Interaction method, electronic equipment and storage medium

Abstract

The invention discloses an interaction method, electronic equipment and a storage medium, and relates to the technical field of interaction, and the interaction method comprises the steps that a challenge target and an interaction target are determined according to a target interaction scene currently selected by a user; generating a target interaction problem according to the interaction target, and receiving response information of the target interaction problem; when detecting that the response information does not meet the challenge target, generating an interaction problem of the response information according to the response information and the interaction target; or, when it is detected that the response information meets the challenge target, the interaction result of the target interaction scene is output. The accuracy of chat robot interaction problems and user response information is improved, and the teaching effect is improved.

Description

Technical Field

[0001] The present application relates to the field of interactive technology, and in particular to an interactive method, an electronic device and a storage medium. Background Art

[0002] A chatbot is a computer program that communicates through dialogue or text. A chatbot can simulate human dialogue and can be used for practical purposes, such as foreign language dialogue teaching. The working principle of a chatbot is as follows: When a question is thrown to a chatbot, the chatbot uses an algorithm to find the most appropriate answer from the database and respond. At present, by mining the text description vector of the consultation text to be analyzed, the chatbot's question-answering strategy is upgraded and optimized using the text description vector, such as adjusting or modifying the answer text, so that the chatbot can be continuously improved and optimized, and the chatbot's intelligence level can be improved. In this way, the rigid question-answering processing mechanism of the chatbot in traditional technology can be improved. However, due to the limited scene recognition ability of the chatbot, there is a problem that the interaction problem for the same question in different dialogue scenarios is the same, resulting in low accuracy of the answer text, which affects the teaching effect. Summary of the invention

[0003] The main purpose of this application is to provide an interaction method, an electronic device and a storage medium, aiming to improve the accuracy of chat robot interaction questions and user response information and improve teaching effects.

[0004] To achieve the above objectives, the present application proposes an interaction method, which includes:

[0005] Determine the challenge target and interaction target based on the target interaction scenario currently selected by the user;

[0006] generating a target interaction question according to the interaction target, and receiving response information of the target interaction question;

[0007] detecting that the response information does not meet the challenge target, generating an interaction question for the response information according to the response information and the interaction target; or,

[0008] It is detected that the response information meets the challenge target, and the interaction result of the target interaction scenario is output.

[0009] In one embodiment, before the step of determining the challenge target and the interaction target according to the target interaction scenario currently selected by the user, the step further includes:

[0010] Displaying an interactive scene selection interface, wherein the interactive scene selection interface at least includes a text box and a random topic selection control;

[0011] In response to an editing operation of the text box, determining the target interaction scenario according to the editing operation; or,

[0012] In response to the trigger instruction of the random topic selection control, the target topic is obtained according to the trigger instruction, and the target interaction scene corresponding to the target topic is displayed in the text box.

[0013] In one embodiment, after the step of generating a target interaction question according to the interaction target and receiving answer information of the target interaction question, the method further includes:

[0014] Extracting keywords from the response information and determining semantic features of the keywords;

[0015] Acquire target semantic features of the challenge target;

[0016] When the similarity between the semantic feature and the target semantic feature is greater than or equal to a preset similarity, determining that the response information meets the challenge target;

[0017] When the similarity between the semantic feature and the target semantic feature is less than the preset similarity, it is determined that the response information does not meet the challenge target.

[0018] In one embodiment, the interaction target includes a plurality of sub-interaction target items, and the step of detecting that the response information does not meet the challenge target and generating an interaction question for the response information according to the response information and the interaction target includes:

[0019] Detecting that the response information does not meet the challenge target, extracting keywords from the response information, and determining semantic features of the keywords;

[0020] Acquiring semantic features of each of the sub-interaction target items;

[0021] Determine, according to the similarities between the semantic features of the keyword and the semantic features of each of the sub-interaction target items, the target sub-interaction target item corresponding to the maximum similarity;

[0022] Obtaining a preset interaction question corresponding to the target sub-interaction target item;

[0023] An interaction question of the response information is determined according to the preset interaction question.

[0024] In one embodiment, the step of determining the interaction question of the response information according to the preset interaction question includes:

[0025] Determine the user's grammatical habits;

[0026] Determining the target grammar of the preset interactive question according to the grammatical habit;

[0027] The target grammar is used to adjust the grammar of the preset interactive question to obtain the interactive question of the response information.

[0028] In one embodiment, the response information includes voice information and / or text information. After the steps of generating a target interaction question according to the interaction target and receiving the response information of the target interaction question, the following steps are further included:

[0029] Acquire standard answer information corresponding to the interactive question, wherein the standard answer information includes standard voice information and / or standard text information;

[0030] Detecting that the voice information does not meet the standard voice information and / or the text information does not meet the standard text information, determining and displaying error correction information of the response information;

[0031] Upon detecting that the voice information satisfies the standard voice information and / or the text information satisfies the standard text information, the step of detecting that the response information does not satisfy the challenge target and generating an interaction question for the response information according to the response information and the interaction target is performed; or, upon detecting that the response information satisfies the challenge target, the step of outputting the interaction result of the target interaction scenario is performed.

[0032] In one embodiment, after the step of obtaining the standard answer information corresponding to the interactive question, the method further includes:

[0033] Determine standard grammar information and standard pronunciation information of each word according to the standard voice information;

[0034] Detecting that the grammatical information of the voice information does not satisfy the standard grammatical information and the pronunciation information of each word of the voice information does not satisfy the standard pronunciation information, determining that the voice information does not satisfy the standard voice information;

[0035] And / or, after the step of obtaining the standard answer information corresponding to the interactive question, the method further includes:

[0036] Determining standard grammar information and standard spelling information of each word according to the standard text information;

[0037] It is detected that the grammatical information of the text information does not satisfy the standard grammatical information and the spelling information of each word of the text information does not satisfy the standard spelling information, and it is determined that the text information does not satisfy the standard text information.

[0038] In one embodiment, the step of detecting that the response information satisfies the challenge target and outputting the interaction result of the target interaction scenario includes:

[0039] Detecting that the response information meets the challenge goal, obtaining the scoring result and error correction information of the response information of each interactive question, and obtaining the difficulty level of the target interactive scenario;

[0040] Determining a total score result of the target interaction scenario according to the score results of each of the response information and the difficulty level of the target interaction scenario;

[0041] The interaction result of the target interaction scenario is generated and output according to the total score result of the target interaction scenario and the error correction information of each of the response information.

[0042] In addition, to achieve the above objectives, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the interaction method described above.

[0043] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the interaction method described above are implemented.

[0044] Before interacting with the chatbot, the application pre-selects the target interaction scenario, determines the challenge target and the interaction target, and generates interaction questions according to the interaction target. Because the interaction questions corresponding to different interaction scenarios are different, the interaction questions output by the robot for the same question are different in different interaction scenarios, thereby improving the accuracy of the response text. In addition, with the challenge target as a guide, the robot's interaction questions and the user's response information do not deviate from the interaction scenario, thereby realizing dialogue training in the interaction scenario and improving the teaching effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 A flowchart of the first embodiment of the interactive method of the present application is provided;

[0048] Figure 2A flowchart of the second embodiment of the interaction method of the present application is provided;

[0049] Figure 3 A flowchart of the third embodiment of the interaction method of the present application is provided;

[0050] Figure 4 A flowchart of the fourth embodiment of the interaction method of the present application is provided;

[0051] Figure 5 A brief flowchart of the interaction method provided in Example 4 of the present application;

[0052] Figure 6 A flowchart of Embodiment 5 of the interactive method of the present application is provided;

[0053] Figure 7 A flowchart of the sixth embodiment of the interactive method of the present application is provided;

[0054] Figure 8 It is a schematic diagram of the structure of an electronic device involved in the interactive method in an embodiment of the present application.

[0055] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0057] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0058] At present, by mining the text description vector of the consultation text to be analyzed, the text description vector is used to upgrade and optimize the chatbot's question-answering strategy, such as adjusting or modifying the answer text, so that the chatbot can be continuously improved and optimized, and the chatbot's intelligence level can be improved. In this way, the rigid question-answering processing mechanism of the chatbot in traditional technology can be improved. However, due to the limited scene recognition ability of the chatbot, there is a problem that the interaction problem for the same question in different dialogue scenarios is the same, resulting in low accuracy of the answer text, which affects the teaching effect.

[0059] In response to the above problems, the present application proposes an interaction method, the main technical solutions of which include: determining the challenge target and the interaction target according to the target interaction scenario currently selected by the user; generating a target interaction question according to the interaction target, and receiving the response information of the target interaction question; detecting that the response information does not meet the challenge target, generating an interaction question of the response information according to the response information and the interaction target; or, detecting that the response information meets the challenge target, outputting the interaction result of the target interaction scenario. Before interacting with the chat robot, the present application pre-selects the target interaction scenario, determines the challenge target and the interaction target, and generates an interaction question according to the interaction target. Since the corresponding interaction questions in different interaction scenarios are different, the interaction questions output by the robot for the same question are also different when the interaction scenarios are different, thereby improving the accuracy of the response text. In addition, with the challenge target as a guide, the robot's interaction questions and the user's response information do not deviate from the interaction scenario, thereby realizing dialogue training in the interaction scenario and improving the teaching effect.

[0060] In addition, the present application provides intelligent agents in different interaction scenarios, which can select interaction scenarios according to actual needs to meet the dialogue training requirements of different scenarios.

[0061] In addition, during the interaction process, the user's response information is corrected, such as grammar correction, spelling correction, etc., so that the user can be aware of his or her own shortcomings and provide convenience for the user's foreign language dialogue training.

[0062] In addition, during the interaction process, in addition to determining the robot's interaction questions based on the selected interaction scenario, the grammar of the robot's interaction questions is also adjusted according to the user's grammatical habits to obtain response information that is more in line with the user's grammatical habits and improve the teaching effect.

[0063] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes an electronic device as an example to illustrate this embodiment and the following embodiments.

[0064] In an application scenario, the interactive method of the present application can be used to realize daily foreign language dialogue teaching and training, where the foreign language can be English, French or other minority languages, etc. A foreign language training interactive scenario can be selected, and the challenge goal and interaction goal of the foreign language training interactive scenario can be obtained, and the interaction goal of the foreign language training interactive scenario can be completed and the challenge goal of the foreign language training interactive scenario can be achieved in a question-and-answer manner, thereby realizing the daily foreign language teaching and training process.

[0065] In addition, in another application scenario, the interactive method of the present application can be used to realize foreign language dialogue in foreign language tests, by setting an interactive scene, setting the challenge goal and interaction goal of the interactive scene, and asking questions through a robot and the user answering, and finally scoring based on the user's answer to each interactive goal of the interactive scene, and finally automatically outputting the user's interaction result for the interactive scene. In this way, a large amount of manpower and material resources can be freed up for grading, which can not only reduce costs, but also improve grading efficiency, providing convenience for test-taking.

[0066] Based on this, the present application embodiment provides an interaction method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the interactive method of the present application.

[0067] In this embodiment, the interaction method includes steps S10 to S40:

[0068] Step S10, determining a challenge target and an interaction target according to the target interaction scenario currently selected by the user;

[0069] An interaction scenario refers to the specific environment and context in which a user uses a product or service, as well as the interaction between the user and the product or service in these environments and contexts. This application can select the corresponding target interaction scenario in the application according to its own needs to simulate the specific environment and context in which the user actually uses the product or service.

[0070] The target interaction scenarios can be classified into "daily communication", "exam question bank", "travel", "communication with store clerks", "communication in the workplace", "campus life", "hobbies", "health and medicine", etc., and each category can be subdivided according to the actual situation. For example, the subdivided scenarios of "daily communication" can be "chatting with friends", "bargaining", "shopping with friends in the supermarket", "getting a number and waiting for a table in a restaurant", etc. The "exam question bank" can be subdivided into "IELTS real questions", "New Concept", "college student job interview", etc. according to the actual situation.

[0071] Different target interaction scenarios have corresponding challenge targets and interactions. The corresponding relationship between different interaction scenarios and challenge targets and interaction targets can be pre-built, and the challenge target and interaction target are determined based on the target interaction scenario currently selected by the user and the corresponding relationship. Among them, the challenge target and interaction target are related to the target interaction scenario currently selected by the user, and the interaction target can be multiple.

[0072] For example, assuming that the selected target interaction scenario is "taking a train while traveling", the challenge goal of the target interaction scenario may be "going swimming", and the interaction goals of the target interaction scenario may include multiple items, including but not limited to: "finding a nearby swimming pool", "checking the business hours of the swimming pool", "preparing for swimming", "obeying swimming pool rules and safety guidelines", and "enjoying swimming and practicing different swimming styles". For another example, assuming that the selected target interaction scenario is "arranging meetings with colleagues in workplace communication", the challenge goal of the target interaction scenario may be "arranging meetings with colleagues", and the interaction goals of the target interaction scenario may include multiple items, including but not limited to: "finding a suitable time period for meetings", "coordinating schedules with colleagues", "determining meeting agendas and goals", "considering the availability of meeting rooms", and "sending meeting invitations and reminders".

[0073] Step S20, generating a target interaction question according to the interaction target, and receiving response information of the target interaction question;

[0074] After generating an interaction target according to the target interaction scenario currently selected by the user, an interaction question is generated according to the interaction target, and different interaction targets correspond to different interaction questions. For example, when the interaction target is "find a nearby swimming pool", the corresponding interaction questions may be "where is the nearby swimming pool", "how many swimming pools are there nearby", "what is the name of the nearby swimming pool".

[0075] In a feasible implementation, a correspondence between an interaction target and a preset interaction question of the interaction target can be pre-constructed, the target interaction question is determined according to the current interaction target and the correspondence, and the target interaction question is displayed on the interaction interface, so as to achieve the effect of determining the interaction question corresponding to different interaction targets. It is understandable that when the target interaction scene changes, the corresponding interaction target and the interaction question of the interaction target also change, so that the interaction question of the robot in the current interaction scene can be accurately obtained, and the accuracy of the interaction question generated by the robot is improved.

[0076] In another feasible implementation, there may be multiple possible interaction questions for the same interaction target, and the closest interaction question can be determined as the target interaction question based on the user's historical reply information. For example, the user's grammatical habits or speaking habits are determined based on the user's historical reply information, and the closest interaction question is determined as the target interaction question based on the user's grammatical habits or speaking habits, and the target interaction question is displayed on the interactive interface. Among them, different reply information will be divided into corresponding grammatical tags, and each grammatical tag is associated with a corresponding interaction question tag, and each interaction question tag has a corresponding interaction question. The grammatical tag can be determined based on the user's historical reply information, and the interaction question tag associated with the grammatical tag is obtained, and then the target interaction question corresponding to the interaction question tag is obtained. It should be noted that if there is no historical reply information, an interaction question is randomly selected as the target interaction question.

[0077] After the target interaction question is generated, the target interaction question is displayed on the interactive interface. Among them, when the training language type is selected at the beginning, the training language type of the target interaction question is also determined accordingly, and the target interaction question corresponding to the selected training language type is displayed on the interactive interface. In addition to being displayed in the interactive interface in the form of text, the target interaction question can also be played by voice. In addition to displaying the target interaction question in the interactive interface in the selected training language type, the language type that the user is accustomed to using can also be selected according to usage habits, and the target interaction question is displayed in the interactive interface in the language type that the user is accustomed to using. For example, the training language type here can be English, and the language type that the user is accustomed to using here can be Chinese, etc.

[0078] The user can operate the voice input control or text input box on the interactive interface and send the answer information of the target interactive question. For example, the user enters the answer information of the target interactive question by long pressing the voice input control, and after disconnecting the contact with the voice input control, the answer information of the target interactive question is sent and displayed on the interactive interface. Alternatively, the answer information of the target interactive question is entered in the text input box, and the answer information is sent after the entry is completed. In order to facilitate operation, save typing time, and improve typing efficiency, the voice input control can be long pressed to enter the voice, and the entered voice can be converted into text content and the text content can be displayed in the preset display box of the interactive interface. After disconnecting the contact with the voice input control, the text content in the preset display box is sent after grammatical adjustment to improve typing efficiency.

[0079] The language type of the user's response information based on the target interactive question must be the same as the above-mentioned training language type to achieve the effect of dialogue training. The user's response information based on the target interactive question and the target interactive question are displayed on the same interactive interface, forming a question-answer effect in the interactive interface.

[0080] Step S30, detecting that the response information does not meet the challenge target, generating an interaction question for the response information according to the response information and the interaction target;

[0081] It should be noted that when the response information does not meet the challenge goal, it means that the current dialogue has not reached the end node, and it is necessary to continue asking questions until the challenge goal is met.

[0082] In a feasible implementation manner, different response information and interaction questions corresponding to interaction targets may be preset, and then the interaction questions of the response information may be obtained.

[0083] In another feasible implementation, context features may be inferred based on semantic features of the response information and semantic features of the interaction target, and interaction questions for the response information may be generated based on the context features.

[0084] Alternatively, in step S40, it is detected that the response information meets the challenge target, and the interaction result of the target interaction scenario is output.

[0085] It should be noted that when the response information meets the challenge goal, it means that the current dialogue has reached the end node, then the current dialogue is terminated, and the interaction result of the target interaction scene is output, where the interaction result includes but is not limited to the total score result of the target interaction scene and the error correction information of each response information.

[0086] This embodiment provides an interaction method. Before interacting with a chat robot, a target interaction scenario is pre-selected, and a challenge target and an interaction target are determined. Interaction questions are generated according to the interaction target. Because the interaction questions corresponding to different interaction scenarios are different, the interaction questions output by the robot in different interaction scenarios are also different for the same question, thereby improving the accuracy of the response text. In addition, with the challenge target as a guide, the robot's interaction questions and the user's response information do not deviate from the interaction scenario, thereby achieving dialogue training in the interaction scenario and improving the teaching effect.

[0087] In another optional embodiment, the user and the robot can terminate the interaction at any time, for example, by setting a preset response time, such as 5 minutes, within which the target interaction question needs to be answered. If the user does not answer the target interaction question within the preset response time, the interaction in the current target interaction scenario is exited.

[0088] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 2 Before step S10, the interaction method further includes steps S01 to S03:

[0089] Step S01, displaying an interactive scene selection interface, wherein the interactive scene selection interface at least includes a text box and a random topic selection control;

[0090] An interactive scene selection interface may be displayed on an electronic device.

[0091] A text box can be used as a text display box or a text input box.

[0092] Step S02, in response to an editing operation of the text box, determining the target interaction scenario according to the editing operation;

[0093] Edit in the text box and determine the target interaction scene based on the content edited in the text box to achieve the effect of a customized scene.

[0094] Since the content edited in the text box sometimes cannot directly determine the target interaction scene, therefore, after detecting that the user has finished editing, keywords are extracted based on the content edited by the user in the text box, and then the extracted keywords are searched for matching preset keywords in the database, and the user-defined target interaction scene is obtained based on the interaction scene associated with the preset keyword, so that the user's customized interaction scene can be intelligently, flexibly, and accurately identified. Here, searching for matching preset keywords based on keywords can be to convert keywords into word vectors, and calculate the cosine distance between the word vector of the keyword and the word vector of each preset keyword in the database, and determine the matching preset keyword based on the cosine distance.

[0095] Alternatively, in step S03, in response to a trigger instruction of the random topic selection control, a target topic is acquired according to the trigger instruction, and a target interaction scene corresponding to the target topic is displayed in the text box.

[0096] The random topic selection control is associated with different topic tags, and each topic tag has a corresponding interaction scenario. The random topic selection control corresponds to a random function. By clicking the random topic selection control, the random function is executed to obtain the randomly selected target topic, and then obtain the target interaction scenario corresponding to the target topic, and display the target interaction scenario corresponding to the target topic in the text box.

[0097] In this embodiment, a method for determining a target interaction scenario is provided. It is possible to determine the target interaction scenario according to one's own needs, and it is also possible to randomly select the target interaction scenario, realizing the customization of the target interaction scenario and meeting the different usage requirements of users.

[0098] Based on the above embodiments of the present application, in the third embodiment of the present application, for the same or similar content as the above embodiments, reference can be made to the above introduction and will not be repeated hereinafter. On this basis, please refer to Figure 3 , after step S20 or before step S30, the interaction method further includes steps S110 to S140:

[0099] Step S110, extract the keywords of the response information and determine the semantic features of the keywords;

[0100] Extracting the keywords of the response information and determining the semantic features of these keywords is a process involving natural language processing and text analysis. It includes the following steps:

[0101] First, perform text processing, including splitting the response information into words or phrases. Remove common words that contribute little to the meaning of the sentence, such as "de", "shi", etc. Restore the words to their basic form or extract their roots for better matching and comparison (this step is mainly applicable to languages with rich morphological changes such as English).

[0102] Next, perform keyword extraction, using algorithms such as TF-IDF (Term Frequency-Inverse Document Frequency), TextRank, etc. to extract keywords. These methods evaluate the importance of words by analyzing the frequency of words in the document and their distribution in the entire corpus. Or, use pre-trained word vectors such as Word2Vec, GloVe, BERT, etc. and deep learning models to identify keywords. These methods can capture the semantic relationships between words, thus extracting keywords more accurately. Or, if the response information belongs to a specific field, a professional dictionary of that field can be used to assist in extracting keywords.

[0103] Next, use pre-trained word vector models such as BERT, RoBERTa, etc. to obtain the vector representation of the keywords. These vectors can capture the semantic information of the words, including their context meaning, sentiment tendency, etc. For keywords with multiple meanings, perform word sense disambiguation to determine the specific meaning in the current context, which can be achieved by querying a dictionary, using context information, or applying a machine learning model. Use natural language processing tools such as dependency syntax analyzers, semantic role labelers, etc. to identify the semantic relationships between keywords, such as subject-predicate relationships, verb-object relationships, etc. These relationships help to more deeply understand the role and meaning of keywords in the response information. If the keywords are related to emotional expression, use sentiment analysis techniques to evaluate their sentiment tendency, such as positive, negative, or neutral.

[0104] Step S120, obtaining the target semantic features of the challenge target;

[0105] The extraction of the target semantic features of the challenge target is similar to the extraction of the semantic features of the response information described above, and will not be elaborated here.

[0106] Step S130, when the similarity between the semantic feature and the target semantic feature is greater than or equal to a preset similarity, determining that the response information meets the challenge target;

[0107] Step S140: When the similarity between the semantic feature and the target semantic feature is less than the preset similarity, it is determined that the response information does not meet the challenge target.

[0108] The preset similarity here can be determined and formulated according to the actual situation. This preset similarity should be able to balance the needs between "accuracy" and "recall rate", that is, to ensure that the response information does meet the requirements of the challenge goal, while avoiding missing reasonable responses due to the preset similarity being set too high.

[0109] Use appropriate semantic similarity calculation methods such as cosine similarity, Jaccard similarity, similarity evaluation based on deep learning models, etc. to compare the semantic features of the response information with the target semantic features to quantify the similarity between them, and compare the calculated similarity with the preset similarity. If the similarity is greater than or equal to the preset similarity, the response information is considered to meet the requirements of the challenge target; otherwise, it is considered not to meet the requirements.

[0110] In this embodiment, by accurately extracting the semantic features of the response information and the target content and calculating the similarity between them, it is possible to more accurately determine whether the response information truly understands the intention and requirements of the challenge target. Compared with simple text matching or keyword matching, this method can better capture the deep meaning and relationship between texts. In addition, when the response information can accurately reflect the intention of the challenge target, the user will be able to obtain more accurate and useful answers, which can not only improve the user's satisfaction with the system or service, but also enhance the interactive experience between the user and the system.

[0111] Based on the above embodiments of the present application, in the fourth embodiment of the present application, the same or similar contents as the above embodiments can be referred to the above introduction, and no further description will be given later. On this basis, the interaction target includes multiple sub-interaction target items, please refer to Figure 4 Step S130 includes: Steps S131 to S135:

[0112] Step S131, detecting that the response information does not meet the challenge target, extracting keywords from the response information, and determining semantic features of the keywords;

[0113] Step S132, obtaining semantic features of each of the sub-interaction target items;

[0114] The method of extracting keywords of the response information, determining the semantic features of the keywords, and obtaining the semantic features of each sub-interaction target item are similar to the above step S110 and will not be described in detail here.

[0115] It should be noted that there are multiple sub-interaction target items, and each sub-interaction target item has a corresponding interaction problem. The sub-interaction target item can guide the robot to generate the corresponding interaction problem, which is used to constrain the robot's interaction problem.

[0116] For example, assuming that the selected target interaction scenario is "taking a train while traveling", the sub-interaction target items of this target interaction scenario include but are not limited to: "find a nearby swimming pool", "check the operating hours of the swimming pool", "prepare for a swim", "comply with swimming pool rules and safety guidelines" and "enjoy swimming and practice different swimming styles".

[0117] Step S133, determining the target sub-interaction target item corresponding to the maximum similarity according to the similarity between the semantic features of the keyword and the semantic features of each of the sub-interaction target items;

[0118] Calculate the similarity between the semantic features of each keyword and the semantic features of each sub-interaction target item, such as using cosine similarity to compare the angle between two vectors, or using a similarity evaluation method based on a deep learning model. For each keyword, compare its similarity with all sub-interaction target items and find the sub-interaction target item with the greatest similarity. This process may require traversing all sub-interaction target items and performing similarity calculations on each target item.

[0119] If the response information contains multiple keywords, the above steps can be performed for each keyword, and the results of multiple keywords may need to be comprehensively considered. This can be achieved by weighted averaging, voting or other aggregation strategies of the similarity results of each keyword to improve the accuracy of the determined target sub-interaction target item.

[0120] Step S134, obtaining a preset interaction question corresponding to the target sub-interaction target item;

[0121] In a feasible implementation, the correspondence between different target sub-interaction target items and corresponding preset interaction questions can be pre-set, and the preset interaction question corresponding to the target sub-interaction target item can be determined according to the currently determined target sub-interaction target item and the pre-set correspondence.

[0122] In another feasible implementation, the target sub-interaction target item may also be input into the corresponding model to obtain a preset interaction question corresponding to the target sub-interaction target item.

[0123] Step S135: determining the interaction question of the response information according to the preset interaction question.

[0124] After determining the preset interactive question, the preset interactive question can be directly determined as the interactive question for the response information. Alternatively, after determining the preset interactive question, the preset interactive question can be adjusted according to the user's grammatical habits to obtain an interactive question that is more in line with the user's grammatical habits, and the interactive question is displayed on the interactive interface.

[0125] In this embodiment, when it is detected that the user's response information does not meet the challenge goal, the interaction problem of the response information is determined based on the user's response information and each sub-interaction target item, so that the determined interaction problem can be connected to the context without being separated from the current interaction scenario, thereby improving the accuracy of the interaction problem.

[0126] Further, see Figure 5 In one embodiment, step S135 includes steps S1351 to S1353:

[0127] Step S1351, determining the user's grammatical habits;

[0128] In a feasible implementation, different countries and regions usually use different primary languages, and these languages ​​often have their own grammatical rules. The user's current geographic location can be determined through the user's location information, and then the language area where the user may be located can be inferred based on the user's current geographic location, and then the user's grammatical habits can be determined based on the language area. For example, if the user is located in France, then they are likely to use French and follow French grammatical rules.

[0129] In another feasible implementation, if the system has historical interaction records with the user, the language features in these records can be analyzed, including vocabulary selection, sentence structure, grammatical rules, etc., to understand the user's grammatical habits.

[0130] In another feasible implementation, the user may be allowed to input a text as a sample, and the grammatical features of the text may be analyzed using natural language processing technology to determine the user's grammatical habits.

[0131] Step S1352, determining the target grammar of the preset interactive question according to the grammar habit;

[0132] The correspondence between different grammatical habits and the grammar of the preset interactive questions can be pre-constructed, and the target grammar of the preset interactive questions can be determined based on the grammatical habits of the user currently receiving training and the pre-constructed correspondence.

[0133] Step S1353: Use the target grammar to adjust the grammar of the preset interactive question to obtain the interactive question of the response information.

[0134] First, it is necessary to clarify the user's target grammatical features, including the user's commonly used vocabulary, sentence structure, grammatical rules, etc. Perform an in-depth analysis of the preset interactive questions to understand their current grammatical structure, including the subject, predicate, object and other elements of the sentence, as well as the complexity of the sentence and the arrangement of the word order. Then, replace the vocabulary in the preset interactive questions with vocabulary that the user is more commonly used or familiar with to conform to the user's grammatical habits, or reconstruct the sentence structure of the preset interactive questions according to the user's sentence preference. For example, if the user is used to using simple sentences, the complex sentence can be split into multiple simple sentences; if the user prefers to use inverted sentences or interrogative sentences, the word order or sentence type can be adjusted accordingly, or the tense, voice, subject-verb agreement and other aspects in the preset interactive questions can be adjusted in accordance with the user's grammatical rules. For example, if the user is used to using the present tense, the past tense or future tense in the original question should be converted to the present tense.

[0135] When adjusting the grammatical structure, it is necessary to ensure that the adjusted interactive questions are still semantically clear and accurate, and avoid changing the intent or meaning of the original questions due to grammatical adjustments.

[0136] In this embodiment, during the interaction process, the grammar of the robot's interactive questions is adjusted according to the user's grammatical habits to obtain response information that is more in line with the user's grammatical habits and improve the teaching effect.

[0137] Based on the above embodiments of the present application, in the fifth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and no further description will be given later. On this basis, the response information includes voice information and / or text information, referring to Figure 6 , after step S120, further comprising:

[0138] Step S210, obtaining standard answer information corresponding to the interactive question, wherein the standard answer information includes standard voice information and / or standard text information;

[0139] Each interactive question has corresponding standard answer information, which can be standard voice information, standard text information, or a combination of standard voice information and standard text information. Similarly, the user may have corresponding actual answer information for each interactive question, which can be voice information, text information, or a combination of voice information and text information.

[0140] Step S220, detecting that the voice information does not meet the standard voice information and / or the text information does not meet the standard text information, determining and displaying error correction information of the response information;

[0141] In a feasible implementation manner, when it is detected that the user's voice information in response to the interactive question does not meet the standard voice information, error correction information of the answer information is determined and displayed.

[0142] In another feasible implementation, it is detected that the text information of the user in response to the interactive question does not meet the standard text information, and error correction information of the answer information is determined and displayed.

[0143] In another feasible implementation, when it is detected that the user's voice information for the interactive question does not meet the standard voice information and the user's text information for the interactive question does not meet the standard text information, error correction information for the answer information is determined and displayed.

[0144] Regardless of the above situation, when the corresponding conditions are not met, it means that the current user's response information may contain grammatical errors, spelling errors or content that does not match the current interaction scenario. In order to improve the accuracy of subsequent interaction processes, when it is identified that the corresponding conditions are not met, error correction information for the response information is generated and displayed, so that users can intuitively and promptly discover errors and improve user experience.

[0145] Step S230, detects that the voice information meets the standard voice information and / or the text information meets the standard text information, executes step S130, detects that the response information does not meet the challenge goal, and generates an interaction question for the response information based on the response information and the interaction goal; or, executes step S140, detects that the response information meets the challenge goal, and outputs the interaction result of the target interaction scenario.

[0146] When the corresponding conditions are met, it means that the current user's response information does not have any grammatical errors, is spelled correctly, and does not contain any content that is inconsistent with the current interaction scenario. Subsequent operations can continue. The subsequent operations can be that when the response information does not meet the challenge goal, interaction questions for the response information can continue to be generated based on the response information and the interaction goal, or, when it is detected that the response information meets the challenge goal, the interaction results of the target interaction scenario are output.

[0147] In this embodiment, during the interaction process, the user's response information is corrected, such as grammar correction, spelling correction, etc., so that the user can be aware of his or her own shortcomings, which facilitates the user's foreign language dialogue training.

[0148] Further, in one embodiment, detecting whether the voice information satisfies the standard voice information and / or whether the text information satisfies the standard text information includes the following steps, that is, after step S210 or before step S220, further including:

[0149] Step S310, determining standard grammar information and standard pronunciation information of each word according to the standard voice information;

[0150] Step S320, detecting that the grammatical information of the voice information does not meet the standard grammatical information and the pronunciation information of each word of the voice information does not meet the standard pronunciation information, and determining that the voice information does not meet the standard voice information;

[0151] For voice information, the pronunciation of each word in the voice information is mainly considered to be accurate and the grammar is accurate. If it is detected that the grammatical information of the voice information does not meet the standard grammatical information and the pronunciation information of each word in the voice information does not meet the standard pronunciation information, it means that both the word pronunciation and the grammar are inaccurate, that is, it is determined that the voice information does not meet the standard voice information.

[0152] It is detected that the grammatical information of the speech information meets the standard grammatical information and the pronunciation information of each word of the speech information meets the standard pronunciation information, indicating that the word pronunciation and grammar are accurate, that is, it is determined that the speech information meets the standard speech information.

[0153] In this embodiment, whether the voice information meets the standard voice information is determined based on the pronunciation information and grammar information of the voice information, so as to facilitate error correction in subsequent voice input scenarios.

[0154] Furthermore, in one embodiment, after step S210 or before step S220, the following steps are further included:

[0155] Step S410, determining standard grammar information and standard spelling information of each word according to the standard text information;

[0156] Step S420: Detect that the grammatical information of the text information does not meet the standard grammatical information and the spelling information of each word of the text information does not meet the standard spelling information, and determine that the text information does not meet the standard text information.

[0157] For text information, the accuracy of the spelling and grammar of each word in the text information is mainly considered. If it is detected that the spelling information of the voice information does not meet the standard spelling information and the grammar information of each word in the voice information does not meet the standard grammar information, it means that both the word spelling and grammar are inaccurate, that is, it is determined that the text information does not meet the standard text information.

[0158] It is detected that the spelling information of the voice information meets the standard spelling information and the grammar information of each word of the voice information meets the standard grammar information, indicating that the word spelling and grammar are accurate, that is, it is determined that the text information meets the standard text information.

[0159] In this embodiment, whether the text information meets the standard text information is determined based on the spelling information and grammar information of the text information input by the user in response to the interactive question, so as to facilitate error correction in subsequent text input scenarios.

[0160] Based on the above embodiments of the present application, in the sixth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and no further description will be given later. On this basis, the response information includes voice information and / or text information, referring to Figure 7 Step S140 includes: Steps S141 to S143:

[0161] Step S141, detecting that the response information meets the challenge target, obtaining the scoring result and error correction information of the response information of each interactive question, and obtaining the difficulty level of the target interactive scenario;

[0162] Each interactive scenario will have a corresponding difficulty level, and if each response information has a corresponding scoring result, the scoring result of each response information can be determined based on the number of correct keywords contained in the response information and the completeness of the response information. Different scoring values ​​can be assigned to each keyword and the completeness of the response information, and then the scoring result of each response information can be determined based on the keyword scoring value of the response information for each interactive question and the completeness scoring value of the response information.

[0163] It should be noted that different interaction scenarios have different difficulty levels, and each difficulty level has a corresponding weight value.

[0164] Step S142, determining a total score result of the target interaction scenario according to the score results of each of the response information and the difficulty level of the target interaction scenario;

[0165] The basic total score value of the score results of each response information can be summarized to obtain the weight value corresponding to the difficulty level of the target interaction scene, and the basic total score value is weighted using the weight value to obtain the total score result of the target interaction scene.

[0166] Step S143: Generate and output the interaction result of the target interaction scenario according to the total score result of the target interaction scenario and the error correction information of each of the response information.

[0167] After obtaining the total score result of the target interaction scenario and the error correction information of each response information, this information will be displayed as the interaction result on the result display interface of the electronic device, so that the user can intuitively view his or her training status and defects for the target interaction scenario, which is convenient for subsequent summary and improves the teaching effect.

[0168] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the interaction method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0169] The present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the interaction method in the above-mentioned embodiment one.

[0170] Reference below Figure 8 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic devices in the embodiments of the present application may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0171] like Figure 8As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0172] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0173] The electronic device provided by the present application, using the interactive method in the above embodiment, can improve the accuracy of the chat robot's interactive questions and user response information, and improve the teaching effect. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as the beneficial effects of the interactive method provided by the above embodiment, and the other technical features in the electronic device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0174] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0175] The above is only a specific implementation 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.

[0176] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the interaction method in the above-mentioned embodiment.

[0177] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0178] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0179] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by an electronic device, the electronic device: determines a challenge target and an interaction target according to the target interaction scenario currently selected by the user; generates a target interaction question according to the interaction target, and receives response information of the target interaction question; detects that the response information does not meet the challenge target, and generates an interaction question for the response information according to the response information and the interaction target; or, detects that the response information meets the challenge target, outputs the interaction result of the target interaction scenario.

[0180] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0181] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0182] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0183] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned interactive method, and can improve the accuracy of chatbot interactive questions and user response information, and improve teaching effects. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the interactive method provided by the above-mentioned embodiment, and will not be repeated here.

[0184] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An interactive method, characterized in that: The method comprises: Determine the challenge target and interaction target based on the target interaction scenario currently selected by the user; generating a target interaction question according to the interaction target, and receiving response information of the target interaction question; detecting that the response information does not meet the challenge target, generating an interaction question for the response information according to the response information and the interaction target; or, It is detected that the response information meets the challenge target, and the interaction result of the target interaction scenario is output.

2. The method according to claim 1, characterized in that Before the step of determining the challenge target and the interaction target according to the target interaction scenario currently selected by the user, the method further includes: Displaying an interactive scene selection interface, wherein the interactive scene selection interface at least includes a text box and a random topic selection control; In response to an editing operation of the text box, determining the target interaction scenario according to the editing operation; or, In response to the trigger instruction of the random topic selection control, the target topic is obtained according to the trigger instruction, and the target interaction scene corresponding to the target topic is displayed in the text box.

3. The method according to claim 1, characterized in that After the step of generating a target interaction question according to the interaction target and receiving answer information of the target interaction question, the method further includes: Extracting keywords from the response information and determining semantic features of the keywords; Acquire target semantic features of the challenge target; When the similarity between the semantic feature and the target semantic feature is greater than or equal to a preset similarity, determining that the response information meets the challenge target; When the similarity between the semantic feature and the target semantic feature is less than the preset similarity, it is determined that the response information does not meet the challenge target.

4. The method according to claim 1, characterized in that The interaction target includes a plurality of sub-interaction target items, and the step of detecting that the response information does not meet the challenge target and generating an interaction question for the response information according to the response information and the interaction target includes: Detecting that the response information does not meet the challenge target, extracting keywords from the response information, and determining semantic features of the keywords; Acquiring semantic features of each of the sub-interaction target items; Determine, according to the similarities between the semantic features of the keyword and the semantic features of each of the sub-interaction target items, the target sub-interaction target item corresponding to the maximum similarity; Obtaining a preset interaction question corresponding to the target sub-interaction target item; An interaction question of the response information is determined according to the preset interaction question.

5. The method according to claim 4, characterized in that The step of determining the interaction question of the response information according to the preset interaction question comprises: Determine the user's grammatical habits; Determining the target grammar of the preset interactive question according to the grammatical habit; The target grammar is used to adjust the grammar of the preset interactive question to obtain the interactive question of the response information.

6. The method according to claim 1, characterized in that The response information includes voice information and / or text information. After the steps of generating a target interaction question according to the interaction target and receiving the response information of the target interaction question, the method further includes: Acquire standard answer information corresponding to the interactive question, wherein the standard answer information includes standard voice information and / or standard text information; Detecting that the voice information does not meet the standard voice information and / or the text information does not meet the standard text information, determining and displaying error correction information of the response information; Upon detecting that the voice information satisfies the standard voice information and / or the text information satisfies the standard text information, the step of detecting that the response information does not satisfy the challenge target and generating an interaction question for the response information according to the response information and the interaction target is performed; or, upon detecting that the response information satisfies the challenge target, the step of outputting the interaction result of the target interaction scenario is performed.

7. The method according to claim 6, characterized in that After the step of obtaining the standard answer information corresponding to the interactive question, the method further includes: Determine standard grammar information and standard pronunciation information of each word according to the standard voice information; Detecting that the grammatical information of the voice information does not satisfy the standard grammatical information and the pronunciation information of each word of the voice information does not satisfy the standard pronunciation information, determining that the voice information does not satisfy the standard voice information; And / or, after the step of obtaining the standard answer information corresponding to the interactive question, the method further includes: Determining standard grammar information and standard spelling information of each word according to the standard text information; It is detected that the grammatical information of the text information does not satisfy the standard grammatical information and the spelling information of each word of the text information does not satisfy the standard spelling information, and it is determined that the text information does not satisfy the standard text information.

8. The method according to any one of claims 1 to 7, characterized in that The step of detecting that the response information meets the challenge target and outputting the interaction result of the target interaction scenario includes: Detecting that the response information meets the challenge goal, obtaining the scoring result and error correction information of the response information of each interactive question, and obtaining the difficulty level of the target interactive scenario; Determining a total score result of the target interaction scenario according to the score results of each of the response information and the difficulty level of the target interaction scenario; The interaction result of the target interaction scenario is generated and output according to the total score result of the target interaction scenario and the error correction information of each of the response information.

9. An electronic device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the interaction method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the interaction method according to any one of claims 1 to 8 are implemented.

Images