A / B testing data analysis method and apparatus based on large model intelligent agents

Abstract

A method and apparatus for A / B testing data analysis based on a large-model intelligent agent are disclosed. The method includes: displaying an intelligent interactive page associated with the intelligent agent, which performs joint analysis of different data indicators using a large model; in response to inputting at least two data indicators on the intelligent interactive page, identifying at least two data indicators as target data indicators to be jointly analyzed; and in response to a joint analysis request triggered on the intelligent interactive page for the target data indicators, displaying the data analysis results for the joint analysis request. This allows for automatic data analysis through relatively simple input operations, simplifying the data analysis process and improving efficiency. Furthermore, since it supports the input of data indicators and the joint analysis of different data indicators, it allows for customized, targeted analysis of different data indicators according to user needs, thereby improving the flexibility of data analysis and the user experience.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a method and apparatus for A / B testing data analysis based on a large model intelligent agent. Background Technology

[0002] With the advent of the big data era, data in business scenarios has become increasingly diverse and complex. To extract meaningful information from this data, data analysis is generally required. For example, in content delivery scenarios, A / B experiments can be conducted, and then the experimental data from the A / B experiments can be compared and analyzed to derive content delivery strategies.

[0003] However, in related technologies, when analyzing data in business scenarios, a single indicator group is generally used as the analysis dimension, and all indicators in the indicator group are drilled down as a whole, which has certain limitations. Summary of the Invention

[0004] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, this disclosure provides an A / B testing data analysis method based on a large model intelligent agent, the method comprising:

[0006] Displays an intelligent interactive page associated with the intelligent agent, which is used to perform joint analysis of different data indicators through a large model;

[0007] In response to inputting at least two data metrics on the intelligent interactive page, the at least two data metrics are identified as target data metrics to be jointly analyzed.

[0008] In response to a joint analysis request for the target data metric triggered on the smart interaction page, the data analysis results for the joint analysis request are displayed on the smart interaction page.

[0009] Secondly, this disclosure provides a data analysis apparatus, the data analysis apparatus comprising:

[0010] The first display module is used to display the intelligent interactive page associated with the intelligent agent, which is used to perform joint analysis of different data indicators through a large model;

[0011] A determination module is configured to determine the at least two data indicators as target data indicators to be jointly analyzed in response to an input operation on the intelligent interactive page.

[0012] The second display module is used to display data analysis results for the joint analysis request triggered on the intelligent interaction page in response to the joint analysis request for the target data indicator.

[0013] Thirdly, this disclosure provides a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of the method described in the first aspect.

[0014] Fourthly, this disclosure provides an electronic device, comprising:

[0015] A storage device on which computer programs are stored;

[0016] A processing device for executing the computer program in the storage device to implement the steps of the method in the first aspect.

[0017] Fifthly, this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.

[0018] The above technical solution allows users to input target data indicators for joint analysis and their joint analysis requirements on an intelligent interactive page. A large model can then automatically analyze these requirements, yielding data analysis results tailored to those needs. This simplifies the data analysis process and improves efficiency by enabling automated data analysis through relatively simple input. Furthermore, because this solution supports the input of data indicators and allows for joint analysis of different indicators, users can customize targeted analyses for different data indicators based on their needs, thereby enhancing the flexibility of data analysis and improving the user experience.

[0019] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0020] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale. In the drawings:

[0021] Figure 1This is a flowchart illustrating an A / B test data analysis method based on a large model intelligent agent according to an exemplary embodiment of the present disclosure;

[0022] Figure 2 This is a schematic diagram illustrating the input of a data indicator according to an exemplary embodiment of the present disclosure;

[0023] Figure 3 This is a schematic diagram illustrating an analysis task script according to an exemplary embodiment of the present disclosure;

[0024] Figure 4 This is a schematic diagram illustrating a content reference according to an exemplary embodiment of the present disclosure;

[0025] Figure 5 This is a schematic diagram illustrating an interactive link graph according to an exemplary embodiment of the present disclosure;

[0026] Figure 6 This is a schematic diagram illustrating the style switching of an intelligent interactive page according to an exemplary embodiment of the present disclosure;

[0027] Figure 7 This is a structural block diagram of an A / B test data analysis device based on a large model intelligent agent, according to an exemplary embodiment of the present disclosure;

[0028] Figure 8 This is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0029] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0030] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0031] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0032] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0033] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0034] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0035] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0036] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0037] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0038] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0039] Meanwhile, it is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0040] As mentioned in the background section, in related technologies, when performing data analysis on data in business scenarios, a single indicator group is generally used as the analysis dimension to perform overall analysis on all indicators in the indicator group, which has certain limitations.

[0041] For example, in a content delivery scenario, multiple different content delivery strategies can be provided, such as content delivery strategy A and content delivery strategy B. In order to determine the optimal content delivery strategy from content delivery strategy A and content delivery strategy B, an A / B experiment can be set up. That is, for the target content to be delivered, a part of the target content to be delivered is delivered based on content delivery strategy A, and another part of the target content to be delivered is delivered based on content delivery strategy B. Finally, the optimal content delivery strategy is determined by comparing the experimental data (i.e., the delivery data).

[0042] However, many data analysis tools in related technologies are built on the concept of a single indicator group, meaning they can only perform overall drill-down or holistic analysis on the entire indicator group. But in real-world business scenarios, users' data analysis needs are often more complex and diverse, potentially requiring the combination of data indicators from different indicator groups. For example, since different businesses may have different key indicators and influencing factors, and launching a new business may impact other businesses, users need to focus on specific indicators within different indicator groups for different businesses to comprehensively assess the business's performance and potential impact.

[0043] Therefore, to achieve cross-indicator group data analysis, related technologies generally rely on manual methods to view and extract data indicators from different indicator groups, and then perform manual analysis based on the extracted data indicators. When conducting indicator group data analysis in this way, users need to switch between different data systems or data analysis tools and manually organize and compare the data in each indicator group, which results in complex data analysis operations and low analysis efficiency.

[0044] In view of this, the present disclosure provides a method and apparatus for A / B testing data analysis based on large model intelligent agents to solve the above-mentioned technical problems.

[0045] The embodiments of this disclosure will be further explained below with reference to the accompanying drawings.

[0046] Figure 1 This is a flowchart illustrating an A / B testing data analysis method based on a large model agent according to an exemplary embodiment of this disclosure, with reference to... Figure 1The A / B testing data analysis method based on large model agents may include the following steps:

[0047] S101: Displays the intelligent interaction page associated with the intelligent agent, which is used to perform joint analysis of different data indicators through a large model.

[0048] For example, when the data analysis platform is opened, the homepage of the data analysis platform can be displayed, and the analysis module "Data Analysis" for data analysis can be displayed on the homepage. When the analysis module "Data Analysis" is triggered by clicking or other operations, the intelligent interaction page associated with the intelligent agent can be displayed, such as... Figure 2 As shown, the intelligent agent is the XX intelligent assistant in the diagram. Alternatively, when the analysis module "Data Analysis" is triggered by clicking or other operations, the data analysis page can be displayed, and the intelligent agent's identifier can be displayed on the data analysis page. When the intelligent agent's identifier is triggered by clicking or other operations, the intelligent interaction page associated with the intelligent agent can be displayed. Alternatively, when the analysis module "Data Analysis" is triggered by clicking or other operations, the data analysis page can be displayed, and data indicator information and a function entry point for triggering the large model to analyze the data indicator information can be displayed on the data analysis page. When the function entry point is triggered by clicking or other operations, the intelligent interaction page associated with the intelligent agent can be displayed. Of course, the intelligent interaction page associated with the intelligent agent can also be triggered and displayed through other means, and this embodiment of the disclosure does not impose any limitations on this.

[0049] In this embodiment, joint analysis of different data indicators can be performed on at least two data indicators in the same data indicator group, or on at least two data indicators in different data indicator groups, or other methods. This disclosure does not impose any restrictions on these methods.

[0050] S102: In response to inputting at least two data metrics on the smart interactive page, identify at least two data metrics as target data metrics to be jointly analyzed.

[0051] In this embodiment, the input operation for at least two data indicators can be performed by the user manually inputting the data indicators through an external input device, such as by inputting the data indicators via a keyboard, thereby obtaining the target data indicator. Alternatively, a selection control for selecting data indicators can be pre-displayed on the intelligent interaction page. When the selection control is triggered by clicking or other operations, an indicator page can be displayed, showing different data indicators. When the indicator page is triggered by clicking or other operations, the target data indicator is obtained. Of course, data indicators can also be input in other ways, and this disclosure embodiment does not impose any limitations on this.

[0052] S103: In response to a joint analysis request for a target data indicator triggered on the smart interaction page, display the data analysis results for the joint analysis request on the smart interaction page.

[0053] In this embodiment, the joint analysis request for the target data indicator triggered on the intelligent interaction page can be triggered through a conversation, or after the target data indicator is determined, a preset joint analysis request for the target data indicator can be displayed on the intelligent interaction page. When the preset joint analysis request is triggered by an operation such as clicking or dragging, the joint analysis request is triggered on the intelligent interaction page. Of course, other methods can also be used to trigger the joint analysis request on the intelligent interaction page, and this embodiment does not impose any limitations on this. When the joint analysis request is triggered through a conversation, it can be triggered by voice input, or by inputting the joint analysis request in the form of natural language text in a text input box. Of course, other conversation methods can also be used, and this embodiment does not impose any limitations on this.

[0054] The above technical solution allows users to input target data indicators for joint analysis and their joint analysis requirements on an intelligent interactive page. A large model can then automatically analyze these requirements, yielding data analysis results tailored to those needs. This simplifies the data analysis process and improves efficiency by enabling automated data analysis through relatively simple input. Furthermore, because this solution supports the input of data indicators and allows for joint analysis of different indicators, users can customize targeted analyses for different data indicators based on their needs, thereby enhancing the flexibility of data analysis and improving the user experience.

[0055] To facilitate understanding of the A / B testing data analysis method based on large model agents provided in this disclosure, the possible implementation methods in this disclosure are described below.

[0056] In possible ways, in response to inputting at least two data metrics on a smart interactive page, identifying at least two data metrics as target data metrics to be jointly analyzed may include:

[0057] In response to shortcut commands triggered on the intelligent interaction page, different data indicators are displayed; in response to the selection operation of at least two data indicators among different data indicators, the at least two data indicators corresponding to the selection operation are determined as the target data indicators to be jointly analyzed.

[0058] In this embodiment, the shortcut command can be determined according to the actual situation, and this disclosure does not impose any restrictions on it. For example, the shortcut command can be a preset character, such as the character "#", so that when the character "#" is entered on the smart interactive page, different data indicators can be displayed. For example, the shortcut command can be a preset voice command, such as "select data indicator", so that when the smart interactive page detects the voice command "select data indicator", different data indicators can be displayed. For example, the shortcut command can be a shortcut key, such as the shortcut key "Ctrl+Q", so that when the smart interactive page detects that an external input device triggers the shortcut key "Ctrl+Q", different data indicators can be displayed.

[0059] In this embodiment, different data indicators can be determined according to the actual situation, and this disclosure does not impose any restrictions on them. For example, different data indicators can be different data indicators in the same data indicator group, or different data indicators in different data indicator groups, or of course, other types, and this disclosure does not impose any restrictions on them.

[0060] For example, the shortcut can be the character "#". The smart interactive page can include a content display area and a content input area. The content input area displays a "Send" control for sending content from the content input area to the content display area. Therefore, when the character "#" is entered in the content input area, a drop-down panel can be displayed, showing multiple different data indicator groups. When "Data Indicator Group 2" is triggered by clicking or other operations, multiple individual data indicators corresponding to "Data Indicator Group 2" can be displayed. When "Data Indicator 2" and "Data Indicator 3" are triggered by clicking or other operations, "Data Indicator 2" and "Data Indicator 3" can be identified as target data indicators and displayed in the content input area, such as... Figure 2 As shown.

[0061] It should be understood that in business scenarios, there are dozens to hundreds of data metrics. If users manually input these metrics, the sheer volume can lead to inaccurate memorization, requiring repeated verification and re-entry, increasing user complexity. In this embodiment, however, different data metrics can be displayed when a shortcut is triggered. Users can then select the appropriate metrics for joint analysis based on their needs, reducing the need for repeated manual input and improving analysis efficiency and user experience. Furthermore, since the same data metric can exist in different data metric groups, to facilitate quick and accurate retrieval and reduce redundant searches and confusion, when selecting metrics via shortcuts, the data metric group can be displayed first after triggering the shortcut, followed by the data metrics within that group. This improves the efficiency and accuracy of metric selection, reduces user complexity, and further enhances the user experience.

[0062] In some possible ways, a joint analysis request may include multiple sub-joint analysis requests that have a logical relationship. Accordingly, in response to a joint analysis request for a target data metric triggered on the intelligent interaction page, the data analysis results for the joint analysis request are displayed on the intelligent interaction page, which may include:

[0063] In response to a request for joint analysis of target data metrics triggered on the intelligent interaction page, the intelligent interaction page displays the analysis task script used to implement the joint analysis request; in response to a trigger operation on the analysis task script, the intelligent interaction page displays the data analysis results obtained based on the analysis task script.

[0064] In this embodiment, triggering the analysis task script can be achieved by: associating the analysis task script with a target control for confirming or executing the analysis task script; thus, after displaying the analysis task script and the target control, triggering the analysis task script can be achieved by triggering the target control. Alternatively, a voice command for confirming or executing the analysis task script can be associated with the analysis task script; thus, after displaying the analysis task script, it can be triggered by a voice command. For example, when the intelligent interactive page detects the voice command "Confirm execution of analysis task script," the analysis task script is triggered. Of course, the triggering operation for the analysis task script can be other than this, and this embodiment does not impose any limitations on it.

[0065] For example, continuing with the previous example, after obtaining the target data metrics, you can input the joint analysis requirements for the target data metrics in the content input area of ​​the intelligent interaction page. For example, you can input the joint analysis requirement "I want to see the performance of these metrics in Dimension 1, Dimension 2, and...", and send "I want to see the performance of these metrics in Dimension 1, Dimension 2, and..." to the content display area by triggering the "Send" control. Then, the large model can automatically decompose "I want to see the performance of these metrics in Dimension 1, Dimension 2, and..." into analysis task scripts to achieve "I want to see the performance of these metrics in Dimension 1, Dimension 2, and..." according to the analysis granularity in the joint analysis requirement. The analysis task scripts are then displayed in the content display area of ​​the intelligent interaction page, along with the target control "Confirm and Start Execution" for executing the analysis task scripts. When "Confirm and Start Execution" is triggered by clicking or other operations, the data analysis results obtained based on the analysis task scripts can be displayed in the content display area of ​​the intelligent interaction page, such as... Figure 3 As shown.

[0066] In this embodiment, since the joint analysis requirement may include multiple logically related sub-joint analysis requirements, the data analysis result may include a single overall data analysis result, or a data analysis result may be generated for each sub-joint analysis requirement. This embodiment does not impose any limitations in this regard. When a data analysis result is generated for each sub-joint analysis requirement, each data analysis result can be displayed in a card style to facilitate users switching between and viewing the data analysis results corresponding to each sub-joint analysis requirement.

[0067] By leveraging the deep understanding capabilities of large models of natural language, joint analysis requirements, including multiple sub-joint analysis needs, can be automatically decomposed into analysis task scripts for implementing these requirements. Thus, by executing a single analysis task script, data analysis results for multiple sub-joint analysis needs can be obtained. Compared to related technologies that require sequential analysis of multiple logically related joint analysis needs, this solution simplifies the analysis process and further improves efficiency.

[0068] In some possible ways, to enable users to clearly understand the analysis process, when a user triggers a joint analysis request on the intelligent interaction page, the large model can identify the intent of the joint analysis request, and then automatically call the corresponding intelligent analysis tool to perform data analysis based on the identified intent. During the data analysis process, the name of the intelligent analysis tool currently performing the data analysis and / or the analysis process are displayed, thereby enhancing the credibility of the data analysis results.

[0069] In possible ways, in response to a triggering operation on the analysis task script, displaying the data analysis results obtained based on the analysis task script on the intelligent interaction page may include:

[0070] In response to the editing operation of the analysis task script, the target analysis task script is determined based on the editing operation; in response to the triggering operation of the target analysis task script, the data analysis results obtained by the target analysis task script are displayed on the intelligent interaction page.

[0071] In this embodiment, the editing operations on the analysis task script can be determined according to the actual situation, and this disclosure does not impose any restrictions on this. For example, such as Figure 3 As shown, editing operations on the analysis task script can include: adding, modifying, or deleting execution conditions, adding, modifying, or deleting analysis content, and adding, modifying, or deleting analysis indicators, etc.

[0072] The above methods allow users to edit the analysis task scripts generated from large models, enabling them to make targeted modifications to the scripts according to actual needs, thereby achieving personalized data analysis and further improving the user experience.

[0073] Among possible approaches, A / B testing data analysis methods based on large model agents may also include:

[0074] Display a content reference control on the smart interaction page, whereby the content reference control is used to reference the historical session content displayed on the smart interaction page;

[0075] Accordingly, in response to a joint analysis request for a target data metric triggered on the intelligent interaction page, the data analysis results for the joint analysis request can be displayed on the intelligent interaction page, which may include:

[0076] In response to a triggering operation on the content referencing control, the target historical session content to be referenced is determined from the historical session content; in response to a joint analysis request for the target data metric triggered on the smart interaction page, the data analysis results for the joint analysis request are displayed on the smart interaction page based on the target historical session content.

[0077] In this embodiment, displaying a content reference control on the smart interaction page can be: displaying a content reference control associated with each historical session content displayed on the smart interaction page, or displaying a content reference control on the smart interaction page, or other methods. This embodiment does not impose any limitations on this.

[0078] When a content reference control is displayed associated with each historical session content, in response to the user's triggering operation on the content reference control, the target historical session content to be referenced in the historical session content can be determined as: the historical session content associated with the triggered content reference control is determined as the target historical session content.

[0079] When a content reference control is displayed on the intelligent interactive page, in response to the user's triggering operation on the content reference control, determining the target historical session content to be referenced in the historical session content can be done in the following ways: After triggering the content reference control, a selection control for selecting historical session content can be displayed. After a selection is made in the historical session content through the selection control, the selected historical session content is determined as the target historical session content. Alternatively, it can be to automatically reference the previous historical session content, or other methods may be used. This disclosure does not impose any limitations on these methods.

[0080] For example, such as Figure 4 As shown, a content reference control "Reference" can be associated with each piece of historical session content in the content display area. When the reference control "Reference" associated with the historical session content "Under 'Axx…', Data Indicator 1 and Not…" is triggered by clicking or other operations, the "Under 'Axx…', Data Indicator 1 and Not…" marker can be displayed in the content input area of ​​the intelligent interaction page. This allows users to intuitively understand the referenced historical session content based on the markers displayed in the content input area. Subsequently, when a user triggers a joint analysis request on the intelligent interaction page, the large model can be used to generate data analysis results for the joint analysis request based on the target historical session content, and these results can be displayed in the content display area of ​​the intelligent interaction page.

[0081] By employing the methods described above, content reference controls can be displayed on the intelligent interactive page. This allows for data analysis to be performed by combining referenced content with joint analysis requirements, thereby further improving the accuracy of the data analysis. Especially when different joint data analysis results exist on the intelligent interactive page, content references enable the current data analysis to focus more on the referenced joint data analysis results, thus further enhancing the accuracy of the data analysis.

[0082] Among possible approaches, A / B testing data analysis methods based on large model agents may also include:

[0083] The interactive link graph is displayed on the intelligent interactive page. The interactive link graph is determined based on the reference relationship between different session content in the intelligent interactive page. In response to the trigger operation of the target session content in the interactive link graph, the target session content is located and displayed on the intelligent interactive page.

[0084] In this embodiment, the interaction link graph refers to a visual structure constructed based on the referencing relationships between session content to reflect the referencing paths between session content. For example, if the smart interaction page displays six session contents, denoted as Session Content 1, Session Content 2, Session Content 3, Session Content 4, Session Content 5, and Session Content 6, where Session Content 5 references Session Content 4, Session Content 4 references Session Content 2, Session Content 3 references Session Content 2, Session Content 2 references Session Content 1, and Session Content 6 does not reference any content, then the smart interaction page can display three interaction link graphs, denoted as Interaction Link Graph 1, Interaction Link Graph 2, and Interaction Link Graph 3. Interaction Link Graph 1 can be represented as: Session Content 2 → Session Content 4 → Session Content 5; Interaction Link Graph 2 can be represented as: Session Content 1 → Session Content 2 → Session Content 3; and Interaction Link Graph 3 can be represented as: Session Content 6.

[0085] In this embodiment, displaying the interaction link graph on the intelligent interaction page can be done by: only displaying the name of the interaction link graph, and when the name of the interaction link graph is triggered, displaying the session content in the interaction link graph according to the session reference order, such as... Figure 5 As shown. Alternatively, the session content in each interaction link graph can be displayed directly on the intelligent interaction page in the order of session reference. Of course, other methods are also possible, and this embodiment of the disclosure does not impose any limitations on this. However, regardless of the display method, as long as the session content in the interaction link graph is triggered, the triggered session content can be located and displayed on the intelligent interaction page.

[0086] Using the above method, an interaction path graph, determined by the referencing relationships between different conversational content within the intelligent interaction page, can be displayed. This interaction path graph assists users in organizing and analyzing their thoughts during multi-turn conversations, further improving analysis efficiency and user experience. Furthermore, since triggering conversational content within the interaction path graph allows for quick navigation to the corresponding content on the intelligent interaction page without the need for manual searching through numerous conversation records, it further enhances the user experience.

[0087] Among possible approaches, the intelligent interactive page includes a full-screen display style and a floating window display style. The full-screen display style of the intelligent interactive page provides data table display functionality. Correspondingly, the A / B test data analysis method based on large model intelligent agents may also include:

[0088] When the smart interactive page is displayed in full-screen mode and a data table is displayed on the smart interactive page, in response to the style switching operation of the smart interactive page, the smart interactive page is displayed in floating window mode, and the data table is updated to display text content, where the text content is used to describe the table content of the data table.

[0089] In this embodiment, the style switching operation of the intelligent interactive page can be performed by entering a shortcut key on an external device. For example, the style switching operation can be performed by entering the shortcut key "Ctrl+D" on the keyboard. Alternatively, a style switching control can be displayed on the intelligent interactive page, thereby triggering the style switching control to switch the style of the intelligent interactive page. Of course, the style switching operation of the intelligent interactive page can also be performed in other ways, and this embodiment does not impose any limitations on this.

[0090] For example, such as Figure 6 As shown, the intelligent interactive page is displayed in full-screen mode, with a data table in the middle and text content below the data table. A style switching control, "Style Switch," is displayed in the upper right corner of the intelligent interactive page. Thus, when "Style Switch" is triggered by clicking or other operations, the intelligent interactive page can be displayed in a floating window mode, and the display of the data table can be canceled.

[0091] In some possible ways, to enable quick viewing of data tables on a smart interactive page, when the displayed content of the smart interactive page includes a data table and the smart interactive page is displayed in a floating window style, a quick switching command can be displayed on the smart interactive page to switch the smart interactive page from the floating window style to the full-screen display style. For example, the quick switching command "View data table in full-screen display mode" can be displayed on the smart interactive page. Figure 6 As shown, by triggering the quick switch command "View data table in full-screen mode", the smart interactive page can be quickly switched from floating window display style to full-screen display style, thereby further improving the user experience.

[0092] It should be understood that when the smart interactive page is displayed in a floating window style, the display window is smaller than in the full-screen display style. Therefore, in order to display the data table completely on the smart interactive page, the table content is small, resulting in poor readability. Therefore, this embodiment updates the data table display as text content when the smart interactive page switches from full-screen to floating window display style, thereby increasing the readability of the displayed content and improving the user experience.

[0093] Based on the same concept, embodiments of this disclosure also provide an A / B testing data analysis device based on a large model intelligent agent, such as... Figure 7 As shown, the A / B test data analysis device 700 based on large model intelligent agents may include:

[0094] The first display module 701 is used to display the intelligent interactive page associated with the intelligent agent, which is used to perform joint analysis of different data indicators through a large model;

[0095] The determination module 702 is used to determine at least two data indicators as target data indicators to be jointly analyzed in response to an input operation on the intelligent interactive page for at least two data indicators.

[0096] The second display module 703 is used to display the data analysis results for the joint analysis request triggered on the intelligent interactive page in response to the joint analysis request for the target data indicators.

[0097] The A / B testing data analysis device 700 based on a large-model intelligent agent allows users to input target data indicators for joint analysis and their joint analysis requirements on an intelligent interactive page. The large model automatically analyzes these joint analysis requirements, yielding data analysis results tailored to those requirements. This simplifies the data analysis process and improves efficiency by enabling automated data analysis through relatively simple input. Furthermore, because this solution supports the input of data indicators and allows for joint analysis of different indicators, users can customize targeted analyses for different data indicators based on their needs, thereby enhancing the flexibility of data analysis and improving the user experience.

[0098] In some possible ways, the determining module 702 may include:

[0099] The first display unit is used to display different data indicators in response to shortcut commands triggered on the intelligent interactive page;

[0100] The first determining unit is used to determine the at least two data indicators corresponding to the selection operation as the target data indicators to be jointly analyzed in response to the selection operation of at least two data indicators among different data indicators.

[0101] In some possible ways, the joint analysis requirement may include multiple sub-joint analysis requirements with logical relationships, and accordingly, the second display module 703 may include:

[0102] The second display unit is used to respond to the joint analysis request for the target data indicators triggered on the intelligent interactive page, and to display the analysis task script for realizing the joint analysis request on the intelligent interactive page.

[0103] The third display unit is used to display the data analysis results obtained based on the analysis task script on the intelligent interactive page in response to the trigger operation of the analysis task script.

[0104] In some possible configurations, the third display unit may include:

[0105] Determine the sub-unit to respond to the editing operation on the analysis task script, and determine the target analysis task script based on the editing operation;

[0106] The display sub-unit is used to respond to the trigger operation of the target analysis task script and display the data analysis results obtained by the target analysis task script on the intelligent interaction page.

[0107] In some possible configurations, the A / B testing data analysis device 700 based on large model agents may also include:

[0108] The third display module is used to display content reference controls on the intelligent interaction page. The content reference controls are used to reference the historical session content displayed on the intelligent interaction page.

[0109] Accordingly, the second display module 703 may include:

[0110] The first determining unit is used to determine the target historical session content to be referenced in the historical session content in response to the triggering operation of the content referencing control.

[0111] The fourth display unit is used to respond to the joint analysis request for the target data indicators triggered on the intelligent interactive page, and to display the data analysis results for the joint analysis request on the intelligent interactive page based on the target historical session content.

[0112] In some possible configurations, the A / B testing data analysis device 700 based on large model agents may also include:

[0113] The fourth display module is used to display the interaction link graph on the intelligent interaction page, wherein the interaction link graph is determined based on the reference relationship between different session content in the intelligent interaction page;

[0114] The fifth display module is used to locate and display the target session content in the intelligent interaction page in response to the trigger operation of the target session content in the interaction link graph.

[0115] In possible configurations, the intelligent interactive page includes a full-screen display style and a floating window display style. The full-screen display style of the intelligent interactive page provides data table display functionality. Correspondingly, the A / B test data analysis device 700 based on the large model intelligent agent may also include:

[0116] The sixth display module is used to respond to the style switching operation of the intelligent interactive page by displaying the intelligent interactive page in a floating window style and canceling the display of the data table when the intelligent interactive page is displayed in full-screen display style and displaying a data table on the intelligent interactive page.

[0117] Based on the same concept, embodiments of this disclosure also provide a computer-readable medium having a computer program stored thereon, which, when executed by a processing device, implements the steps of any of the above-described A / B test data analysis methods based on large model intelligent agents.

[0118] Based on the same concept, this disclosure also provides an electronic device that may include:

[0119] A storage device on which computer programs are stored;

[0120] A processing device is used to execute a computer program stored in a storage device to implement the steps of any of the above-described A / B test data analysis methods based on large model intelligent agents.

[0121] Based on the same concept, embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described A / B test data analysis methods based on large model agents.

[0122] The following is for reference. Figure 8 This diagram illustrates a structural schematic of an electronic device 800 suitable for implementing embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0123] like Figure 8 As shown, the electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage device 808 into a random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the electronic device 800. The processing device 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0124] Typically, the following devices can be connected to I / O interface 805: input devices 806 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 807 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 808 including, for example, magnetic tapes, hard disks, etc.; and communication devices 809. Communication device 809 allows electronic device 800 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8 An electronic device 800 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0125] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 809, or installed from a storage device 808, or installed from a ROM 802. When the computer program is executed by a processing device 801, it performs the functions defined in the methods of embodiments of this disclosure.

[0126] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0127] In some implementations, communication can be conducted using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can be interconnected with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0128] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0129] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: display an intelligent interactive page associated with an intelligent agent, the intelligent agent being used to perform joint analysis of different data indicators through a large model; in response to input operations on at least two data indicators on the intelligent interactive page, identify at least two data indicators as target data indicators to be jointly analyzed; and in response to a joint analysis request triggered on the intelligent interactive page for the target data indicators, display data analysis results for the joint analysis request on the intelligent interactive page.

[0130] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0132] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules are not, in some cases, intended to limit the functionality of the module itself.

[0133] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0134] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0135] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0136] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0137] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative forms of implementing the claims. Regarding the apparatus in the above embodiments, the specific manner in which the various modules perform their operations has been described in detail in the embodiments relating to the method, and will not be elaborated upon here.

Claims

1. A method for A / B testing data analysis based on large model intelligent agents, characterized in that, The A / B testing data analysis method based on large model agents includes: The intelligent agent is associated with an intelligent interaction page, and a content reference control and an interaction link graph are displayed on the intelligent interaction page. The content reference control is used to reference the historical session content displayed on the intelligent interaction page. The interaction link graph is determined based on the reference relationship between different session content on the intelligent interaction page. The intelligent agent is used to perform joint analysis of different data indicators in A / B testing experiments through a large model. In response to inputting at least two data metrics on the intelligent interactive page, the at least two data metrics are identified as target data metrics to be jointly analyzed. In response to a triggering operation on the content referencing control, the target historical session content to be referenced is determined from the historical session content; In response to a joint analysis request for the target data metric triggered on the smart interaction page, the data analysis results for the joint analysis request are displayed on the smart interaction page based on the target historical session content.

2. The A / B testing data analysis method based on large model agents according to claim 1, characterized in that, The step of responding to inputting at least two data metrics on the intelligent interactive page, and determining the at least two data metrics as target data metrics to be jointly analyzed, includes: In response to shortcut commands triggered on the smart interactive page, different data metrics are displayed; In response to the selection operation of at least two data indicators among the different data indicators, the at least two data indicators corresponding to the selection operation are determined as target data indicators to be jointly analyzed.

3. The A / B testing data analysis method based on large model intelligent agents according to claim 1 or 2, characterized in that, The joint analysis request includes multiple sub-joint analysis requests with logical relationships. In response to the joint analysis request triggered on the intelligent interaction page for the target data indicator, based on the target historical session content, the data analysis results for the joint analysis request are displayed on the intelligent interaction page, including: In response to a joint analysis request for the target data indicator triggered on the intelligent interaction page, an analysis task script for implementing the joint analysis request is displayed on the intelligent interaction page. In response to the triggering operation of the analysis task script, the data analysis results obtained based on the analysis task script and the target historical session content are displayed on the intelligent interaction page.

4. The A / B testing data analysis method based on a large model intelligent agent according to claim 3, characterized in that, In response to a trigger operation on the analysis task script, the data analysis results obtained based on the analysis task script and the target historical session content are displayed on the intelligent interactive page, including: In response to an editing operation on the analysis task script, a target analysis task script is determined based on the editing operation; In response to a trigger operation on the target analysis task script, the data analysis results obtained from the target analysis task script and the target historical session content are displayed on the intelligent interaction page.

5. The A / B testing data analysis method based on large model intelligent agents according to claim 1 or 2, characterized in that, The A / B testing data analysis method based on large model agents also includes: In response to a triggering operation on the target session content in the interaction link graph, the target session content is located and displayed on the intelligent interaction page.

6. The A / B testing data analysis method based on large model intelligent agents according to claim 1 or 2, characterized in that, The intelligent interactive page includes a full-screen display style and a floating window display style. The full-screen display style of the intelligent interactive page provides a data table display function. The A / B test data analysis method based on large model intelligent agents also includes: When the smart interactive page is displayed in full-screen mode and a data table is displayed on the smart interactive page, in response to the style switching operation of the smart interactive page, the smart interactive page is displayed in the floating window mode, and the display of the data table is canceled.

7. An A / B testing data analysis device based on a large model intelligent agent, characterized in that, The data analysis device includes: The first display module is used to display the intelligent interaction page associated with the intelligent agent, and to display content reference controls and interaction link graphs on the intelligent interaction page. The content reference controls are used to reference the historical session content displayed on the intelligent interaction page, and the interaction link graph is determined based on the reference relationship between different session content on the intelligent interaction page. The intelligent agent is used to perform joint analysis of different data indicators in A / B testing experiments through a large model. A determination module is configured to determine the at least two data indicators as target data indicators to be jointly analyzed in response to an input operation on the intelligent interactive page. The second display module is configured to, in response to a triggering operation of the content referencing control, determine the target historical session content to be referenced in the historical session content, and, in response to a joint analysis request for the target data metric triggered on the smart interaction page, display the data analysis results for the joint analysis request on the smart interaction page based on the target historical session content.

8. A computer-readable medium having a computer program stored thereon, characterized in that, When executed by a processing device, the computer program performs the steps of the method according to any one of claims 1-6.

9. An electronic device, characterized in that, include: A storage device on which computer programs are stored; A processing device for executing the computer program in the storage device to implement the steps of the method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-6.

Images