Result generation method and device, equipment and storage medium

Abstract

The invention belongs to the technical field of computers, and discloses a result generation method and device, equipment and a storage medium. The method comprises the following steps: acquiring query information; searching related question and answer data corresponding to the question searching information; and generating question-asking result data based on the question-asking information and the related question-answering data. The related question and answer data related to the questioning information is searched after the questioning information is obtained, and the questioning result data is further generated according to the questioning information and the related question and answer data, so that a user can obtain a required result only by questioning without modifying a question or a keyword by himself, the complexity is reduced, and the user experience is improved. And the use experience of the user is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a result generation method, device, equipment and storage medium. Background Art

[0002] Nowadays, in the field of human-computer interaction, computers can only feedback corresponding results for the same search term. If the user is not satisfied with the search or generated data results, he can only modify the questions or search terms he asked and try to obtain the results again. When adjusting the search terms, the user needs to have relatively rich search or query experience to adjust them more accurately, so as to obtain the results that the user really needs. However, users generally do not have rich experience, which leads to a high overall complexity of use and a poor user experience.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a result generation method, device, equipment and storage medium, aiming to solve the technical problem in the prior art that when users are not satisfied with the obtained results, they can only adjust the questions or search terms by themselves.

[0005] To achieve the above object, the present invention provides a result generation method, which comprises the following steps:

[0006] In response to the received follow-up question information, searching for relevant question and answer data corresponding to the follow-up question information and question information corresponding to the relevant question and answer data;

[0007] Get follow-up information;

[0008] Searching for relevant question and answer data corresponding to the follow-up question information;

[0009] Generate inquiry result data based on the inquiry information and the related question and answer data.

[0010] Optionally, the step of generating follow-up question result data based on the follow-up question information and the related question and answer data includes:

[0011] Obtaining the information modification intention corresponding to the inquiry information;

[0012] Extracting target question information from the relevant question-answer data;

[0013] Constructing follow-up question information according to the information modification intention and the target question information;

[0014] Generate follow-up question result data based on the follow-up question information and the related question and answer data.

[0015] Optionally, the step of obtaining the information modification intention corresponding to the inquiry information includes:

[0016] Extracting keywords from the follow-up question information to obtain a set of follow-up question keywords;

[0017] Performing weight analysis on the query keyword set to obtain a keyword weight sequence;

[0018] Matching is performed in a preset knowledge base according to the keyword weight sequence to determine the information modification intention corresponding to the follow-up information.

[0019] Optionally, the step of performing weight analysis on the query keyword set to obtain a keyword weight sequence includes:

[0020] Obtaining the question structure and information properties corresponding to the follow-up information;

[0021] Determine the weight ratio corresponding to each follow-up keyword in the follow-up keyword set according to the question structure and the information nature;

[0022] The follow-up question keywords in the follow-up question keyword set are sorted based on the weight ratio to obtain a keyword weight sequence.

[0023] Optionally, the step of constructing follow-up question information according to the information modification intention and the target question information includes:

[0024] Determine the problem modification location and problem modification instructions based on the information modification intention;

[0025] The target question information is adjusted according to the question modification position and the question modification instruction to obtain follow-up question information.

[0026] Optionally, the step of extracting target question information from the relevant question and answer data includes:

[0027] Determine the problem domain and problem modification instructions based on the information modification intention;

[0028] Matching the question domain and the question modification instruction with the question information corresponding to each of the relevant question and answer data to determine the matching degree corresponding to each of the question information;

[0029] Based on the matching degree, target question information is selected from the question information corresponding to each of the related question and answer data.

[0030] Optionally, the step of adjusting the target question information according to the question modification position and the question modification instruction to obtain the follow-up question information includes:

[0031] Determining the keywords to be modified in the target question information according to the question modification position;

[0032] Searching for a keyword set corresponding to the problem modification instruction based on the to-be-modified keyword;

[0033] Extracting replacement keywords from the keyword set;

[0034] The keywords to be modified in the target question information are adjusted according to the replacement keywords to obtain follow-up question information.

[0035] Optionally, the step of extracting replacement keywords from the keyword set includes:

[0036] Compare the question information corresponding to the relevant question and answer data with the target question information to determine the difference keywords;

[0037] Filtering the keyword set according to the difference keywords to obtain a candidate keyword set;

[0038] Extract replacement keywords from the candidate keyword set.

[0039] Optionally, the step of generating follow-up question result data based on the follow-up question information and the related question and answer data includes:

[0040] Searching in a preset knowledge base based on the follow-up question information to obtain at least one answer corpus information;

[0041] Perform keyword extraction on the answer corpus information to obtain result keywords;

[0042] Construct follow-up question result data according to the result keywords and the related question and answer data.

[0043] Optionally, the step of extracting keywords from the answer corpus information to obtain result keywords includes:

[0044] Obtaining question keywords corresponding to the follow-up question information;

[0045] Find the answer keywords corresponding to the question keywords;

[0046] Keyword extraction is performed on the answer corpus information according to the answer keywords to obtain result keywords.

[0047] Optionally, the step of extracting keywords from the answer corpus information according to the answer keywords to obtain result keywords includes:

[0048] Selecting target corpus information from the at least one answer corpus information according to the relevant question and answer data;

[0049] Keyword extraction is performed on the target corpus information according to the answer keywords to obtain result keywords.

[0050] Optionally, the step of searching for relevant question and answer data corresponding to the follow-up question information includes:

[0051] Obtaining session identification data corresponding to the follow-up question information;

[0052] Searching for corresponding historical display results and historical question information according to the session identification data to obtain historical display data;

[0053] searching for question information corresponding to the historical display data according to the result response identifier corresponding to the historical display data;

[0054] Relevant question and answer data are constructed according to the historical display data and the question information.

[0055] Optionally, the step of obtaining follow-up information includes:

[0056] Obtain the follow-up information input by the user through the interactive input box, or obtain the follow-up information input by the user through the follow-up prompt button.

[0057] Optionally, the interactive input box and / or the follow-up prompt button includes at least one of the following:

[0058] The interactive input box is displayed independently;

[0059] The interactive input box and the interactive topic are displayed correspondingly;

[0060] Displayed in association with question and answer pairs;

[0061] Display in association with the question;

[0062] Display in association with the answer;

[0063] After receiving the user's operation of selecting page content, it is displayed in association with the selected content.

[0064] In addition, to achieve the above object, the present invention also proposes a result generating device, which includes the following modules:

[0065] An acquisition module is used to obtain follow-up information;

[0066] A search module, used to search for relevant question and answer data corresponding to the follow-up question information;

[0067] A generation module is used to generate question result data based on the question information and the related question and answer data.

[0068] Optionally, the generation module is also used to obtain the information modification intention corresponding to the follow-up information; extract target question information from the relevant question and answer data; construct follow-up question information according to the information modification intention and the target question information; and generate follow-up question result data based on the follow-up question information and the relevant question and answer data.

[0069] Optionally, the generation module is further used to extract keywords from the follow-up information to obtain a follow-up keyword set; perform weight analysis on the follow-up keyword set to obtain a keyword weight sequence; and match the keyword weight sequence in a preset knowledge base to determine the information modification intention corresponding to the follow-up information.

[0070] Optionally, the generation module is also used to obtain the question structure and information properties corresponding to the follow-up information; determine the weight ratio corresponding to each follow-up keyword in the follow-up keyword set according to the question structure and the information properties; sort the follow-up keywords in the follow-up keyword set based on the weight ratio to obtain a keyword weight sequence.

[0071] In addition, to achieve the above-mentioned purpose, the present invention also proposes a result generating device, which includes: a processor, a memory, and a result generating program stored in the memory and executable on the processor, and the result generating program implements the steps of the result generating method described above when executed by the processor.

[0072] In addition, to achieve the above-mentioned purpose, the present invention also proposes a computer-readable storage medium, on which a result generation program is stored, and when the result generation program is executed, the steps of the result generation method described above are implemented.

[0073] The present invention obtains follow-up information; searches for relevant question and answer data corresponding to the follow-up information; and generates follow-up result data based on the follow-up information and the relevant question and answer data. After the follow-up information is obtained, the relevant question and answer data related to the follow-up information is searched, and the follow-up result data is further generated based on the follow-up information and the relevant question and answer data, so that the user does not need to modify the question or keywords by himself, but only needs to ask questions to obtain the results he needs, which reduces the complexity and improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a schematic diagram of the structure of an electronic device in a hardware operating environment involved in an embodiment of the present invention;

[0075] Figure 2 It is a flowchart of the first embodiment of the result generation method of the present invention;

[0076] Figure 3It is a flow chart of the second embodiment of the result generating method of the present invention;

[0077] Figure 4 It is a flowchart of a third embodiment of the result generation method of the present invention;

[0078] Figure 5 It is a flowchart of a fourth embodiment of the result generating method of the present invention;

[0079] Figure 6 It is a flowchart of a fifth embodiment of the result generating method of the present invention;

[0080] Figure 7 It is a structural block diagram of the first embodiment of the result generating device of the present invention.

[0081] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0082] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0083] Reference Figure 1 , Figure 1 A schematic diagram of a device structure is generated as a result of the hardware operating environment involved in the embodiment of the present invention.

[0084] like Figure 1 As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0085] Those skilled in the art will understand that Figure 1The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0086] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a result generation program.

[0087] exist Figure 1 In the electronic device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in a result generating device, and the electronic device calls the result generating program stored in the memory 1005 through the processor 1001, and executes the result generating method provided by an embodiment of the present invention.

[0088] The embodiment of the present invention provides a method for generating a result, referring to Figure 2 , Figure 2 The figure is a flow chart of a first embodiment of a result generating method of the present invention.

[0089] In this embodiment, the result generation method includes the following steps:

[0090] Step S10: Obtaining follow-up information.

[0091] It should be noted that the executor of this embodiment may be the result generating device, in which a result generating program (also referred to as an intelligent assistant, which may be a pre-trained intelligent language model) is provided, and the result generating device may be a personal computer, server or other electronic device, or other device that can realize the same or similar functions. This embodiment does not limit this. In this embodiment and the following embodiments, the result generating method of this embodiment and the following embodiments is explained by taking the result generating device as an example.

[0092] It should be noted that the intelligent assistant will divide the process of interacting with the user into sessions. The cycle of a session is the entire process from the user opening the interaction window to closing the interaction window. After the user obtains the result data once, if the user enters the question again, the intelligent assistant will determine that it has received follow-up information.

[0093] In order to avoid misjudgment of follow-up questions, after receiving the question or search term input by the user, it can also be matched with other questions in the current session to determine the relevance. If the relevance reaches a preset threshold, it is determined that the follow-up question information has been received.

[0094] In a specific implementation, the user can input the follow-up information through the interactive input box set in the interactive window, or can input the follow-up information by clicking the follow-up prompt button displayed in the interactive window. The display of the interactive input box and / or the follow-up prompt button may include at least one of the following:

[0095] The interactive input box is displayed independently (i.e., an independent area is divided in the interactive window to display the interactive input box);

[0096] The interactive input box is displayed corresponding to the interactive topic (i.e., an interactive input box is set for each interactive topic in the interactive window);

[0097] Displaying in association with question-answer pairs (i.e., displaying an interactive input box and / or at least one follow-up prompt button in the display area of ​​each question-answer pair);

[0098] Display in association with the question (i.e., displaying an interactive input box and / or at least one follow-up question prompt button in the display area for each question input by the user);

[0099] Display in association with the answer (i.e., display an interactive input box and / or at least one follow-up prompt button in the display area of ​​each answer);

[0100] After receiving the user's operation of selecting page content, it is displayed in association with the selected content (that is, after the user selects page content in the interactive interface, an interactive input box and / or at least one follow-up prompt button is displayed near the selected content).

[0101] The question may be a question input by the user, and the answer may be the displayed result data.

[0102] Step S20: searching for relevant question and answer data corresponding to the follow-up question information.

[0103] It should be noted that when generating result data, the intelligent assistant will determine the question information based on the questions or keywords input by the user, combined with the current context and the user's historical interaction feedback data, and generate result data based on the question information. At this time, the relevant question and answer data corresponding to the follow-up information may include the questions input by the user in the same session as the follow-up information, the question information used by the intelligent assistant when generating the result data, and the generated result data.

[0104] In the specific implementation, in order to ensure that the relevant question and answer data can be accurately obtained, the intelligent assistant can set a corresponding unique identifier for each conversation. When it is necessary to obtain the relevant question and answer data corresponding to the follow-up information, the session unique identifier of the conversation to which the follow-up information belongs can be obtained, and the relevant question and answer data can be searched according to the session unique identifier.

[0105] In a specific implementation, in order to ensure that relevant question and answer data can be accurately obtained, the intelligent assistant can set a corresponding unique identifier for each conversation. In this case, step S20 in this embodiment may include:

[0106] Obtaining session identification data corresponding to the follow-up question information;

[0107] Searching for corresponding historical display results and historical question information according to the session identification data to obtain historical display data;

[0108] searching for question information corresponding to the historical display data according to the result response identifier corresponding to the historical display data;

[0109] Relevant question and answer data are constructed according to the historical display data and the question information.

[0110] It should be noted that obtaining the session identification data corresponding to the follow-up information may be to obtain the unique identifier corresponding to the session to which the follow-up information belongs, thereby obtaining the session identification data. According to the session identification data, the corresponding historical display results and historical question information are searched, and the historical display data is obtained by searching for the session whose corresponding unique identifier is consistent with the session identification data, and then obtaining all historical display results and historical question data belonging to the session, thereby obtaining the historical display data. Among them, the historical display results may be the result data generated by the intelligent assistant based on the questions raised by the user, and the historical question data may be the question information historically input by the user.

[0111] Similarly, when generating result data, the intelligent assistant will set a corresponding unique identifier for the result data, and store it in association with the question information used to generate the result data. Then, searching for the question information corresponding to the historical display data according to the result response identifier corresponding to the historical display data can be to obtain the unique identifier of the result data contained in the historical display data, that is, the result response identifier, and searching for the question information associated with the historical display data according to the result response identifier, thereby obtaining the question information corresponding to the historical display data.

[0112] In actual use, constructing relevant question and answer data based on historical display data and question information may be to aggregate the historical display data and question information according to a corresponding relationship, thereby obtaining relevant question and answer data.

[0113] Step S30: Generate inquiry result data based on the inquiry information and the related question and answer data.

[0114] It should be noted that generating follow-up question result data based on follow-up question information and related question and answer data can be to select target question and answer data with the highest relevance to the follow-up question information from the related question and answer information, modify the question information in the target question and answer data according to the follow-up question information, obtain the follow-up question information, and then search for related corpus data based on the follow-up question information, and generate follow-up question result data based on the corpus data.

[0115] This embodiment obtains follow-up information; searches for relevant question and answer data corresponding to the follow-up information; and generates follow-up result data based on the follow-up information and the relevant question and answer data. After obtaining the follow-up information, the relevant question and answer data related to the follow-up information is searched, and the follow-up result data is further generated based on the follow-up information and the relevant question and answer data, so that the user does not need to modify the question or keywords by himself, but only needs to ask questions to obtain the results he needs, which reduces complexity and improves the user experience.

[0116] refer to Figure 3 , Figure 3 It is a flowchart of a second embodiment of a result generating method of the present invention.

[0117] Based on the first embodiment, step S30 of the result generation method of this embodiment includes:

[0118] Step S301: Obtain the information modification intention corresponding to the inquiry information.

[0119] It should be noted that obtaining the information modification intention corresponding to the follow-up information can be to perform semantic analysis on the follow-up information to determine the reason why the user is dissatisfied with the generated result data, thereby obtaining the information modification intention. For example: if the follow-up information input by the user is "Can it be more detailed?", it means that the user thinks that the currently displayed result data is too rough, and at this time, the information modification intention corresponding to the follow-up information can be determined to be "obtain more detailed data results"; if the follow-up information input by the user is "the result field is wrong", it means that the user thinks that there is an error in the field of the currently displayed result data, and at this time, the information modification intention corresponding to the follow-up information can be determined to be "obtain data in other fields".

[0120] Step S302: extracting target question information from the relevant question and answer data.

[0121] It should be noted that when a user asks a follow-up question, it is generally based on the result data displayed last time. In this case, extracting the target question information from the relevant question and answer data can be to obtain the result data displayed last time in the relevant question and answer data, and then use the question information corresponding to the result data as the target question information.

[0122] Furthermore, after asking a question, the user may try to ask other questions. In order to meet this scenario, step S302 in this embodiment may include:

[0123] Determine the problem domain and problem modification instructions based on the information modification intention;

[0124] Matching the question domain and the question modification instruction with the question information corresponding to each relevant question and answer data, and determining the matching degree corresponding to each question information;

[0125] Based on the matching degree, target question information is selected from question information corresponding to relevant question and answer data.

[0126] It should be noted that when users ask follow-up questions about other previous questions, they will generally be more specific. At this time, the information modification intention determined based on the follow-up information will include information related to the previously asked questions, such as the field to which the question belongs (such as the mechanical field, software development field, etc.) and more specific question modification instructions. At this time, the question attribution field and question modification instructions can be extracted from the information modification intention, and then the question attribution field and question modification instructions are matched with the question information corresponding to each relevant question and answer data, so as to determine the matching degree corresponding to each question information.

[0127] In actual use, selecting target question information from question information corresponding to relevant question and answer data based on the matching degree may be selecting question information with the greatest matching degree among the question information corresponding to the relevant question and answer data as the target question information.

[0128] Step S303: construct follow-up question information according to the information modification intention and the target question information.

[0129] It should be noted that constructing the follow-up question information according to the information modification intention and the target question information may be to adjust the target question information according to the information modification intention, thereby obtaining the follow-up question information. Adjusting the target question information may be to replace or add keywords to the target question information, and this embodiment does not limit this.

[0130] Step S304: Generate follow-up question result data based on the follow-up question information and the related question and answer data.

[0131] It should be noted that generating follow-up question result data based on follow-up question information and related question and answer data can be to generate at least one result data based on the follow-up question information, calculate the answer matching degree of each result data in combination with the related question and answer data, and take the one with the highest answer matching degree as the follow-up question result data.

[0132] Calculating the answer matching degree of each result data in combination with the relevant question and answer data may be calculating the correlation degree between the result data and the result data included in the relevant question and answer data, and using the correlation degree as the answer matching degree.

[0133] Of course, in some cases, if the user believes that the previously generated result data is not satisfactory, he will ask follow-up questions to adjust the subsequently generated result data. At this time, the answer matching degree of each result data can be calculated in combination with the result data contained in the relevant question and answer data and the information modification intention. At this time, the correlation and difference data between the result data contained in the relevant question and answer data and the generated result data can be calculated first, and then the answer matching degree corresponding to each result data can be determined according to the information modification intention, the correlation and the difference data. For example: assuming that the information modification intention is "obtaining more detailed data results", the higher the correlation and the more difference data, the higher the answer matching degree; if the information modification intention is "obtaining data in other fields", the lower the correlation program and the more difference data, the higher the answer matching degree.

[0134] This embodiment obtains the information modification intention corresponding to the follow-up information; extracts the target question information from the related question and answer data; constructs the follow-up question information according to the information modification intention and the target question information; and generates the follow-up question result data based on the follow-up question information and the related question and answer data. Since the corresponding information modification intention is determined according to the follow-up information, the follow-up question information is constructed according to the information modification intention and the question information corresponding to the related question and answer data corresponding to the follow-up information, and the follow-up question result data is generated according to the follow-up question information and the related question and answer data, the user does not need to modify the question or keywords by himself, but only needs to ask questions to obtain the results he needs, which reduces the complexity and improves the user experience.

[0135] refer to Figure 4 , Figure 4 It is a flowchart diagram of a third embodiment of a result generating method of the present invention.

[0136] Based on the above second embodiment, step S301 of the result generation method of this embodiment includes:

[0137] Step S3011: extract keywords from the follow-up question information to obtain a set of follow-up question keywords.

[0138] It should be noted that extracting keywords from the follow-up information to obtain the follow-up keyword set may be to segment the follow-up information, and after segmentation, obtain a segmentation set, and delete modal particles, conjunctions, etc. in the segmentation set to obtain the follow-up keyword set.

[0139] Step S3012: performing weight analysis on the query keyword set to obtain a keyword weight sequence.

[0140] It should be noted that the weight analysis of the follow-up keyword set can be performed in combination with the context to determine the weight of each keyword in the follow-up keyword set, and sort the keywords in the follow-up keyword set from high to low according to the weight, and construct a keyword weight sequence based on the sorting results.

[0141] In a specific implementation, in order to ensure the normal construction of the keyword weight sequence, step S3012 in this embodiment may include:

[0142] Obtaining the question structure and information properties corresponding to the follow-up information;

[0143] Determine the weight ratio corresponding to each follow-up keyword in the follow-up keyword set according to the question structure and the information nature;

[0144] The follow-up question keywords in the follow-up question keyword set are sorted based on the weight ratio to obtain a keyword weight sequence.

[0145] It should be noted that when users input follow-up information, the question structure (the grammatical structure used to ask questions, including the connection relationship, connection order, conjunctions, etc. between key words) and the nature of the information (the type of question asked, such as rhetorical questions, interrogative sentences, etc.) used may affect the weight of the keywords. In order to ensure the normal construction of the keyword weight sequence, the question structure and information nature corresponding to the follow-up information can be obtained first, and then the follow-up information can be semantically analyzed according to the question structure and information nature to determine the weight ratio corresponding to each follow-up keyword in the follow-up keyword set, and then the follow-up keywords in the follow-up keyword set can be sorted based on the weight ratio to obtain the keyword weight sequence.

[0146] Among them, since the keywords at the front of the sequence play a greater role in determining the intent later, when sorting the follow-up keywords in the follow-up keyword set based on the weight ratio, the follow-up keywords in the follow-up keyword set can be sorted from large to small according to the corresponding weight ratio to ensure that the keywords with higher weight ratios are at the front of the sequence.

[0147] Step S3013: matching the keyword weight sequence in a preset knowledge base to determine the information modification intention corresponding to the follow-up information.

[0148] It should be noted that the preset knowledge base can be a database used to train the intelligent assistant in advance, which contains a large number of data samples constructed according to the keyword weight sequence and the modification intention. After the intelligent assistant determines the keyword weight sequence corresponding to the follow-up information, it can match it in the preset knowledge base according to the keyword weight sequence, determine at least one data sample, and make a prediction based on the data sample to determine the information modification intention corresponding to the follow-up information.

[0149] This embodiment extracts keywords from the follow-up information to obtain a follow-up keyword set; performs weight analysis on the follow-up keyword set to obtain a keyword weight sequence; matches the keyword weight sequence in a preset knowledge base to determine the information modification intention corresponding to the follow-up information. Since the follow-up information is first subjected to keyword extraction, and then the weight analysis is performed on each keyword in the extracted follow-up keyword set to determine the importance of each keyword, and a keyword warrant sequence is constructed, and then the information modification intention is determined based on the keyword weight sequence, it is ensured that when determining the information modification intention, there will be no intention recognition errors caused by keyword identification errors, thereby improving the accuracy of the result generation method of this application.

[0150] refer to Figure 5 , Figure 5 It is a flowchart diagram of a fourth embodiment of a result generating method of the present invention.

[0151] Based on the above second embodiment, step S303 of the result generation method of this embodiment includes:

[0152] Step S3031: Determine the problem modification location and problem modification instructions based on the information modification intention.

[0153] It should be noted that determining the question modification position and question modification instructions based on the information modification intention may be to determine the keyword position related to the information modification intention in the target question information, determine the question modification position, and search for question modification instructions matching the information modification intention. The question modification instructions may include the adjustment direction of the keywords, such as replacing them with more detailed synonyms or replacing them with similar professional terms.

[0154] Step S3032: adjusting the target question information according to the question modification position and the question modification instruction to obtain follow-up question information.

[0155] It should be noted that the target question information is adjusted according to the question modification position and the question modification instruction, and the follow-up question information can be obtained by extracting the keywords to be modified in the target question information according to the question modification position, and replacing the keywords to be modified according to the question modification instruction, thereby obtaining the follow-up question information.

[0156] In a specific implementation, in order to ensure that accurate follow-up question information can be obtained as much as possible, step S3032 in this embodiment may include:

[0157] Determining the keywords to be modified in the target question information according to the question modification position;

[0158] Searching for a keyword set corresponding to the problem modification instruction based on the to-be-modified keyword;

[0159] Extracting replacement keywords from the keyword set;

[0160] The keywords to be modified in the target question information are adjusted according to the replacement keywords to obtain follow-up question information.

[0161] It should be noted that determining the keywords to be modified in the target question information according to the question modification position may be to obtain the keywords located at the question modification position in the target question information, thereby determining the keywords to be modified. Searching for a keyword set corresponding to the question modification instruction based on the keywords to be modified may be to search for corresponding keywords according to the adjustment direction of the keywords in the question modification instruction and the keywords to be modified, and constructing a keyword set based on the found keywords.

[0162] In actual use, extracting the replacement keyword from the keyword set may be to randomly extract a keyword from the keyword set as the replacement keyword. Adjusting the keyword to be modified in the target question information according to the replacement keyword, and obtaining the follow-up question information may be to modify the keyword to be modified in the target question information into the replacement keyword, thereby obtaining the follow-up question information.

[0163] Furthermore, in order to reasonably select replacement keywords and avoid duplication of follow-up question information with previously used question information, the step of extracting replacement keywords from the keyword set in this embodiment may include:

[0164] Compare the question information corresponding to the relevant question and answer data with the target question information to determine the difference keywords;

[0165] Filtering the keyword set according to the difference keywords to obtain a candidate keyword set;

[0166] Extract replacement keywords from the candidate keyword set.

[0167] It should be noted that, the keyword set is screened according to the difference keyword to obtain the candidate keyword set, which may be obtained by removing the keywords in the keyword set that are the same as the difference keyword, thereby obtaining the candidate keyword set. Extracting the replacement keyword from the candidate keyword set may be randomly extracting a keyword from the candidate keyword set as the replacement keyword.

[0168] It is understandable that in order to obtain the results they need, users may ask questions multiple times in the same session. If the user obtains the required results, he or she will not ask the question again. Therefore, in order to avoid the generated result data being the same as the previously generated one, the question information corresponding to the relevant question and answer data can be compared with the target question information to determine the difference keywords, and then the keyword set can be filtered based on the difference keywords to ensure that after the target question information is adjusted by selecting keywords, the generated follow-up question information will not be repeated with the question information used to generate the result data previously.

[0169] This embodiment selects target question information from the question information corresponding to the relevant question and answer data; determines the question modification position and question modification instructions based on the information modification intention; and adjusts the target question information according to the question modification position and the question modification instructions to obtain follow-up question information. Since the target question information that the user actually asks is extracted from the question information corresponding to the relevant question and answer data, and then the target question information is adjusted according to the question modification position and question modification instructions determined by the information modification intention to obtain the follow-up question information, it is ensured that the follow-up question information can be accurately generated according to the user's actual modification intention, and the accuracy of the results fed back by the result generation method of this embodiment is improved.

[0170] refer to Figure 6 , Figure 6 It is a flowchart diagram of a fifth embodiment of a result generating method of the present invention.

[0171] Based on the above second embodiment, step S304 of the result generation method of this embodiment includes:

[0172] Step S3041: searching in a preset knowledge base based on the follow-up question information to obtain at least one piece of answer corpus information.

[0173] It should be noted that searching in a preset knowledge base based on the follow-up question information to obtain at least one piece of answer corpus information may be searching in the preset knowledge base for answer corpus information that matches the follow-up question information, thereby obtaining at least one piece of answer corpus information. The manager of the result generating device may pre-set corresponding data tags for the answer corpus information in the preset knowledge base, and if the tag of the answer corpus information matches a keyword in the follow-up question information, it may be determined that the answer corpus information matches the follow-up question information.

[0174] Step S3042: extract keywords from the answer corpus information to obtain result keywords.

[0175] It should be noted that the answer corpus information is generally the answers or suggestions obtained on the Internet, and the content of some answer corpus information is bloated and contains a lot of useless information. In order to exclude this useless information, keyword extraction can be performed on the answer corpus information to obtain keywords related to the answer question information, that is, result keywords.

[0176] Further, in order to accurately extract keywords from the answer corpus information, step S3042 in this embodiment may include:

[0177] Obtaining question keywords corresponding to the follow-up question information;

[0178] Find the answer keywords corresponding to the question keywords;

[0179] Keyword extraction is performed on the answer corpus information according to the answer keywords to obtain result keywords.

[0180] It should be noted that obtaining the question keyword corresponding to the follow-up question information may be to parse the follow-up question information to obtain at least one keyword contained in the follow-up question information, thereby obtaining the question keyword. Finding the answer keyword corresponding to the question keyword may be to find the answer keyword corresponding to the question keyword in a preset keyword mapping table, wherein the answer keyword may be a keyword that may appear when the question corresponds to the question keyword, and the preset keyword mapping table may include a mapping relationship between the answer keyword and the question keyword, and the mapping relationship may be pre-set by the administrator of the result generation device, or may be constructed by the intelligent assistant when training the intelligent assistant.

[0181] In a specific implementation, keyword extraction is performed on the answer corpus information according to the answer keyword, and the result keyword can be obtained by extracting keywords that are the same as the answer keyword or have a similar part of speech to the answer keyword from the answer corpus information to obtain the result keyword.

[0182] Furthermore, since the answer corpus information obtained may be repeated when answering different question information, in order to avoid repeated answers causing a decrease in the actual user experience, the step of extracting keywords from the answer corpus information according to the answer keywords and obtaining result keywords in this embodiment may include:

[0183] Selecting target corpus information from the at least one answer corpus information according to the relevant question and answer data;

[0184] Keyword extraction is performed on the target corpus information according to the answer keywords to obtain result keywords.

[0185] It should be noted that selecting target corpus information from at least one answer corpus information based on relevant question and answer data may be to obtain the answer corpus information corresponding to the relevant question and answer data, remove the answer corpus information in at least one answer corpus information that is consistent with the answer corpus information corresponding to the relevant question and answer data, and use the remaining answer corpus information as the target corpus information.

[0186] It is understandable that by adjusting at least one piece of answer corpus information currently found in combination with the answer corpus information used in the relevant question and answer data, it is possible to avoid feeding back the same result when the user asks follow-up questions, thereby increasing the possibility that the user obtains results that meet their needs.

[0187] In actual use, in order to avoid insufficient corpus after screening and the inability to feedback the results normally, after selecting the target corpus information from at least one answer corpus information based on the relevant question and answer data, the number of target corpus information can also be detected. If the number of target corpus information is greater than or equal to the preset number threshold, keyword extraction can be performed on the target corpus information based on the answer keywords; if the number of target corpus information is less than the preset number threshold, keyword extraction can be performed directly on at least one answer corpus information based on the answer keywords.

[0188] Step S3043: constructing follow-up question result data according to the result keywords and the related question and answer data.

[0189] In a specific implementation, constructing follow-up question result data based on result keywords and related question and answer data can be to use the related question and answer data as context information, make predictions based on the context information, determine the connection order and connecting words of each result keyword, and then connect the result keywords according to the connection order and connecting words, thereby generating follow-up question result data.

[0190] This embodiment searches in a preset knowledge base based on the follow-up question information to obtain at least one answer corpus information; extracts keywords from the answer corpus information to obtain result keywords; and constructs follow-up result data based on the result keywords and the related question and answer data. Since keyword extraction is performed on the answer corpus information after it is obtained, and follow-up result data is constructed based on the extracted result keywords and the related question and answer data, it is ensured that the final result data will not be too redundant, which is convenient for users to read, thereby improving the user experience.

[0191] In addition, an embodiment of the present invention further provides a storage medium, on which a result generation program is stored. When the result generation program is executed by a processor, the steps of the result generation method described above are implemented.

[0192] Reference Figure 7 , Figure 7It is a structural block diagram of the first embodiment of the result generating device of the present invention.

[0193] like Figure 7 As shown, the result generating device proposed in the embodiment of the present invention includes:

[0194] An acquisition module 10, used to acquire follow-up information;

[0195] A search module 20, used to search for relevant question and answer data corresponding to the follow-up question information;

[0196] The generating module 30 is used to generate the inquiry result data based on the inquiry information and the related question and answer data.

[0197] This embodiment obtains follow-up information; searches for relevant question and answer data corresponding to the follow-up information; and generates follow-up result data based on the follow-up information and the relevant question and answer data. After obtaining the follow-up information, the relevant question and answer data related to the follow-up information is searched, and the follow-up result data is further generated based on the follow-up information and the relevant question and answer data, so that the user does not need to modify the question or keywords by himself, but only needs to ask questions to obtain the results he needs, which reduces complexity and improves the user experience.

[0198] Furthermore, the generation module 30 is also used to obtain the information modification intention corresponding to the follow-up information; extract the target question information from the relevant question and answer data; construct the follow-up question information according to the information modification intention and the target question information; and generate the follow-up question result data based on the follow-up question information and the relevant question and answer data.

[0199] Furthermore, the generation module 30 is also used to extract keywords from the follow-up information to obtain a follow-up keyword set; perform weight analysis on the follow-up keyword set to obtain a keyword weight sequence; and match the keyword weight sequence in a preset knowledge base to determine the information modification intention corresponding to the follow-up information.

[0200] Furthermore, the generation module 30 is also used to obtain the question structure and information properties corresponding to the follow-up information; determine the weight ratio corresponding to each follow-up keyword in the follow-up keyword set according to the question structure and the information properties; sort the follow-up keywords in the follow-up keyword set based on the weight ratio to obtain a keyword weight sequence.

[0201] Furthermore, the generating module 30 is also used to determine the question modification position and the question modification indication based on the information modification intention; adjust the target question information according to the question modification position and the question modification indication to obtain follow-up question information.

[0202] Furthermore, the generation module 30 is also used to determine the problem attribution field and the problem modification instructions according to the information modification intention; match the problem attribution field and the problem modification instructions with the problem information corresponding to each of the related question and answer data to determine the matching degree corresponding to each of the problem information; and select the target problem information from the problem information corresponding to each of the related question and answer data based on the matching degree.

[0203] Furthermore, the generation module 30 is also used to determine the keywords to be modified in the target question information according to the question modification position; search for a keyword set corresponding to the question modification indication based on the keywords to be modified; extract replacement keywords from the keyword set; adjust the keywords to be modified in the target question information according to the replacement keywords to obtain follow-up question information.

[0204] Furthermore, the generation module 30 is also used to compare the question information corresponding to the relevant question and answer data with the target question information to determine the difference keywords; filter the keyword set according to the difference keywords to obtain a candidate keyword set; and extract replacement keywords from the candidate keyword set.

[0205] Furthermore, the generation module 30 is also used to search in a preset knowledge base based on the follow-up question information to obtain at least one answer corpus information; extract keywords from the answer corpus information to obtain result keywords; and construct follow-up question result data based on the result keywords and the related question and answer data.

[0206] Furthermore, the generating module 30 is further used to obtain question keywords corresponding to the follow-up question information; search for answer keywords corresponding to the question keywords; and perform keyword extraction on the answer corpus information according to the answer keywords to obtain result keywords.

[0207] Furthermore, the generation module 30 is also used to select target corpus information from the at least one answer corpus information according to the relevant question and answer data; and perform keyword extraction on the target corpus information according to the answer keywords to obtain result keywords.

[0208] Furthermore, the search module 20 is also used to obtain session identification data corresponding to the follow-up information; search for corresponding historical display results and historical question information according to the session identification data to obtain historical display data; search for question information corresponding to the historical display data according to the result response identifier corresponding to the historical display data; and construct relevant question and answer data based on the historical display data and the question information.

[0209] Furthermore, the acquisition module 10 is also used to acquire the follow-up question information input by the user through the interactive input box, or to acquire the follow-up question information input by the user through the follow-up question prompt button.

[0210] Furthermore, the interactive input box and / or the follow-up prompt button include at least one of the following situations:

[0211] The interactive input box is displayed independently;

[0212] The interactive input box and the interactive topic are displayed correspondingly;

[0213] Displayed in association with question and answer pairs;

[0214] Display in association with the question;

[0215] Display in association with the answer;

[0216] After receiving the user's operation of selecting page content, it is displayed in association with the selected content.

[0217] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0218] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0219] In addition, for technical details that are not described in detail in this embodiment, reference can be made to the result generation method provided in any embodiment of the present invention, and will not be repeated here.

[0220] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0221] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0222] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0223] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0224] The present application discloses A1, a result generation method, the result generation method comprising the following steps:

[0225] Get follow-up information;

[0226] Searching for relevant question and answer data corresponding to the follow-up question information;

[0227] Generate inquiry result data based on the inquiry information and the related question and answer data.

[0228] A2. The result generating method as described in A1, wherein the step of generating the follow-up question result data based on the follow-up question information and the related question and answer data comprises:

[0229] Obtaining the information modification intention corresponding to the inquiry information;

[0230] Extracting target question information from the relevant question-answer data;

[0231] Constructing follow-up question information according to the information modification intention and the target question information;

[0232] Generate follow-up question result data based on the follow-up question information and the related question and answer data.

[0233] A3. In the result generation method described in A2, the step of obtaining the information modification intention corresponding to the inquiry information comprises:

[0234] Extracting keywords from the follow-up question information to obtain a set of follow-up question keywords;

[0235] Performing weight analysis on the query keyword set to obtain a keyword weight sequence;

[0236] Matching is performed in a preset knowledge base according to the keyword weight sequence to determine the information modification intention corresponding to the follow-up information.

[0237] A4, as described in A3, the method for generating the result, wherein the step of performing weight analysis on the query keyword set to obtain a keyword weight sequence comprises:

[0238] Obtaining the question structure and information properties corresponding to the follow-up information;

[0239] Determine the weight ratio corresponding to each follow-up keyword in the follow-up keyword set according to the question structure and the information nature;

[0240] The follow-up question keywords in the follow-up question keyword set are sorted based on the weight ratio to obtain a keyword weight sequence.

[0241] A5. The result generation method as described in A2, wherein the step of constructing follow-up question information according to the information modification intention and the target question information comprises:

[0242] Determine the problem modification location and problem modification instructions based on the information modification intention;

[0243] The target question information is adjusted according to the question modification position and the question modification instruction to obtain follow-up question information.

[0244] A6. The result generation method as described in A2, wherein the step of extracting target question information from the relevant question and answer data comprises:

[0245] Determine the problem domain and problem modification instructions based on the information modification intention;

[0246] Matching the question domain and the question modification instruction with the question information corresponding to each of the relevant question and answer data to determine the matching degree corresponding to each of the question information;

[0247] Based on the matching degree, target question information is selected from the question information corresponding to each of the related question and answer data.

[0248] A7. The result generation method as described in A5, wherein the step of adjusting the target question information according to the question modification position and the question modification instruction to obtain the follow-up question information comprises:

[0249] Determining the keywords to be modified in the target question information according to the question modification position;

[0250] Searching for a keyword set corresponding to the problem modification instruction based on the to-be-modified keyword;

[0251] Extracting replacement keywords from the keyword set;

[0252] The keywords to be modified in the target question information are adjusted according to the replacement keywords to obtain follow-up question information.

[0253] A8. The result generating method as described in A7, wherein the step of extracting replacement keywords from the keyword set comprises:

[0254] Compare the question information corresponding to the relevant question and answer data with the target question information to determine the difference keywords;

[0255] Filtering the keyword set according to the difference keywords to obtain a candidate keyword set;

[0256] Extract replacement keywords from the candidate keyword set.

[0257] A9. The result generating method as described in A2, wherein the step of generating the follow-up question result data based on the follow-up question information and the related question and answer data comprises:

[0258] Searching in a preset knowledge base based on the follow-up question information to obtain at least one answer corpus information;

[0259] Perform keyword extraction on the answer corpus information to obtain result keywords;

[0260] Construct follow-up question result data according to the result keywords and the related question and answer data.

[0261] A10. The result generation method as described in A9, wherein the step of extracting keywords from the answer corpus information to obtain result keywords comprises:

[0262] Obtaining question keywords corresponding to the follow-up question information;

[0263] Find the answer keywords corresponding to the question keywords;

[0264] Keyword extraction is performed on the answer corpus information according to the answer keywords to obtain result keywords.

[0265] A11. The result generation method as described in A10, wherein the step of extracting keywords from the answer corpus information according to the answer keywords to obtain result keywords comprises:

[0266] Selecting target corpus information from the at least one answer corpus information according to the relevant question and answer data;

[0267] Keyword extraction is performed on the target corpus information according to the answer keywords to obtain result keywords.

[0268] A12. In the result generation method as described in A1, the step of searching for relevant question and answer data corresponding to the follow-up question information comprises:

[0269] Obtaining session identification data corresponding to the follow-up question information;

[0270] Searching for corresponding historical display results and historical question information according to the session identification data to obtain historical display data;

[0271] searching for question information corresponding to the historical display data according to the result response identifier corresponding to the historical display data;

[0272] Relevant question and answer data are constructed according to the historical display data and the question information.

[0273] A13. In the result generation method as described in any one of A1 to A12, the step of obtaining follow-up information comprises:

[0274] Obtain the follow-up information input by the user through the interactive input box, or obtain the follow-up information input by the user through the follow-up prompt button.

[0275] A14. In the result generation method as described in any one of A1 to A12, the interactive input box and / or the follow-up prompt button include at least one of the following situations:

[0276] The interactive input box is displayed independently;

[0277] The interactive input box and the interactive topic are displayed correspondingly;

[0278] Displayed in association with question and answer pairs;

[0279] Display in association with the question;

[0280] Display in association with the answer;

[0281] After receiving the user's operation of selecting page content, it is displayed in association with the selected content.

[0282] The present application also discloses B15, a result generating device, the result generating device comprising the following modules:

[0283] An acquisition module is used to obtain follow-up information;

[0284] A search module, used to search for relevant question and answer data corresponding to the follow-up question information;

[0285] A generation module is used to generate question result data based on the question information and the related question and answer data.

[0286] B16. The result generating device as described in B15, wherein the generating module is further used to obtain the information modification intention corresponding to the follow-up question information; extract the target question information from the relevant question and answer data; construct the follow-up question information according to the information modification intention and the target question information; and generate the follow-up question result data based on the follow-up question information and the relevant question and answer data.

[0287] B17. The result generating device as described in B16, wherein the generating module is further used to extract keywords from the follow-up information to obtain a follow-up keyword set; perform weight analysis on the follow-up keyword set to obtain a keyword weight sequence; and perform matching in a preset knowledge base according to the keyword weight sequence to determine the information modification intention corresponding to the follow-up information.

[0288] B18. The result generating device as described in B17, wherein the generating module is further used to obtain the question structure and information properties corresponding to the follow-up information; determine the weight ratio corresponding to each follow-up keyword in the follow-up keyword set according to the question structure and the information properties; sort the follow-up keywords in the follow-up keyword set based on the weight ratio to obtain a keyword weight sequence.

[0289] The present application also discloses C19, a result generating device, which includes: a processor, a memory, and a result generating program stored in the memory and executable on the processor, wherein the result generating program implements the steps of the result generating method described above when executed by the processor.

[0290] The present application also discloses D20, a computer-readable storage medium, on which a result generation program is stored, and when the result generation program is executed, the steps of the result generation method described above are implemented.

Claims

1. A result generation method, characterized in that: The result generation method comprises the following steps: Get follow-up information; Searching for relevant question and answer data corresponding to the follow-up question information; Generate inquiry result data based on the inquiry information and the related question and answer data.

2. The result generation method according to claim 1, characterized in that: The step of generating the inquiry result data based on the inquiry information and the related question and answer data includes: Obtaining the information modification intention corresponding to the inquiry information; Extracting target question information from the relevant question-answer data; Constructing follow-up question information according to the information modification intention and the target question information; Generate follow-up question result data based on the follow-up question information and the related question and answer data.

3. The result generation method according to claim 2, characterized in that: The step of obtaining the information modification intention corresponding to the inquiry information includes: Extracting keywords from the follow-up question information to obtain a set of follow-up question keywords; Performing weight analysis on the query keyword set to obtain a keyword weight sequence; Matching is performed in a preset knowledge base according to the keyword weight sequence to determine the information modification intention corresponding to the follow-up information.

4. The result generation method according to claim 3, characterized in that: The step of performing weight analysis on the query keyword set to obtain a keyword weight sequence includes: Obtaining the question structure and information properties corresponding to the follow-up information; Determine the weight ratio corresponding to each follow-up keyword in the follow-up keyword set according to the question structure and the information nature; The follow-up question keywords in the follow-up question keyword set are sorted based on the weight ratio to obtain a keyword weight sequence.

5. The result generation method according to claim 2, characterized in that: The step of constructing follow-up question information according to the information modification intention and the target question information includes: Determine the problem modification location and problem modification instructions based on the information modification intention; The target question information is adjusted according to the question modification position and the question modification instruction to obtain follow-up question information.

6. The result generation method according to claim 2, characterized in that: The step of extracting target question information from the relevant question and answer data comprises: Determine the problem domain and problem modification instructions based on the information modification intention; Matching the question domain and the question modification instruction with the question information corresponding to each of the relevant question and answer data to determine the matching degree corresponding to each of the question information; Based on the matching degree, target question information is selected from the question information corresponding to each of the related question and answer data.

7. The result generation method according to claim 5, characterized in that: The step of adjusting the target question information according to the question modification position and the question modification instruction to obtain follow-up question information includes: Determining the keywords to be modified in the target question information according to the question modification position; Searching for a keyword set corresponding to the problem modification instruction based on the to-be-modified keyword; Extracting replacement keywords from the keyword set; The keywords to be modified in the target question information are adjusted according to the replacement keywords to obtain follow-up question information.

8. A result generating device, characterized in that: The result generating device comprises the following modules: An acquisition module is used to obtain follow-up information; A search module, used to search for relevant question and answer data corresponding to the follow-up question information; A generation module is used to generate question result data based on the question information and the related question and answer data.

9. A result generating device, characterized in that: The result generating device comprises: a processor, a memory, and a result generating program stored in the memory and executable on the processor, wherein the result generating program implements the steps of the result generating method according to any one of claims 1 to 7 when executed by the processor.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a result generation program, which, when executed, implements the steps of the result generation method according to any one of claims 1 to 7.

Images