioned first evaluation parameter and the second evaluation parameter can also be adjusted according to needs, and this application does not limit this.

[0085] Further, in some optional embodiments of the present application, determining the first standard question according to the multiple first evaluation results may include:

[0086] Sorting the plurality of first evaluation results according to a preset sorting rule to obtain a sorting result;

[0087] The first standard question is determined based on the sorting result.

[0088] Among them, the preset sorting rule can be to sort the result values ​​of multiple first evaluation results from high to low to obtain the sorting result. Accordingly, the first question corresponding to the first evaluation result with the highest sorting can be used as the first standard question.

[0089] Further, determining the set of candidate standard questions based on the first standard question includes:

[0090] Obtaining a first similar question set corresponding to the first standard question in the first question set to be analyzed;

[0091] The first similar problem set is a set of remaining problems in the first problem set to be analyzed, whose corresponding first similarity meets the first preset condition;

[0092] If the first similar question set includes all questions in the first question set to be analyzed except the first standard question, determining the candidate standard question set based on the first standard question includes: taking the first standard question as the only element of the candidate standard question set to obtain the candidate standard question set;

[0093] If the first similar question set only includes some of the first questions in the first question set to be analyzed except the first standard question, the above method further includes:

[0094] S281, determining a second set of questions to be analyzed corresponding to the first standard question based on the first standard question and the first set of questions to be analyzed, wherein the second set of questions to be analyzed is included in the first set of questions to be analyzed;

[0095] S282, obtaining an evaluation result set corresponding to the second set of problems to be analyzed;

[0096] S283, using the evaluation result set to determine a second standard question corresponding to the target answer;

[0097] S284: Determine the candidate standard question set based on the second standard question. Specifically, determining the candidate standard question set based on the second standard question may specifically include: determining the candidate standard question set based on the first standard question and the second standard question.

[0098] Specifically, in the aforementioned step S281, the second set of questions to be analyzed is a set of other first questions in the first set of questions to be analyzed except the first similar question set and the first standard question.

[0099] The evaluation result set corresponding to the second set of problems to be analyzed is a set of second evaluation results corresponding to the second problem in the second set of problems to be analyzed, wherein the second problem refers to the first problem in the second set of problems to be analyzed, and the second evaluation result refers to the first evaluation result corresponding to the first problem in the second set of problems to be analyzed.

[0100] Further, in S283, the evaluation result set is used to determine the second standard question corresponding to the target answer, which is similar to the aforementioned method of determining the first standard question based on the multiple first evaluation results, that is, the evaluation result set is sorted according to a preset sorting rule to obtain a sorting result; the second standard question is determined based on the sorting result. The specific details can be found in the aforementioned content and will not be repeated here.

[0101] Further, determining a second set of questions to be analyzed corresponding to the first standard question based on the first standard question and the first set of questions to be analyzed includes:

[0102] Obtain a first similar question set corresponding to the first standard question in the first set of questions to be analyzed;

[0103] The first similar question set is deleted from the plurality of first question sets to be analyzed to obtain the second question set to be analyzed.

[0104] In some optional embodiments of the present application, the aforementioned determination of the candidate standard question set based on the first standard question and the second standard question may include:

[0105] Determine a third set of questions to be analyzed corresponding to the second standard question based on the second standard question and the second set of questions to be analyzed;

[0106] If the third set of questions to be analyzed is empty, the set of the first standard question and the second standard question is used as the set of candidate standard questions.

[0107] Similarly, determining a third set of questions to be analyzed corresponding to the second standard question based on the second standard question and the second set of questions to be analyzed includes:

[0108] Obtain a second similar question set corresponding to the second standard question in the second question set to be analyzed;

[0109] The second similar question set is deleted from the plurality of second question sets to be analyzed to obtain the third question set to be analyzed.

[0110] The process is analogous to that above until the last remaining set of questions to be analyzed in the first set of questions to be analyzed is empty, thereby obtaining a set of alternative standard questions.

[0111] In some optional embodiments of the present application, when the first standard question set includes multiple elements, the method further includes:

[0112] S21, obtaining the user question;

[0113] S22: Based on the user question, select the target standard question from the set of candidate standard questions.

[0114] Specifically, the user question may be carried in the answer acquisition request sent by the client device. In the aforementioned step S22, based on the user question, filtering out the target standard question from the alternative standard question set may include: calculating the similarity between the user question and each alternative standard question in the alternative standard question set to obtain multiple alternative similarities; and taking the alternative standard question corresponding to the alternative similarity with the highest similarity value in the alternative standard question set as the target standard question.

[0115] Furthermore, after determining the target standard question, the above method also includes: determining an answer corresponding to the target standard question according to a preset corresponding relationship; and using the answer corresponding to the target standard question as the target answer corresponding to the user question.

[0116] It should be noted that the aforementioned method can simultaneously analyze the alternative standard question sets corresponding to multiple target answers. During actual execution, the alternative standard question sets for each target answer can be determined in sequence according to the set target answer set. This application does not impose any limitation on this.

[0117] In addition, the aforementioned method may also be applicable to client devices, which is not limited in this application.

[0118] The standard question determination scheme provided in the present application is achieved by obtaining a first set of questions to be analyzed and a preset set of reference questions for a target answer, wherein the similarity between the target answer and the reference answer corresponding to the reference question set is less than a preset threshold; and using the first set of questions to be analyzed and the reference question set to determine a set of alternative standard questions corresponding to the target answer; wherein the set of alternative standard questions is used to determine the target standard questions corresponding to the user questions when the user questions are obtained. The scheme not only takes into account the representativeness of the standard questions for similar questions, but also introduces a reference question set for reducing the probability of ambiguity of the selected standard questions, thereby improving the accuracy of the question answer recall results.

[0119] Figure 3a A flowchart of a standard determination method provided by an exemplary embodiment of the present application is provided. The execution subject of the method may be a server device, and the method at least includes the following steps:

[0120] Questions that have the same answer are recorded as similar questions;

[0121] Get the number of positive examples: Calculate the similarity of similar questions two by two;

[0122] Get the number of negative examples: Count each pair of non-similar questions;

[0123] Calculate the question score: Score = α*N-β*M;

[0124] Standard question selection;

[0125] Determine whether there are other standard questions with the same answers that need to be determined. If so, return to step "record the questions with the same answers as the same type of questions" to continue execution. If not, end. When calculating the similarity between two pairs, performance optimization can be achieved by means of initial screening, recall, filtering, etc.

[0126] Further, see Figure 3b As shown, the aforementioned “standard selection” may specifically include the following steps:

[0127] Sort the questions and store them in a queue;

[0128] If the first standard question selected is the first question in the queue, then the first question in the queue and its similar questions are deleted;

[0129] Check whether the queue is empty. If so, end the process. If not, return to step "sort the questions and store them in the queue" to continue.

[0130] The specific implementation principle of this embodiment can be found in the above content and will not be repeated here.

[0131] This solution is a solution for automatically determining the standard questions corresponding to user questions based on the determined set of alternative standard questions. Before the set of alternative standard questions is determined, the first data set to be analyzed and the reference data set can be manually labeled, and similarity calculation services and other recall service interfaces can be used. The solution of this application can effectively improve the accuracy of the recall results for user questions.

[0132] An exemplary embodiment of the present application further provides a data processing method, which may include at least the following steps:

[0133] S401, obtaining a user question input by a user;

[0134] S402, based on the user question, sending an answer acquisition request to the server device, so that the server device determines a set of candidate standard questions corresponding to the user question based on the answer acquisition request, screens out a target standard question corresponding to the user question from the set of candidate standard questions, determines a target answer corresponding to the target standard question, and feeds back the target answer; wherein the set of candidate standard questions is obtained by the server device through obtaining a first set of questions to be analyzed and a preset reference set of questions for the target answer, wherein the similarity between the target answer and the reference answer corresponding to the reference set of questions is less than a preset threshold; determined using the first set of questions to be analyzed and the reference set of questions;

[0135] S403, receiving the target answer fed back by the server device;

[0136] S404: Display the target answer.

[0137] The specific implementation details corresponding to this embodiment can be found in the above content and will not be repeated here.

[0138] Figure 4 A schematic diagram of a standard determination device provided by an exemplary embodiment of the present application;

[0139] The device includes: an acquisition module 41 and a determination module 42; wherein:

[0140] An acquisition module 41 is used to acquire a first set of questions to be analyzed and a preset set of reference questions for a target answer, wherein the similarity between the target answer and the reference answers corresponding to the reference question set is less than a preset threshold;

[0141] A determination module 42, configured to determine a set of candidate standard questions corresponding to the target answer by using the first set of questions to be analyzed and the reference set of questions;

[0142] The candidate standard question set is used to determine the target standard question corresponding to the user question when the user question is obtained.

[0143] Optionally, when the determination module 42 is used to determine the candidate standard question set corresponding to the target answer by using the first set of questions to be analyzed and the reference question set, it is specifically used to:

[0144] Determine a first similarity result set of a plurality of first questions in the first set of questions to be analyzed with respect to the first set of questions to be analyzed;

[0145] Determine a second similarity result set of the plurality of first questions with respect to the reference question set;

[0146] The candidate standard question set is determined using the first similarity result set and the second similarity result set.

[0147] Optionally, when the determination module 42 is used to determine a first similarity result set of a plurality of first questions in the first set of questions to be analyzed with respect to the first set of questions to be analyzed, it is specifically used to:

[0148] respectively determining a first similarity result of each of the plurality of first questions with respect to the first set of questions to be analyzed, to obtain a plurality of first similarity results;

[0149] The first similarity result set is determined according to the multiple first similarity results.

[0150] Optionally, when the determination module 42 is used to determine the first similarity result of the first question with respect to the first set of questions to be analyzed, it is specifically used to:

[0151] Obtaining a plurality of remaining questions of the first question for the first set of questions to be analyzed;

[0152] Calculating a plurality of first similarities between the first question and the plurality of remaining questions;

[0153] Determine a first number of first similarities that meet a first preset condition among the plurality of first similarities;

[0154] The first similarity result is determined using the first number.

[0155] Optionally, when the determination module 42 is used to determine the second similarity result set of the plurality of first questions with respect to the reference question set, it is specifically used to:

[0156] respectively determining a second similarity result of each of the plurality of first questions with respect to the reference question set, to obtain a plurality of second similarity results;

[0157] The second similarity result set is determined according to the plurality of second similarity results.

[0158] Optionally, when the determination module 42 is used to determine the second similarity result of the first question with respect to the reference question set, it is specifically used to:

[0159] Obtaining a plurality of reference questions of the first question with respect to the reference question set;

[0160] calculating a plurality of second similarities between the first question and the plurality of reference questions;

[0161] Determining a second number of second similarities that meet a second preset condition among the plurality of second similarities;

[0162] The second similarity result is determined using the second number.

[0163] Optionally, when the determination module 42 is used to determine the candidate standard set using the first similarity result set and the second similarity result set, it is specifically used to:

[0164] Get the preset evaluation rules;

[0165] Determine a first standard question using the evaluation rule, the first similarity result set, and the second similarity result set;

[0166] The set of candidate standard questions is determined based on the first standard question.

[0167] Optionally, when the determination module 42 is used to determine the first standard question by using the evaluation rule, the first similarity result set, and the second similarity result set, it is specifically used to:

[0168] Determine a plurality of result pairs based on the first similarity result set and the second similarity result set;

[0169] Determine a plurality of first evaluation results using the plurality of result pairs and the evaluation rules;

[0170] The first standard question is determined according to the plurality of first evaluation results.

[0171] Optionally, when the determination module 42 is used to determine the first standard according to the multiple first evaluation results, it is specifically used to:

[0172] Sorting the plurality of first evaluation results according to a preset sorting rule to obtain a sorting result;

[0173] The first standard question is determined based on the sorting result.

[0174] Optionally, the above device is also used for:

[0175] Obtain the user question;

[0176] Based on the user question, the target standard question is selected from the set of candidate standard questions.

[0177] Optionally, when the above device is used to determine the candidate standard question set based on the first standard question, it is specifically used to:

[0178] Obtaining a first similar question set corresponding to the first standard question in the first question set to be analyzed;

[0179] If the first similar question set only includes some of the first questions in the first set of questions to be analyzed except the first standard question, then

[0180] Determining a second set of questions to be analyzed corresponding to the first standard question based on the first standard question and the first set of questions to be analyzed, wherein the second set of questions to be analyzed is included in the first set of questions to be analyzed;

[0181] Obtaining an evaluation result set corresponding to the second set of questions to be analyzed;

[0182] Determine a second standard question corresponding to the target answer using the evaluation result set;

[0183] The set of candidate standard questions is determined based on the second standard question.

[0184] Optionally, when the apparatus is used to determine the second set of questions to be analyzed corresponding to the first standard question based on the first standard question and the first set of questions to be analyzed, it is specifically used to:

[0185] Obtain a first similar question set corresponding to the first standard question in the first set of questions to be analyzed;

[0186] The first similar question set is deleted from the plurality of first question sets to be analyzed to obtain the second question set to be analyzed.

[0187] It should be understood that the device embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, no further description is given here. Specifically, the device may perform the above method embodiment, and the above and other operations and / or functions of each module in the device are the corresponding processes in each method in the above method embodiment, respectively, and no further description is given here for the sake of brevity.

[0188] The above describes the device of the embodiment of the present application from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software form instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or a combination of hardware and software modules in the decoding processor to perform. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory, and completes the steps in the above method embodiment in conjunction with its hardware.

[0189] Figure 5 is a schematic block diagram of an electronic device provided in an embodiment of the present application, and the electronic device may include:

[0190] The memory 501 and the processor 502, the memory 501 is used to store the computer program and transmit the program code to the processor 502. In other words, the processor 502 can call and run the computer program from the memory 501 to implement the method in the embodiment of the present application.

[0191] For example, the processor 502 may be used to execute the above method embodiment according to the instructions in the computer program. In some embodiments of the present application, the processor 502 may include but is not limited to:

[0192] General-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.

[0193] In some embodiments of the present application, the memory 501 includes but is not limited to:

[0194] Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0195] In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 501 and executed by the processor 502 to complete the method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0196] like Figure 5 As shown, the electronic device may also include:

[0197] The transceiver 503 may be connected to the processor 502 or the memory 501 .

[0198] The processor 502 may control the transceiver 503 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices. The transceiver 503 may include a transmitter and a receiver. The transceiver 503 may further include an antenna, and the number of antennas may be one or more.

[0199] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0200] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a computer, the computer can perform the method of the above method embodiment. In other words, the present application embodiment also provides a computer program product containing instructions, and when the instructions are executed by a computer, the computer can perform the method of the above method embodiment.

[0201] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a solid state drive (solid state disk, SSD)), etc.

[0202] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0203] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the module is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0204] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. For example, each functional module in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0205] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining a standard, characterized in that: include: Obtaining a first set of questions to be analyzed and a preset set of reference questions for a target answer, wherein a similarity between the target answer and the reference answers corresponding to the reference question set is less than a preset threshold; Determine a first similarity result set of a plurality of first questions in the first set of questions to be analyzed with respect to the first set of questions to be analyzed; determine a second similarity result set of the plurality of first questions with respect to the reference set of questions; obtain a preset evaluation rule; Determine a plurality of result pairs based on the first similarity result set and the second similarity result set; For each result pair in the plurality of result pairs, determining a first similarity result and a second similarity result in the result pair, and determining a first evaluation parameter and a second evaluation parameter corresponding to the evaluation rule; Determine a first product of the first similarity result and the first evaluation parameter; determine a second product of the second similarity result and the second evaluation parameter; determining the first evaluation result according to the difference between the first product and the second product, thereby obtaining a plurality of first evaluation results; Sorting the result values ​​of the plurality of first evaluation results from high to low to obtain a sorting result, and taking the first question corresponding to the first evaluation result ranked highest in the sorting result as the first standard question; Obtain a first similar question set corresponding to the first standard question in the first set of questions to be analyzed, wherein the first similar question set is a set of remaining questions in the first set of questions to be analyzed whose corresponding first similarity meets a first preset condition; If the first similar question set includes all questions in the first set of questions to be analyzed except the first standard question, the first standard question is used as the only element of a candidate standard question set to obtain the candidate standard question set; If the first similar question set only includes some of the first questions in the first question set to be analyzed except the first standard question, then determining a second question set to be analyzed corresponding to the first standard question based on the first standard question and the first question set to be analyzed, wherein the second question set to be analyzed is a set of other first questions in the first question set to be analyzed except the first similar question set and the first standard question; obtaining an evaluation result set corresponding to the second question set to be analyzed; and determining a second standard question corresponding to the target answer using the evaluation result set; Obtain a second similar question set corresponding to the second standard question in the second set of questions to be analyzed; delete the second similar question set from the second set of questions to be analyzed to obtain a third set of questions to be analyzed; If the third set of questions to be analyzed is empty, the set of the first standard question and the second standard question is used as the candidate standard question set, wherein the candidate standard question set is used to determine the target standard question corresponding to the user question when the user question is obtained.

2. The method according to claim 1, characterized in that Determining a first similarity result set of a plurality of first questions in the first set of questions to be analyzed for the first set of questions to be analyzed includes: respectively determining a first similarity result of each of the plurality of first questions with respect to the first set of questions to be analyzed, to obtain a plurality of first similarity results; The first similarity result set is determined according to the multiple first similarity results.

3. The method according to claim 1, characterized in that Determining a second similarity result set of the plurality of first questions with respect to the reference question set includes: respectively determining a second similarity result of each of the plurality of first questions with respect to the reference question set, to obtain a plurality of second similarity results; The second similarity result set is determined according to the plurality of second similarity results.

4. The method according to claim 1, characterized in that The method further comprises: Obtain the user question; Based on the user question, the target standard question is selected from the set of candidate standard questions.

5. A data processing method, characterized in that: include: Get user questions entered by the user; Based on the user question, an answer acquisition request is sent to the server device, so that the server device determines a set of candidate standard questions corresponding to the user question based on the answer acquisition request, screens out a target standard question corresponding to the user question from the set of candidate standard questions, determines a target answer corresponding to the target standard question, and feeds back the target answer; wherein the set of candidate standard questions is determined by the server device, and the server device obtains a first set of questions to be analyzed for the target answer and a preset set of reference questions, wherein the similarity between the target answer and the reference answer corresponding to the reference question set is less than a preset threshold; determines that a plurality of first questions in the first set of questions to be analyzed are related to the first set of questions to be analyzed similarity result set; determine a second similarity result set of the multiple first questions for the reference question set; obtain a preset evaluation rule; determine multiple result pairs based on the first similarity result set and the second similarity result set; for each result pair in the multiple result pairs, determine the first similarity result and the second similarity result in the result pair, and determine the first evaluation parameter and the second evaluation parameter corresponding to the evaluation rule; determine the first product of the first similarity result and the first evaluation parameter; determine the second product of the second similarity result and the second evaluation parameter; determine the first evaluation result according to the difference between the first product and the second product, and then obtain multiple first evaluation results; sort the result values ​​of the multiple first evaluation results from high to low to obtain sorting results, taking the first question corresponding to the first evaluation result ranked highest in the sorting results as the first standard question; obtaining the first similar question set corresponding to the first standard question in the first set of questions to be analyzed, wherein the first similar question set is a set of remaining questions in the first set of questions to be analyzed whose corresponding first similarity meets the first preset condition; if the first similar question set includes all the questions in the first set of questions to be analyzed except the first standard question, taking the first standard question as the only element of the candidate standard question set to obtain the candidate standard question set; if the first similar question set only includes some of the first questions in the first set of questions to be analyzed except the first standard question, then based on the first standard question Determine a second set of questions to be analyzed corresponding to the first standard question from the first set of questions to be analyzed, wherein the second set of questions to be analyzed is a set of first questions in the first set of questions to be analyzed except the first set of similar questions and the first standard question; obtain an evaluation result set corresponding to the second set of questions to be analyzed; determine a second standard question corresponding to the target answer using the evaluation result set; obtain a second set of similar questions corresponding to the second standard question in the second set of questions to be analyzed; delete the second set of similar questions from the second set of questions to be analyzed to obtain a third set of questions to be analyzed; if the third set of questions to be analyzed is empty, use the set of the first standard question and the second standard question as the candidate set of standard questions; Receiving the target answer fed back by the server device; The target answer is displayed.

6. A standard determination device, characterized in that: include: An acquisition module, configured to acquire a first set of questions to be analyzed and a preset set of reference questions for a target answer, wherein a similarity between the target answer and the reference answers corresponding to the reference question set is less than a preset threshold; A determination module is provided to determine a first similarity result set of a plurality of first questions in the first set of questions to be analyzed with respect to the first set of questions to be analyzed; determine a second similarity result set of the plurality of first questions with respect to the reference set of questions; and obtain a preset evaluation rule; Determine a plurality of result pairs based on the first similarity result set and the second similarity result set; For each result pair in the plurality of result pairs, determining a first similarity result and a second similarity result in the result pair, and determining a first evaluation parameter and a second evaluation parameter corresponding to the evaluation rule; Determine a first product of the first similarity result and the first evaluation parameter; determine a second product of the second similarity result and the second evaluation parameter; determining the first evaluation result according to the difference between the first product and the second product, thereby obtaining a plurality of first evaluation results; Sorting the result values ​​of the plurality of first evaluation results from high to low to obtain a sorting result, and taking the first question corresponding to the first evaluation result ranked highest in the sorting result as the first standard question; Obtain a first similar question set corresponding to the first standard question in the first set of questions to be analyzed, wherein the first similar question set is a set of remaining questions in the first set of questions to be analyzed whose corresponding first similarity meets a first preset condition; If the first similar question set includes all questions in the first set of questions to be analyzed except the first standard question, the first standard question is used as the only element of a candidate standard question set to obtain the candidate standard question set; If the first similar question set only includes some of the first questions in the first question set to be analyzed except the first standard question, then determining a second question set to be analyzed corresponding to the first standard question based on the first standard question and the first question set to be analyzed, wherein the second question set to be analyzed is a set of other first questions in the first question set to be analyzed except the first similar question set and the first standard question; obtaining an evaluation result set corresponding to the second question set to be analyzed; and determining a second standard question corresponding to the target answer using the evaluation result set; Obtain a second similar question set corresponding to the second standard question in the second set of questions to be analyzed; delete the second similar question set from the second set of questions to be analyzed to obtain a third set of questions to be analyzed; If the third set of questions to be analyzed is empty, the set of the first standard question and the second standard question is used as the candidate standard question set, wherein the candidate standard question set is used to determine the target standard question corresponding to the user question when the user question is obtained.

7. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images