Chart type recommendation method and device for user questions and medium
By performing keyword analysis and business data matching on user question content, combining rule base and machine learning model, we recommend suitable chart types, which solves the problem of low efficiency and accuracy of intelligent chart recommendation systems, and achieves efficient and accurate chart types Recommended and personalized display.
Patent Information
- Application Number
- CN202411042779.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-15
AI Technical Summary
The existing intelligent chart recommendation system is low in efficiency and accuracy when recommending chart types, making it difficult to meet users' personalized needs, especially when complex business scenarios and diverse data cannot accurately analyze and recommend appropriate chart types.
By performing keyword analysis on user's question content, predicting the user's expected chart display category, combining the field type combination of business data, using a pre-built rule library and machine learning model for matching and scoring, the most suitable chart type is recommended.
It improves the efficiency and accuracy of chart type recommendations, can better meet user needs, provide efficient and accurate data analysis results, and supports user personalized preferences and system updates.
Smart Images

Figure CN118964738A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a method, device and medium for recommending chart types in response to user questions. Background Art
[0002] With the rapid development of big data and artificial intelligence technology, intelligent recommendation systems have gradually become one of the core technologies in various fields. Especially in the fields of e-commerce, media content recommendation, personalized advertising, etc., intelligent recommendation systems are increasingly used and play a vital role. The intelligent chart recommendation system is a branch of the intelligent recommendation system. It aims to automatically recommend appropriate chart types based on the user's data characteristics and needs, helping users better understand and display data.
[0003] At present, there are intelligent chart recommendation systems based on big data and machine learning. These systems usually include modules such as data analysis, feature extraction, and recommendation algorithms, which can automatically recommend suitable chart types based on data files uploaded by users.
[0004] However, the recommendation algorithm is still relatively simple, and can only make recommendations based on some basic rules and statistical information. This results in the recommendation results often lacking personalization and depth, and it is difficult to meet the actual needs of users. In addition, most intelligent chart recommendation systems cannot combine and apply business data, data models and other feature information. When dealing with complex business scenarios and diverse data, the system cannot accurately parse and recommend appropriate chart types. This ultimately leads to low efficiency and accuracy in recommending chart types for user questions. Summary of the invention
[0005] The embodiments of the present application provide a method, device and medium for recommending chart types in response to user questions, which are used to solve the problem of low efficiency and accuracy in recommending chart types in response to user questions.
[0006] The present application embodiment adopts the following technical solutions:
[0007] On the one hand, an embodiment of the present application provides a method for recommending chart types for user questions, the method comprising: performing keyword analysis on the user's question content to obtain a keyword combination; retrieving a target business data table of the question content based on the keyword combination; determining a field type combination of the target business data table based on the table structure description information of the target business data table; performing intent analysis on the keyword combination to predict the user's expected chart display category; the expected chart display category includes descriptive charts, comparative charts, and analytical charts; in a pre-constructed rule library, matching the expected chart display category with the field type combination to obtain a target rule; the rule library includes multiple rules for different expected chart display categories, each rule being used to describe a different set of chart types corresponding to different field type combinations; scoring the chart type set of the target rule to obtain a recommended chart type.
[0008] In one example, retrieving the target business data table of the question content based on the keyword combination specifically includes: obtaining table structure description information of each business data table in a business data table database; the table structure description information includes table name, field name and field type; matching each keyword in the keyword combination with the table structure description information of each business data table to obtain the matching degree of each business data table; and determining the business data table with the highest matching degree as the target business data table.
[0009] In one example, the intent analysis of the keyword combination to predict the user's expected chart display category specifically includes: obtaining a sample keyword combination and the expected chart display category of the sample keyword combination; using the sample keyword combination as a sample input and the expected chart display category of the sample keyword as a sample label to train an initial classification model to obtain an intent analysis classification model; inputting the keyword combination into the intent analysis classification model to obtain the expected chart display category.
[0010] In one example, in a pre-constructed rule library, the expected chart display category is matched with the field type combination to obtain a target rule, which specifically includes: in a pre-constructed rule library, retrieving a rule set of the expected chart display category; in the rule set, matching the field type combination to obtain a target rule.
[0011] In one example, scoring the chart type set of the target rule to obtain a recommended chart type specifically includes: obtaining a sample chart recommendation set and a sample field type combination, and a recommendation score for each chart type in the sample chart recommendation set; using the sample chart recommendation set and the sample field type combination as sample inputs, and the recommendation score for each chart type as a sample label, training an initial neural network model to obtain a recommendation scoring network model; inputting the field type combination and the chart type set into the recommendation scoring network model to obtain a recommendation score for each chart type; and determining the chart type with the highest recommendation score as the recommended chart type.
[0012] In one example, after scoring the chart type set of the target rule to obtain a recommended chart type, the method further includes: converting the target business data table to obtain a business data chart of the recommended chart type; obtaining the user's preference style; adjusting the business data chart according to the preference style, and recommending the adjusted business data chart to the user.
[0013] In one example, the keyword analysis of the user's question content to obtain the keyword combination specifically includes: obtaining sample question content and the keyword combination of the sample question content; using the sample question content as a sample input, using the keyword combination of the sample question content as a sample label, training an initial semantic neural network model to obtain a semantic network model; and inputting the question content into the semantic network model to obtain the keyword combination.
[0014] In one example, after adjusting the business data chart according to the preference style and recommending the adjusted business data chart to the user, the method further includes: converting the adjusted business data chart into an interactive chart; receiving an editing request from the user to update the adjusted business data chart when the user adjusts the interactive chart.
[0015] On the other hand, an embodiment of the present application provides a device for recommending chart types in response to user questions, comprising: 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 any of the above-described methods for recommending chart types in response to user questions.
[0016] On the other hand, an embodiment of the present application provides a non-volatile computer storage medium for recommending chart types for user questions, storing computer executable instructions, and the computer executable instructions can execute any of the above-mentioned methods for recommending chart types for user questions.
[0017] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:
[0018] It is able to perform intent analysis on the keywords in the question content to obtain the user's expected chart display category, and then combine the expected chart display category with the field type combination of business data to match the appropriate chart type candidate set, and then select the optimal chart type for recommendation, thereby greatly improving the efficiency and accuracy of data analysis, and achieving efficient and accurate recommendation of the most suitable chart type that meets user needs. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solution of the present application, some embodiments of the present application will be described in detail below in conjunction with the accompanying drawings, in which:
[0020] Figure 1 A flowchart of a method for recommending chart types in response to user questions provided in an embodiment of the present application;
[0021] Figure 2 A schematic diagram of the structure of a device for recommending chart types in response to user questions provided in an embodiment of the present application. DETAILED DESCRIPTION
[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0023] Some embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0024] Figure 1 A flowchart of a method for recommending chart types for user questions provided in an embodiment of the present application. The method can be applied to different business fields, such as Internet financial business field, e-commerce business field, instant messaging business field, game business field, official business field, etc. The process can be executed by a computing device in the corresponding field, and some input parameters or intermediate results in the process allow manual intervention and adjustment to help improve accuracy.
[0025] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.
[0026] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.
[0027] Figure 1 The process in includes the following steps:
[0028] S101: Perform keyword analysis on the user's question content to obtain a keyword combination.
[0029] In some embodiments of the present application, the process of keyword analysis is as follows:
[0030] First, obtain sample question content and keyword combinations of the sample question content. Then, use the sample question content as sample input, use the keyword combinations of the sample question content as sample labels, train the initial semantic neural network model, and obtain a semantic network model. Finally, input the question content into the semantic network model to obtain the keyword combination.
[0031] S102: Retrieve a target business data table of the question content according to the keyword combination.
[0032] In some embodiments of the present application, the process of retrieving the target business data table of the query content is as follows:
[0033] First, in the business data table database, obtain the table structure description information of each business data table. The table structure description information includes the table name, field name and field type. Then, match each keyword in the keyword combination with the table structure description information of each business data table to obtain the matching degree of each business data table. Then, determine the business data table with the highest matching degree as the target business data table.
[0034] It should be noted that the higher the matching keywords, the higher the matching degree.
[0035] S103: Determine a field type combination of the target business data table according to the table structure description information of the target business data table.
[0036] It should be noted that the field type combination can be used to describe different field types and the quantity of each field type.
[0037] S104: performing intention analysis on the keyword combination to predict the user's desired chart display category; the desired chart display category includes descriptive charts, comparative charts, and analytical charts.
[0038] It should be noted that descriptive charts are used to display the basic situation of data, such as average, median, etc. Comparative charts are used to compare the data differences between different groups, such as bar charts, line charts, etc. Analytical charts are used to deeply analyze the relationship and trend between data, such as scatter plots, regression analysis charts, etc.
[0039] In some embodiments of the present application, the process of performing intent analysis on a keyword combination is as follows:
[0040] First, obtain sample keyword combinations and the expected chart display categories of the sample keyword combinations. Then, use the sample keyword combinations as sample inputs and the expected chart display categories of the sample keywords as sample labels to train the initial classification model and obtain the intent analysis classification model. Finally, input the keyword combinations into the intent analysis classification model to obtain the expected chart display categories.
[0041] For example, for the user's question "Compare sales data of different products", the keywords "compare" and "sales data" can be extracted. The intent analysis classification model can predict that the user's desired chart display category is a comparative chart, because the keyword "compare" implies that the user wants to compare different data.
[0042] For example, if the question mentions "proportion" or "ratio", it is recommended to use descriptive charts such as pie charts or doughnut charts. If the question mentions "trend" or "growth", it is recommended to use comparative charts such as bar charts or line charts to reflect trends. If the question mentions "relationship" or "correlation", it is recommended to use analytical charts.
[0043] It should be noted that the initial classification model can be set according to actual needs, such as a naive Bayes classifier, a support vector machine or a neural network, etc. For example, the structure of the neural network is defined, including an input layer, a hidden layer and an output layer, and the neural network structure is trained.
[0044] S105: In a pre-built rule library, the expected chart display category is matched with the field type combination to obtain a target rule; the rule library includes multiple rules for different expected chart display categories, each rule is used to describe a different chart type set corresponding to a different field type combination.
[0045] In some embodiments of the present application, the rule base is formulated based on historical experience and expert knowledge, which defines the data feature conditions applicable to different chart types. For example, for comparative charts, one rule is: when the data has one and only one date type field, one or more numeric type fields, and no other character type fields, it is recommended to use a line chart. For descriptive charts, one rule is: when there are two and only two fields, one of which is a character type and one is a numeric type, and the amount of data does not exceed 10, it is recommended to use a pie chart, and when the number exceeds 10, it is recommended to use a bar chart. For analytical charts, one rule is: when there are three and only three fields, one of which is a character type and two fields are numeric types, it is recommended to use a dual-value axis scatter chart.
[0046] The process of matching the expected chart display category with the field type combination is as follows: in the pre-built rule library, the rule set of the expected chart display category is retrieved. Then, in the rule set, the field type combination is matched to obtain the target rule.
[0047] It should be noted that there may be multiple target rules, and the chart type set of the target rule includes the chart type sets of multiple rules.
[0048] S106: Score the chart type set of the target rule to obtain a recommended chart type.
[0049] In some embodiments of the present application, a set of chart types of target rules is scored and sorted by a pre-trained machine learning model.
[0050] Based on this, first, we obtain the sample chart recommendation set and sample field type combination, as well as the recommendation score of each chart type in the sample chart recommendation set. Then, we use the sample chart recommendation set and sample field type combination as sample input, and the recommendation score of each chart type as sample label to train the initial neural network model and obtain the recommendation score network model.
[0051] Thus, the field type combination and the chart type set are input into the recommendation score network model to obtain the recommendation score of each chart type. The chart type with the highest recommendation score is determined as the recommended chart type.
[0052] It should be noted that the higher the score, the more suitable the chart type is for the current question content. The chart type with the highest score is selected as the optimal chart type.
[0053] In some embodiments of the present application, users are supported to set personalized preferences and apply these preferences to recommended charts. Users can select style options such as color, font, and visibility of chart labels through the GUI and save them as default settings or optional items. When the system generates a recommended chart, it will make corresponding style adjustments based on the user's personalized preferences. In addition, the user preference module also supports interactive adjustment functions, allowing users to fine-tune the generated charts to meet specific needs.
[0054] Based on this, the target business data table is converted to obtain a business data chart of the recommended chart type. Then, the user's preferred style is obtained. Finally, the business data chart is adjusted according to the preferred style, and the adjusted business data chart is recommended to the user.
[0055] Further, the adjusted business data chart is converted into an interactive chart. An editing request from a user is received, so that when the user adjusts the interactive chart, the adjusted business data chart is updated.
[0056] That is, the recommended charts are presented to users as interactive Canvas-based charts that are already available in the current product, and the editing, saving and sharing functions are provided. Users can view the recommended charts through the GUI and edit them, such as adjusting the axis range, adding data labels, changing colors, changing fonts, etc. Once the user is satisfied with the chart, they can choose to save it as an image or PDF file for subsequent use or sharing with others.
[0057] It should be noted that although the embodiments of the present application are based on Figure 1 Steps S101 to S106 are described in sequence, but this does not mean that steps S101 to S106 must be performed in a strict order. Figure 1 The order shown in the figure is to introduce and explain step S101 to step S106 in sequence, in order to facilitate those skilled in the art to understand the technical solution of the embodiment of the present application. In other words, in the embodiment of the present application, the order between step S101 to step S106 can be appropriately adjusted according to actual needs.
[0058] pass Figure 1 The method can analyze the intent of the keywords in the question content, so as to obtain the user's expected chart display category, and then match the expected chart display category with the field type combination of business data to match the appropriate chart type candidate set, and then select the optimal chart type for recommendation, thereby greatly improving the efficiency and accuracy of data analysis, and realizing the efficient and accurate recommendation of the most suitable chart type that meets user needs to users.
[0059] Furthermore, it supports the setting of user personalized preferences, and recommends icon display types and display styles that conform to user habits and aesthetics based on user preferences, which is more humane.
[0060] Furthermore, it supports the update and expansion of rule sets and machine learning models, enables hot deployment updates, and improves system availability.
[0061] More intuitively, the following is an example of visual analysis of a company's product sales data provided by the embodiment of the present application. Assume that the preparation work before the intelligent chart type recommendation has been completed, such as the product sales data model has been maintained and trained.
[0062] First, the user inputs "analysis of sales of different products in various regions last year" by voice or text. Then, the question content is analyzed for keywords to obtain the keyword combination of "last year", "various regions", "different products", and "sales".
[0063] Then, in the business data table database, the target business data table is retrieved, as shown in Table 1.
[0064] Table 1
[0065] areaname productname Salesvolume North China Peanut Oil 200 North China Soybean Oil 100 …… …… …… northwest Peanut Oil 100 northwest Soybean Oil 150 …… …… ……
[0066] In addition, the semantic description information DataSchemas of the sales data corresponding model includes the original field name, field alias, field type, display format, decimal places, measurement unit, etc., as shown in Table 2.
[0067] Table 2
[0068]
[0069] It can be seen that the field type combination is: String, String, Decimal, and the number of fields is 3.
[0070] Based on this, the data features of the question content may include: Number of columns: 3 (region name, product name, sales). Data type: region name (character type), product name (character type), sales (numeric type). Data range: minimum and maximum sales value. Data distribution: the distribution of sales.
[0071] Then, we conduct intent analysis on the keyword combination and predict that the user's desired chart display category is a comparative chart. For example, "last year" refers to the time dimension and is used for filtering, "regions" and "different products" refer to the classification dimension, and "sales" refers to the numerical indicator. Combining this information, we can preliminarily judge that the user wants to conduct a "classification comparison" type of analysis.
[0072] Then, in the pre-built rule library, the expected chart display category and field type combination are matched to obtain the target rule, and the chart type set of the target rule is: bar chart, line chart, stacked bar chart, and stacked area chart.
[0073] Then, the chart type set of the target rule is scored as follows: line chart: 80 points, bar chart: 90 points, stacked bar chart: 40 points, stacked area chart: 30 points. Finally, the optimal chart type is the bar chart. That is, the recommended chart type for business data is the bar chart.
[0074] Based on the same idea, some embodiments of the present application also provide devices and non-volatile computer storage media corresponding to the above methods.
[0075] Figure 2 A schematic diagram of a diagram type recommendation device for user questions provided in an embodiment of the present application includes:
[0076] at least one processor; and,
[0077] a memory communicatively connected to the at least one processor; wherein,
[0078] 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 any one of the above-mentioned methods for recommending a chart type for a user question.
[0079] Some embodiments of the present application provide a non-volatile computer storage medium for recommending chart types for user questions, which stores computer executable instructions capable of executing any of the above-described methods for recommending chart types for user questions.
[0080] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0081] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.
[0082] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0083] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0084] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0085] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0086] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0087] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0088] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0089] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0090] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the technical principle of the present application should all fall within the protection scope of the present application.
Claims
1. A method for recommending chart types based on user questions, characterized in that: The method comprises: Perform keyword analysis on the user's question content to obtain keyword combinations; Retrieving a target business data table of the question content according to the keyword combination; Determine the field type combination of the target business data table according to the table structure description information of the target business data table; Performing intention analysis on the keyword combination to predict the user's desired chart display category; the desired chart display category includes descriptive charts, comparative charts, and analytical charts; In a pre-built rule library, the expected chart display category is matched with the field type combination to obtain a target rule; the rule library includes multiple rules for different expected chart display categories, each rule is used to describe a different chart type set corresponding to a different field type combination; The chart type set of the target rule is scored to obtain a recommended chart type.
2. The method according to claim 1, characterized in that The step of retrieving the target business data table of the question content according to the keyword combination specifically includes: In the business data table database, obtaining table structure description information of each business data table; the table structure description information includes table name, field name and field type; Matching each keyword in the keyword combination with the table structure description information of each business data table to obtain a matching degree of each business data table; The business data table with the highest matching degree is determined as the target business data table.
3. The method according to claim 1, characterized in that: The performing intention analysis on the keyword combination to predict the user's desired chart display category specifically includes: Acquire a sample keyword combination and a desired chart display category of the sample keyword combination; The sample keyword combination is used as a sample input, the expected chart display category of the sample keyword is used as a sample label, and an initial classification model is trained to obtain an intent analysis classification model; The keyword combination is input into the intention analysis classification model to obtain the desired chart display category.
4. The method according to claim 1, characterized in that: In the pre-built rule library, the expected chart display category is matched with the field type combination to obtain the target rule, which specifically includes: Retrieving a rule set of the desired chart display category from a pre-built rule library; In the rule set, the field type combination is matched to obtain a target rule.
5. The method according to claim 1, characterized in that Scoring the chart type set of the target rule to obtain the recommended chart type specifically includes: Obtain a sample chart recommendation set and a sample field type combination, as well as a recommendation score for each chart type in the sample chart recommendation set; The sample chart recommendation set and the sample field type are combined as sample input, and the recommendation score of each chart type is used as a sample label to train the initial neural network model to obtain a recommendation score network model; Inputting the field type combination and the chart type set into a recommendation scoring network model to obtain a recommendation score for each chart type; The chart type with the highest recommendation score is determined as the recommended chart type.
6. The method according to claim 1, characterized in that After scoring the chart type set of the target rule to obtain the recommended chart type, the method further includes: Converting the target business data table to obtain a business data chart of a recommended chart type; Obtaining the user's preferred style; The business data chart is adjusted according to the preference style, and the adjusted business data chart is recommended to the user.
7. The method according to claim 6, characterized in that After adjusting the business data chart according to the preference pattern and recommending the adjusted business data chart to the user, the method further includes: Converting the adjusted business data chart into an interactive chart; An editing request from a user is received, so that when the user adjusts the interactive chart, the adjusted business data chart is updated.
8. The method according to claim 1, characterized in that The keyword analysis of the user's question content to obtain a keyword combination specifically includes: Obtaining sample question content and keyword combinations of the sample question content; The sample question content is used as a sample input, and the keyword combination of the sample question content is used as a sample label to train the initial semantic neural network model to obtain a semantic network model; The question content is input into the semantic network model to obtain a keyword combination.
9. A device for recommending chart types in response to user questions, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for recommending chart types for user questions as described in any one of claims 1 to 8.
10. A non-volatile computer storage medium for recommending chart types for user questions, storing computer executable instructions, characterized in that: The computer executable instructions can execute the method for recommending chart types in response to user questions as described in any one of claims 1 to 8.
Citation Information
Patent Citations
Task-oriented visual recommendation method and device
CN112749224A
Visual recommendation method and device, equipment and storage medium
CN113761334A
Method and device for obtaining recommended chart type, electronic equipment and storage medium
CN114595272A
Method for intelligently identifying user search intention and visually displaying element search result
CN117093708A
Chart generation method and device, equipment and storage medium
CN117851457A
Cited By
Field rule matching recommendation method and device based on multi-dimensional feature fusion
CN120873037A
Field rule matching recommendation method and device based on multi-dimensional feature fusion
CN120873037B
