Question and answer method and system and electronic equipment

Abstract

The invention provides a question and answer method and system and electronic equipment. The question and answer method comprises the following steps: in response to a first question input by a user, outputting a first data service matched with the first question; wherein the first data service is used for accessing and displaying a first data asset; outputting at least one recommended second question based on the first question and the first data service; in response to a second question triggered by the user, outputting a corresponding result based on a second data service matched with the second question; wherein the second data service is used for accessing and displaying a second data asset. According to the method and the device, flexible and changeable data type access is realized, according to actual conditions such as different scenes or different data sources, targeted answers conforming to business expectations are generated, corresponding guidance is given, an internal data island of an enterprise is broken, and deep integration and efficient utilization of data are realized.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a question-answering method and system, and an electronic device. Background Technology

[0002] In today's digital age, enterprises have accumulated massive amounts of data, originating from different business departments, application scenarios, and various data generation systems. However, the management and utilization of internal enterprise data faces numerous challenges, one of the most prominent being the phenomenon of data silos. Data silos refer to the state where data between different departments or systems within an enterprise cannot be shared or circulated, remaining isolated from each other.

[0003] The existence of data silos severely hinders enterprises' efficient use of data. In different business scenarios, enterprises need to integrate data from multiple sources for decision support, business optimization, and innovation. However, due to data silos, this data is difficult to integrate effectively, preventing enterprises from fully realizing its value and causing them to miss business growth opportunities. Therefore, breaking down internal data silos and achieving efficient integration and utilization of data from different scenarios and data sources has become a pressing issue for enterprises. Summary of the Invention

[0004] The technical problem to be solved by this disclosure is to overcome the above-mentioned defects in the prior art and provide a question-and-answer method, system, and electronic device that can deeply integrate and efficiently utilize different data.

[0005] This disclosure solves the above-mentioned technical problems through the following technical solution:

[0006] A first aspect of this disclosure provides a question-answering method, comprising the following steps: in response to a first question input by a user, outputting a first data service matching the first question; wherein the first data service is used to access and display a first data asset; outputting at least one recommended second question based on the first question and the first data service; in response to a second question triggered by a user, outputting a corresponding result based on a second data service matching the second question; wherein the second data service is used to access and display a second data asset.

[0007] Optionally, the step of providing a first data service that outputs a solution to the first problem specifically includes:

[0008] Identify the feature words corresponding to the first question;

[0009] Output the first data service that matches the feature word.

[0010] Optionally, before the step of outputting a first data service that matches the first question, the method further includes: replacing non-standard words in the first question with corresponding standard words in the knowledge base.

[0011] Optionally, the second data service matching the second problem is one, and the step of outputting the corresponding result based on the second data service matching the second problem specifically includes:

[0012] Output the second data service that matches the second problem.

[0013] Optionally, at least one second data service matches the second problem, and the step of outputting the corresponding result based on the second data service matching the second problem specifically includes:

[0014] Output at least one second data service that matches the second problem;

[0015] In response to the user's confirmation of the interface parameters of any second data service, the target data asset corresponding to the interface parameters is output; wherein, the interface parameters are obtained based on the second question.

[0016] Optionally, the step of outputting the result corresponding to the second data service matching the second question further includes: inputting the prompt word corresponding to the target data asset into the large model and outputting the corresponding result.

[0017] A second aspect of this disclosure provides a question-answering system, including a first output module, a second output module, and a third output module. The first output module is configured to output a first data service matching the first question in response to a first question input by a user; wherein the first data service is used to access and display a first data asset. The second output module is configured to output at least one recommended second question based on the first question and the first data service. The third output module is configured to output a corresponding result based on a second data service matching the second question in response to a second question triggered by a user; wherein the second data service is used to access and display a second data asset.

[0018] Optionally, the first output module is specifically used to identify the feature words corresponding to the first question, and to output a first data service that matches the feature words.

[0019] Optionally, the first output module is further configured to replace non-standard words in the first question with corresponding standard words in the knowledge base before the step of outputting the first data service that matches the first question.

[0020] Optionally, there is one second data service that matches the second problem, and the third output module is specifically used to output the second data service that matches the second problem.

[0021] Optionally, the second data service matching the second question is at least one, and the third output module is specifically used to output at least one second data service matching the second question, and in response to the user confirming the interface parameters of any second data service, output the target data asset corresponding to the interface parameters; wherein, the interface parameters are obtained based on the second question.

[0022] Optionally, the third output module is further configured to input the prompt words corresponding to the target data asset into the large model and output the corresponding results.

[0023] A third aspect of this disclosure provides an electronic device including a memory, a processor, and a computer program stored in the memory and for running on the processor, wherein the processor executes the computer program to implement the question-and-answer method as described in the first aspect.

[0024] A fourth aspect of this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the question-and-answer method as described in the first aspect.

[0025] The fifth aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the question-and-answer method as described in the first aspect.

[0026] Based on common knowledge in the field, the above-mentioned preferred conditions can be combined arbitrarily to obtain various preferred embodiments of this disclosure.

[0027] The positive and progressive effects of this disclosure are as follows: by providing data services for accessing and displaying different data assets, and setting up the correspondence between different data services and different questions, after the user enters the first question, the first data asset is displayed through the matched first data service, and the user is guided to trigger the second question. Combined with the matched second data service, the corresponding result is output, realizing flexible and varied data type access. Based on different scenarios or different data sources, targeted answers that meet business expectations are generated and corresponding guidance is provided, breaking down data silos within the enterprise and realizing deep integration and efficient utilization of data. Attached Figure Description

[0028] Figure 1 This is a flowchart of a question-and-answer method provided in Embodiment 1 of this disclosure.

[0029] Figure 2 This is a schematic diagram of an application scenario of the question-and-answer method provided in Embodiment 1 of this disclosure.

[0030] Figure 3 This is a schematic diagram illustrating another application scenario of the question-and-answer method provided in Embodiment 1 of this disclosure.

[0031] Figure 4 This is a schematic diagram illustrating another application scenario of the question-and-answer method provided in Embodiment 1 of this disclosure.

[0032] Figure 5 This is a schematic diagram illustrating another application scenario of the question-and-answer method provided in Embodiment 1 of this disclosure.

[0033] Figure 6 This is a schematic diagram illustrating another application scenario of the question-and-answer method provided in Embodiment 1 of this disclosure.

[0034] Figure 7 This is a structural block diagram of a question-and-answer system provided in Embodiment 1 of this disclosure.

[0035] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 2 of this disclosure. Detailed Implementation

[0036] The present disclosure is further illustrated below by way of embodiments, but the present disclosure is not limited to the scope of the embodiments described herein.

[0037] The prefixes such as "first" and "second" used in this disclosure are merely for distinguishing different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in this disclosure does not constitute a limitation on the described objects. The description of the described objects is given in the claims or the context of the embodiments, and should not be construed as an unnecessary limitation. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0038] In this embodiment of the disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good morals.

[0039] The question-and-answer method provided in this disclosure can be applied to systems integrating various types of data, such as enterprise internal data management systems, to solve the problem of data silos within enterprises and achieve deep data integration and efficient utilization. Specifically, by providing data services for accessing and displaying different data assets, and setting the correspondence between different data services and different questions, after a user inputs a first question, the first data asset is displayed through the matched first data service, guiding the user to trigger a second question. The corresponding result is then output through the matched second data service. This achieves flexible access to various data types, generating targeted answers that meet business expectations and providing corresponding guidance based on different scenarios or data sources, breaking down data silos within enterprises and achieving deep data integration and efficient utilization.

[0040] Example 1

[0041] Figure 1 This is a flowchart illustrating a question-and-answer method provided in this embodiment. This method can be executed by a question-and-answer system, which can be implemented through software and / or hardware. The question-and-answer system can be part or all of an electronic device. The question-and-answer method provided in this embodiment is described below using an electronic device as the executing entity.

[0042] like Figure 1 As shown, the question-and-answer method provided in this embodiment may include the following steps S11~S13:

[0043] Step S11: In response to the first question input by the user, output a first data service that matches the first question; wherein the first data service is used to access and display the first data asset.

[0044] Step S12: Recommend at least one second question based on the first question and the output of the first data service.

[0045] Step S13: In response to the second question triggered by the user, output the corresponding result based on the second data service that matches the second question; wherein the second data service is used to access and display the second data asset.

[0046] It should be noted that the aforementioned data services refer to information technology-driven services that provide various forms of data evolution, including data acquisition, data transmission, data storage, data processing (including calculation, analysis, visualization, etc.), data exchange, and data destruction. Essentially, they are service programs that support database systems, typically composed of a group of processes or threads responsible for listening to client requests and providing corresponding services. Data services can usually support multiple different database systems, and in practical applications, the supported database systems can be accessed through the data service.

[0047] The aforementioned data assets can be of various types, including reports, data tables, images, videos, files, and smart agents. Access to these data assets is achieved by configuring links, authorization information, and descriptions for each type of data asset in the first and second data services. In some examples, the authorization information for a data asset may include the address, account, and password of the data asset platform, as well as the SSL (Secure Socket Layer) authentication address. The description information may include the data asset name, address, code, and remarks on the data asset platform. Different data asset platforms are used to store different types of data assets.

[0048] Specifically, it is necessary to pre-set the correspondence between different data services and different questions, including the correspondence between the first data service and the first question, and the correspondence between the second data service and the second question.

[0049] In practice, in response to the first question input by the user, the system automatically links to the corresponding first data service based on the correspondence between the first data service and the first question. Similarly, in response to the second question triggered by the user, the system automatically links to the corresponding second data service based on the correspondence between the second data service and the second question.

[0050] In one optional implementation, step S11 specifically includes: firstly identifying feature words corresponding to the first question, and then outputting a first data service matching the feature words. Feature words refer to keywords or phrases that can characterize the user's query intent, and are usually closely related to the enterprise's business area and data type. Specifically, natural language processing can be performed on the first question input by the user to extract feature words. For example, in the question "Which stores experience service speed timeouts?", feature words such as "stores", "service speed", and "timeout" can be identified.

[0051] In practical applications, each data service has its own functional description, interface parameters, data source, and other information. In some examples, the matching degree between feature words and each first data service is calculated, and the first data service with the highest matching degree is selected as the output result.

[0052] In one optional implementation, before outputting the first data service matching the first question, non-standard words in the first question are replaced with corresponding standard words from the knowledge base. This aims to handle non-standard expressions or synonyms that users may use, ensuring accurate understanding of the user's query intent. For example, a user might use "shop" instead of "storefront," or "slow" instead of "timeout." In this implementation, maintaining a standardized word knowledge base allows these non-standard expressions to be mapped to standard words. For example, if the user's first question is "Which shops have slow service?", "shop" will be replaced with "storefront," and "slow" will be replaced with "timeout," before subsequent feature word recognition and / or data service matching.

[0053] Specifically, it requires maintaining a proprietary knowledge base of standardized terminology for the enterprise. This knowledge base contains commonly used business terms and their standard expressions. When a user enters a question containing non-standard expressions, the knowledge base is consulted to replace the non-standard terms with their corresponding standard terms. This step is particularly important for handling internal professional and industry-specific terminology, as different users may use different expressions to describe the same concept.

[0054] In this embodiment, a first question is received from the user via an interactive interface or voice input. A corresponding first data service is matched according to a pre-set mapping. Based on the user-input first question and the output first data service, at least one relevant second question is generated and recommended. These recommended second questions aim to guide the user to conduct more in-depth data exploration and analysis.

[0055] In some examples, a second question relevant to the current context is generated by analyzing the semantic content of the first question and the data features displayed by the first data service. In other examples, the second question can be recommended by combining different business scenarios, user historical query behavior, and user preferences. In still others, Retrieval-augmented Generation (RAG) technology is used to search for similar service recommendation questions in a matching vector database based on the user-input first question. According to the system configuration of the service recommendation questions, subsequent questions matching the first question are then used as the recommended second question.

[0056] In some examples, these recommended second questions are displayed as clickable options on the user interface, allowing users to select them directly or enter their own second question based on these recommendations. In other examples, these recommended second questions are played via voice prompts to guide users in triggering the second question.

[0057] It should be noted that the aforementioned interactive interface can be a search engine's interface, utilizing the search engine to perform matching operations between questions and data services. Furthermore, a recommendation engine can be used to generate recommended second questions, a display engine can be used to showcase different data services and corresponding data assets, and a recognition engine can be used to replace non-standard words in the first question. In this way, the question-answering method provided in this embodiment is achieved through the collaborative work of different engines, thereby enabling flexible access to various data types.

[0058] In practical applications, the first question could be a query about business operations, sales, human resources, etc. Figure 2 In the example shown, in response to the user's first input question, "Which stores are experiencing service speed timeouts?", the matched first data service, "W11 Operational Weekly Service Speed ​​by Store (Standard 3.5min)," is output to the user interface. Simultaneously, the first data service accesses the corresponding data asset, i.e., the first data asset. The first data service connects to the enterprise's store service database to query data, extracts relevant store service speed data from the enterprise database, and presents it to the user in a preset display format (such as tables, charts, etc.). It also determines which stores are experiencing service speed timeouts based on the preset standard (3.5 minutes). Figure 2 The first data service shown displays a table containing service speed data for all stores, with stores exceeding the 3.5-minute timeout standard specifically marked. Based on the first question and the second question recommended by the first data service output, "Why did the service speed of a specific store time out?"

[0059] In one possible implementation of step S13 above, there is only one second data service matching the second question. In this implementation, the second data service matching the second question is directly output. For example, when a user triggers the second question "Training status of employee ID XX and name XX", the only matching second data service is "Employee Information Query", so this second data service will be directly output to display the training status data of the specified employee. In this example, the user can obtain the answer to the first question through the employee's training status data.

[0060] In another optional implementation of step S13 above, at least one second data service matches the second question. In this implementation, these second data services are output for the user to select. After the user confirms the interface parameters of any second data service, the target data asset corresponding to the interface parameters is output. The interface parameters are obtained based on the second question. In some examples, the second data service can automatically identify the interface parameters involved in the second question, requiring only a confirmation operation from the user. In other examples, the user needs to select the interface parameters involved in the second question from the second data service before triggering the confirmation operation.

[0061] exist Figure 3 In the example shown, in response to the user-triggered second question, "Why did the service speed at **3 store time out? What are your suggestions?", three relevant second data services were matched, including "Store service speed statistics", "Store service speed by time period", and "Overall service speed analysis from various dimensions". For example... Figure 4 As shown, after the user confirms the interface parameter "**3 stores" for the second data service, which is "Store Time-Based Service Speed", they will enter... Figure 5 The user interface shown outputs the target data asset corresponding to the interface parameters, namely the data table "W11 Operation Weekly **3 Store Time-of-Day Service Speed ​​Statistics". In this example, the user can obtain the answer to the first question through this data table.

[0062] In one optional implementation, step S13 further includes: inputting the prompt words corresponding to the target data asset into the large model and outputting the corresponding results. Different data assets may correspond to the same prompt words or different prompt words; specifically, the prompt words can be set according to the user's question-and-answer needs. The large model refers to an artificial intelligence model with powerful natural language processing capabilities, capable of generating relevant analysis results based on the input prompt words. These results, as supplementary information, are displayed to the user along with the target data asset, helping the user better understand the data and make decisions. In this implementation, the prompt words corresponding to the target data asset can be input into the large model based on user-triggered actions, or the prompt words corresponding to the target data asset can be input automatically.

[0063] exist Figure 6 In the example shown, after inputting the prompt "Analysis data of service speed failure in **3 stores" corresponding to the data table "W11 Operation Week **3 Store Service Speed ​​Statistics by Time Period" into the large model, the large model will generate analysis results based on the prompt, including: the severity of service speed failure, the time period pattern of service speed failure, the time period of serious timeout, and other issues.

[0064] This embodiment also provides a question-and-answer system, such as Figure 7As shown, the system includes a first output module 71, a second output module 72, and a third output module 73. The first output module is used to respond to a first question input by a user and output a first data service matching the first question; wherein the first data service is used to access and display a first data asset. The second output module is used to output at least one recommended second question based on the first question and the first data service. The third output module is used to respond to a second question triggered by a user and output a corresponding result based on a second data service matching the second question; wherein the second data service is used to access and display a second data asset.

[0065] In this embodiment, the question-and-answer system can be a software system integrating multiple functional modules, used to achieve intelligent enterprise data access and analysis. This system can be deployed on the enterprise's server, providing services to internal users via the network.

[0066] In one optional implementation, the first output module is specifically used to identify the feature words corresponding to the first question, and to output a first data service that matches the feature words.

[0067] In one optional implementation, the first output module is further configured to replace non-standard words in the first question with corresponding standard words in the knowledge base before the step of outputting the first data service that matches the first question.

[0068] In one optional implementation, there is one second data service that matches the second problem, and the third output module is specifically used to output the second data service that matches the second problem.

[0069] In one optional implementation, the second data service matching the second problem is at least one, and the third output module is specifically used to output at least one second data service matching the second problem, and in response to the user confirming the interface parameters of any second data service, output the target data asset corresponding to the interface parameters; wherein, the interface parameters are obtained based on the second problem.

[0070] In one optional implementation, the third output module is further configured to input the prompt words corresponding to the target data asset into the large model and output the corresponding results.

[0071] It should be noted that the question-and-answer system in this embodiment can be a separate chip, chip module, or electronic device, or it can be a chip or chip module integrated into an electronic device.

[0072] Regarding the various modules / units included in the question-answering system described in this embodiment, they may be software modules / units, hardware modules / units, or a combination of both.

[0073] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs.

[0074] Example 3

[0075] Figure 8 This is a schematic diagram of the structure of an electronic device provided in this embodiment. The electronic device includes at least one processor and a memory communicatively connected to the at least one processor. The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the steps of the question-and-answer method in Embodiment 1. Figure 8 The electronic device 3 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0076] The components of the electronic device 3 may include, but are not limited to: at least one processor 4, at least one memory 5, and a bus 6 connecting different system components (including memory 5 and processor 4).

[0077] Bus 6 includes a data bus, an address bus, and a control bus.

[0078] The memory 5 may include volatile memory, such as random access memory (RAM) 51 and / or cache memory 52, and may further include read-only memory (ROM) 53.

[0079] The memory 5 may also include a program tool 55 having a set (at least one) of program modules 54, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0080] Processor 4 executes various functional applications and data processing, such as the question-and-answer method described above, by running computer programs stored in memory 5.

[0081] Electronic device 3 can also communicate with one or more external devices 7 (e.g., keyboard, pointing device, etc.). This communication can be performed through input / output (I / O) interface 8. Furthermore, electronic device 3 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 9. Figure 8 As shown, network adapter 9 communicates with other modules of electronic device 3 via bus 6. It should be understood that, although... Figure 8 Not shown, it can be combined with electronic device 3 to use other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0082] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0083] Example 3

[0084] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the question-and-answer method in Embodiment 1.

[0085] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0086] In a possible implementation, this disclosure may also be implemented as a computer program product comprising a computer program that, when executed by a processor, implements the steps of the question-and-answer method in Embodiment 1.

[0087] The computer program for executing the present disclosure can be written in any combination of one or more programming languages, and the computer program can be executed entirely on an electronic device, partially on an electronic device, as a stand-alone software package, partially on an electronic device and partially on a remote device, or entirely on a remote device.

[0088] While specific embodiments of this disclosure have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of this disclosure is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of this disclosure, but all such changes and modifications fall within the scope of protection of this disclosure.

Claims

1. A question-and-answer method, characterized in that, Includes the following steps: In response to a first question input by the user, a first data service matching the first question is output; wherein, the first data service is used to access and display a first data asset; At least one second question recommended based on the first question and the output of the first data service; In response to a second question triggered by the user, a corresponding result is output based on a second data service that matches the second question; wherein the second data service is used to access and display the second data asset.

2. The question-and-answer method as described in claim 1, characterized in that, The steps of providing the first data service that matches the first problem specifically include: Identify the feature words corresponding to the first question; Output the first data service that matches the feature word.

3. The question-and-answer method as described in claim 1, characterized in that, Prior to the step of providing a first data service that outputs a value matching the first problem, the method further includes: Replace the non-standard words in the first question with the corresponding standard words from the knowledge base.

4. The question-and-answer method as described in claim 1, characterized in that, There is one second data service that matches the second problem. The step of outputting the corresponding result based on the second data service that matches the second problem specifically includes: Output the second data service that matches the second problem.

5. The question-and-answer method as described in claim 1, characterized in that, There is at least one second data service that matches the second problem, and the step of outputting the corresponding result based on the second data service that matches the second problem specifically includes: Output at least one second data service that matches the second problem; In response to the user's confirmation of the interface parameters of any second data service, the target data asset corresponding to the interface parameters is output; wherein, the interface parameters are obtained based on the second question.

6. The question-and-answer method as described in claim 5, characterized in that, The step of outputting the result corresponding to the second data service that matches the second problem further includes: Input the prompt words corresponding to the target data asset into the large model, and output the corresponding results.

7. A question-and-answer system, characterized in that, include: The first output module is used to respond to a first question input by the user and output a first data service that matches the first question; wherein the first data service is used to access and display a first data asset; The second output module is used to output at least one recommended second question based on the first question and the first data service; The third output module is used to respond to a second question triggered by the user and output a corresponding result based on a second data service that matches the second question; wherein the second data service is used to access and display the second data asset.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, characterized in that, When the processor executes the computer program, it implements the question-and-answer method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the question-and-answer method as described in any one of claims 1 to 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 question-and-answer method as described in any one of claims 1-6.

Images