Data diagnosis method and device and electronic equipment

Abstract

Embodiments of the invention disclose a data diagnosis method and apparatus, and an electronic device. The method comprises the steps of establishing a data bottom table containing data source information corresponding to a plurality of data diagnosis scenes; obtaining prompt information template configuration information; after a request for performing data diagnosis on a target scene is received, querying and obtaining data corresponding to the target scene from the data bottom table, converting the data into a standard data structure, and determining a target prompt information template corresponding to the target scene; and integrating the target prompt information template with data which corresponds to the target scene and is expressed through a standard data structure to obtain prompt information, and inputting the prompt information to an artificial intelligence (AI) model, so that the AI model generates conclusion content which accords with a corresponding data diagnosis purpose through data analysis. Through the embodiment of the invention, the smoothly expressed diagnostic verbal skills and suggestions can be generated in a natural language mode, the user experience is better, the cost is low, and the expandability is good.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data diagnosis method, device and electronic equipment. Background Art

[0002] In the product information service system, in order to enhance some merchants' understanding of the industry and their own business conditions, the operators in the system can provide merchants with periodic problem diagnosis services through diagnostic service reports, guide merchants to pay attention to the store's operating status and provide reasonable improvement suggestions, thereby driving improvements in merchants' operating results and improving the platform's retention rate.

[0003] However, in the process of providing the above diagnostic services, there are at least the following problems: Homogeneity of service content: A merchant's diagnostic service may produce multiple reports, such as productized reports, third-party diagnostic services, and industry customer service personnel, but the content of each report is very similar. In addition, the report delivery method is mainly third-party procurement, which leads to high procurement costs. Summary of the invention

[0004] The present application provides a data diagnosis method, device and electronic device, which can generate fluently expressed diagnostic words and opinions in natural language, provide better user experience, low cost and good scalability.

[0005] This application provides the following solutions:

[0006] A data diagnosis method, comprising:

[0007] Establish a data base table containing data source information corresponding to multiple data diagnosis scenarios;

[0008] Acquire prompt information template configuration information, wherein the prompt information template configuration information includes association relationship information between the prompt information template and the scene identifier; the prompt information template at least includes information describing the purpose of data diagnosis;

[0009] After receiving a request for data diagnosis for a target scene, query and obtain data corresponding to the target scene from the data base table, convert the data into a standard data structure, and determine a target prompt information template corresponding to the target scene according to the association relationship information in the prompt information template configuration information;

[0010] The prompt information is obtained by integrating the target prompt information template with the data expressed by the standard data structure corresponding to the target scene, and the prompt information is input into the artificial intelligence AI model, so that the AI ​​model generates conclusion content that meets the corresponding data diagnosis purpose through data analysis.

[0011] Among them, the prompt information template also includes: content for adding business meaning information to the data in the data source, so that the AI ​​model generates the conclusion content based on understanding the business meaning of the data.

[0012] Among them, the content used to add business meaning information to the data in the data source includes: content in the form of parameter variables, so that in the process of integrating prompt information, the data corresponding to the parameters can be determined according to the data pulled from the data base table to generate the prompt information.

[0013] Among them, the content used to add business meaning information to the data in the data source includes: content in the form of list variables, so that in the process of integrating prompt information, the prompt information is generated after determining the data of each row and column according to the row and column information defined in the list.

[0014] Among them, it also includes:

[0015] The data related to the target scenario queried from the data base table is expressed in the form of a chart and returned together with the conclusion content generated by the AI ​​model.

[0016] A data diagnostic device, comprising:

[0017] A data base table establishing unit, used to establish a data base table containing data source information corresponding to a plurality of data diagnosis scenarios;

[0018] A prompt information template configuration information acquisition unit, used to acquire prompt information template configuration information, wherein the prompt information template configuration information includes association relationship information between the prompt information template and the scene identifier; the prompt information template at least includes information describing the purpose of data diagnosis;

[0019] A data and template acquisition unit, configured to, upon receiving a request for data diagnosis for a target scene, query and acquire data corresponding to the target scene from the data base table, convert the data into a standard data structure, and determine a target prompt information template corresponding to the target scene according to the association relationship information in the prompt information template configuration information;

[0020] The prompt information integration unit is used to obtain prompt information by integrating the target prompt information template with the data expressed by the standard data structure corresponding to the target scene, and input the prompt information to the artificial intelligence AI model, so that the AI ​​model generates conclusion content that meets the corresponding data diagnosis purpose through data analysis.

[0021] Among them, the prompt information template also includes: content for adding business meaning information to the data in the data source, so that the AI ​​model generates the conclusion content based on understanding the business meaning of the data.

[0022] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any of the methods described above.

[0023] An electronic device, comprising:

[0024] one or more processors; and

[0025] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of any of the aforementioned methods.

[0026] A computer program product comprises a computer program / computer executable instructions, wherein the computer program / computer executable instructions implement the steps of any of the aforementioned methods when executed by a processor in an electronic device.

[0027] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0028] Through the embodiment of the present application, a data base table containing data source information corresponding to multiple data diagnosis scenarios can be pre-established; prompt information template configuration information is obtained, and the prompt information template configuration information includes the association relationship information between the prompt information template and the scenario identifier; the prompt information template at least includes information describing the purpose of data diagnosis. After receiving a request for data diagnosis for a target scenario, the data corresponding to the target scenario can be queried from the data base table, converted into a standard data structure, and the target prompt information template corresponding to the target scenario can be determined according to the association relationship information in the prompt information template configuration information. Then, the target prompt information template can be integrated with the data expressed by the standard data structure corresponding to the target scenario to obtain prompt information, and the prompt information can be input into the artificial intelligence AI model so that the AI ​​model generates conclusion content that meets the corresponding data diagnosis purpose through data analysis. In this way, since the setting of multi-scenario diagnosis Prompt can be realized through the solution of configuring the Prompt template, and data extraction from the data base table can be completed by writing a simple data query statement according to the specification, and the Prompt template and the extracted data are automatically constructed into a Prompt for a specific business scenario, the development cost is lower. Moreover, with the help of the content generation capability of the AI ​​model, it is possible to generate fluent diagnostic words and opinions in natural language, which provides a better user experience. In addition, through the configurable Prompt construction scheme, this scheme only requires simple development to complete the Prompt change, which has better scalability.

[0029] Of course, any product implementing the present application does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 It is a schematic diagram of the system architecture provided by the embodiment of the present application;

[0032] Figure 2 is a flow chart of the method provided in the embodiment of the present application;

[0033] Figure 3 It is a schematic diagram of the task processing flow provided by the embodiment of the present application;

[0034] Figure 4It is a schematic diagram of the process of performing task query on the front end provided in an embodiment of the present application;

[0035] Figure 5 is a schematic diagram of an interface provided by an embodiment of the present application;

[0036] Figure 6 is a schematic diagram of a device provided in an embodiment of the present application;

[0037] Figure 7 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of this application.

[0039] In order to reduce the cost of report delivery, one approach that can be considered is to directly map the diagnostic analysis language to the merchant's indicator keywords, and generate a multi-paragraph diagnostic conclusion through simple splicing. However, the problems with this approach are: (1) high development cost: it is necessary to define the diagnostic opinions of multiple indicators and language for mapping, and it is extremely complicated to exhaustively sort out the diagnostic opinions. It is necessary to match the indicators and language through methods such as manual coding keyword matching; (2) the language is not fluent: the fluency of natural language description cannot be guaranteed by simply splicing together the language points, and the merchant's understanding of the conclusion is in a dotted manner; (3) poor scalability: each new indicator requires the diagnostic opinions to be sorted and coded, which is not universal.

[0040] In view of the above situation, the embodiment of the present application provides an implementation scheme for realizing data diagnostic analysis and generating diagnostic opinions through the content generation capability of the AI ​​(Artificial Intelligence) model. Among them, the AI ​​model can generally refer to an AI large-scale parameter model (referred to as AI large model), which has natural language understanding, reasoning ability, and content generation ability. Therefore, the embodiment of the present application can realize data diagnostic services with the help of the above-mentioned capabilities of the AI ​​model. Among them, in the specific implementation, since it is usually necessary to first construct a prompt information (Prompt) in the process of calling the AI ​​model, and therefore, in the embodiment of the present application, the Prompt construction capability is also provided. Specifically, the public template capability can be precipitated by defining the Prompt template, and the Prompt template can at least include specific data diagnostic purposes and other information, which can be described in the form of text. In addition, since in the scenario of the embodiment of the present application, it is necessary to analyze and draw conclusions from the various data associated with the merchant, if these data are directly input to the AI ​​model, there may be a situation where the AI ​​model cannot understand these data, therefore, in an optional implementation method, it is also possible to provide content for adding business meaning information to specific data in the Prompt template, so that the AI ​​model generates conclusion content based on the understanding of the business meaning of the data. For example, these contents may exist in the form of parameter variables or lists. In a specific example, three types of Prompt templates may be defined: plain text type, text containing variable type template, text containing list type template, and so on.

[0041] In addition, when performing data diagnosis, it may be necessary to perform data diagnosis on a variety of different scenarios. For example, for the business type of "Leader Merchant" service report, specific scenarios may include export volume analysis, secondary category performance, industry red and blue ocean distribution, industry advantage blue ocean leaf category trends, store-wide business diagnosis, industry leader exclusive core equity data, traffic country, traffic channel, traffic conversion, commodity structure, destination product analysis, service summary, etc. Of course, in the specific implementation, in addition to the "Leader Merchant" service report, it can also be extended to other business types, and each business type may include a variety of specific scenarios. And in each scenario, which data needs to be analyzed may be different, and these data may also change. Therefore, in the specific implementation, in addition to providing the Prompt construction capability, a data base table can also be constructed in the embodiment of the present application, which can record the data source information corresponding to a variety of different scenarios, and can also update the data source of each scenario according to the preset cycle, for example, it can be updated every day, and so on.

[0042] Furthermore, since the data sources corresponding to different scenarios may be different, the data characteristics of different data sources may also be different. Some data may be relatively simple and do not require special processing. The AI ​​model can process it. In this case, you can configure a plain text Prompt template. Otherwise, if the data source is relatively complex, you can configure a text containing variable type template, a text containing list type template, etc. Therefore, when configuring the Prompt template, you can also configure the associated scenario identification information for the specific Prompt template, that is, you can configure the corresponding type of Prompt template according to the data characteristics of the data source associated with each scenario.

[0043] In this way, when it is necessary to perform data diagnosis on a specific scene, the data corresponding to the target scene can be queried from the data base table, converted into a standard data structure, and then the target Prompt template corresponding to the target scene can be determined according to the Prompt template configuration information. By integrating the target Prompt template with the data expressed in the standard data structure corresponding to the target scene, the complete prompt information, that is, Prompt, can be obtained. By inputting it into the AI ​​model, the AI ​​model can generate conclusions that meet the corresponding data diagnosis purpose through data analysis.

[0044] From the perspective of system architecture, see Figure 1 , the embodiment of the present application can provide data diagnosis services for merchant users in the commodity information service system. The service can provide Prompt templates and data base tables, which can contain data source information corresponding to multiple data diagnosis scenarios, and can update data according to a certain period. In addition, a diagnostic processor can be provided. When data diagnosis is required for a certain scene, the diagnostic task can be submitted through the diagnostic processor. Specifically, the specific relevant data can be first queried from the data base table and converted into a standard data structure, that is, a unified data structure can be used to express the queried data. After that, the Prompt template corresponding to the scene can be determined, and then the specific Prompt template can be integrated with the data to obtain a complete Prompt for input into the AI ​​model, so that the AI ​​model can generate conclusive content. Correspondingly, the diagnostic processor can return the diagnosis result.

[0045] The specific implementation scheme provided in the embodiments of the present application is described in detail below.

[0046] First, the present application embodiment provides a data diagnosis method, see Figure 2 , the method may specifically include:

[0047] S201: Establishing a data base table including data source information corresponding to a plurality of data diagnosis scenarios.

[0048] Specifically, a data table can be established in advance based on the data required for each scenario to be diagnosed. The data source information corresponding to each diagnostic scenario can be saved in the data table. For example, a scenario needs to be analyzed based on data related to export and foreign trade. The specific data source can include fields such as date and export amount. This information related to specific merchants can be saved in the data table. In addition, since new data may be continuously generated in the system, the data in the data table can also be updated according to a certain preset cycle, for example, the above export amount data is updated every day, and so on.

[0049] In specific implementation, the data source can be defined in multiple ways. For example, in one way, it can be as shown in Table 1:

[0050] Table 1

[0051]

[0052]

[0053] That is to say, the specific data source may include a data source of common parameter type data, and may also include a data source of list type data.

[0054] S202: Acquire prompt information template configuration information, wherein the prompt information template configuration information includes association relationship information between the prompt information template and the scene identifier; the prompt information template at least includes information describing the purpose of data diagnosis.

[0055] In addition to establishing a data base table, you can also configure a Prompt template. The specific Prompt template can be associated with a scene identifier. For example, in a specific implementation, the basic form of a Prompt template can be a mapping of bizCode and Value (configuration template parameter object), where bizCode identifies the business scenario code, and Value is the configured template parameter, where sceneDesc is the scene description information, dataKey is used to represent the replacement key of the data, promptTemplate is the Prompt template, and promptDataItemTemplate represents the list type of Prompt template entry.

[0056] In specific implementation, the Prompt template may at least include information describing the purpose of data diagnosis, that is, instructions to the AI ​​model, which can be described in the form of text, for example, "International station market analysis, give a concise conclusion". In addition, since the data of some data sources may be complex and not easy for the AI ​​model to understand, it is also possible to configure a Prompt template containing ordinary parameter variables, or a Prompt template containing list variables, to give the data in the data source corresponding business meanings. In other words, the specific Prompt template may also include: content for adding business meaning information to the data in the data source, so that the AI ​​model generates the conclusion content based on the understanding of the business meaning of the data. Among them, it may specifically include content in the form of parameter variables, so that in the process of integrating prompt information, the data of the corresponding parameters is determined according to the data pulled from the data base table, so as to generate the prompt information. Or, content in the form of list variables, so that in the process of integrating prompt information, according to the row and column information defined in the list, the data of each row and column is determined, and then the prompt information is generated.

[0057] That is to say, in the specific implementation, there can be multiple Prompt templates, including a plain text Prompt template, that is, a pure instruction type Prompt template that does not contain variables. Alternatively, there can be a Prompt template containing ordinary parameter variables, and a Prompt template with list variables. Of course, the same Prompt template can also include both ordinary parameter variables and list variables, and so on.

[0058] In order to better understand the various types of Prompt templates, examples are given below.

[0059] 1. The plain text type Prompt template can be configured as follows:

[0060] "INDUSTRY_DIAGNOSIS_INDUSTRY_TRENDS":{

[0061] "sceneDesc":"Industry & Category Trends",

[0062] "dataKey":"",

[0063] "promptTemplate":"International station market analysis, give a concise conclusion, market size, positive trend, export trade, trade growth, market prospects, industry trends",

[0064] "promptDataItemTemplate":""

[0065] }

[0066] 2. The Prompt template containing common parameter variables can be configured as follows:

[0067] "INDUSTRY_DIAGNOSIS_INDUSTRY_TRENDS":{

[0068] "sceneDesc":"Industry & Category Trends",

[0069] "dataKey":"",

[0070] "promptTemplate":"International station ${cate_lv1_cn_desc}Industry trend data:\nOffline export dataThis year's cumulative export current value${offlineExport}US dollarsYear-on-year${offlineExportYoy}ProportionFirst-level industry share${offlineExportPercentage}\nIndustry operating dataThe current value of the average AB3 of merchants in the past three months is${l1BuyerNumber}Year-on-year${l1BuyerNumberYoy}Month-on-month${l1BuyerNumberQoq}\nInternational station demand daily average AB3 current value${ab3BuyerNumber}Year-on-year${ab3BuyerNumberYoy}Month-on-month${ab3BuyerNumberQoq}\nPlease give a concise conclusion based on the above data, market size, positive trend, export trade, trade growth, market prospects, industry trends",

[0071] "promptDataItemTemplate":""

[0072] }

[0073] Among them, "this year's cumulative export current value", "year-on-year", "share of the first-level industry", "current average AB3 value of the last three months", "month-on-month", etc. are all keys for specific parameters, and "${offlineExport}", "${offlineExportYoy}", etc. are values ​​to be replaced.

[0074] 3. The Prompt template containing list-type variables can be configured as follows (the following Prompt template contains both common variable-type data sources and list-type variables (such as the format configured in promptDataItemTemplate)):

[0075] "INDUSTRY_DIAGNOSIS_ALIBABA_REQIREMENT":{

[0076] "sceneDesc":"Industry Leaders' First Diagnosis Report International Station Demand Analysis",

[0077] "dataKey":"alibabaRequirement",

[0078] "promptTemplate":"The merchant's industry is ${cate_lv1_cn_desc}, and the international site demand data is:\nThe daily average number of buyers is ${l1BuyerNumber}, the year-on-year ${l1BuyerNumberYoy}, and the month-on-month ${l1BuyerNumberQoq}\nThe daily average of AB3 scale is ${ab3BuyerNumber}, the year-on-year ${ab3BuyerNumberYoy}, and the month-on-month ${ab3BuyerNumberQoq}\n${alibabaRequirement}\nPlease give a brief and clear analysis conclusion based on the above data, and the analysis conclusion should be concisely summarized",

[0079] "promptDataItemTemplate":"${month}Month buyer dataBuyer number${duvValue}L1 buyer number${l1BuyerNumber}AB3 scale${ab3BuyerNumber}"

[0080] }

[0081] S203: After receiving a request for data diagnosis for a target scenario, query and obtain data corresponding to the target scenario from the data base table, convert it into a standard data structure, and determine the target prompt information template corresponding to the target scenario according to the association relationship information in the prompt information template configuration information.

[0082] Since the data base table and Prompt template are pre-configured, after receiving a request for data diagnosis for a target scenario, the data corresponding to the target scenario can be first queried from the data base table and converted into a standard data structure. In other words, different scenarios correspond to different data sources, but they can all be converted into a unified data structure for integration with the Prompt template. In addition to extracting specific data, the corresponding target Prompt template can also be determined based on specific scenario identification and other information.

[0083] S204: Obtain prompt information by integrating the target prompt information template with the data expressed by the standard data structure corresponding to the target scene, and input the prompt information into the artificial intelligence AI model, so that the AI ​​model generates conclusion content that meets the corresponding data diagnosis purpose through data analysis.

[0084] After determining the target Prompt template and extracting the specific data, the two can be integrated to generate a complete Prompt. It should be noted here that whether the Prompt template contains ordinary parameter-type variables or list-type variables, after being integrated with the data, the generated Prompt can exist in the form of text. Afterwards, the generated Prompt can be input into the AI ​​model. Accordingly, the AI ​​model can analyze and process the specific data, and generate corresponding conclusive content according to the instruction information such as the analysis purpose included in the specific Prompt.

[0085] It should be noted that, in an optional manner, the embodiment of the present application can implement the function of streaming result query based on distributed cache. Figure 3 As shown in the figure, first, during diagnosis, the merchant side can trigger a request, which can generate a task ID, which will be returned to the front end. Then, after the AI ​​model streaming output results are connected through the model adaptation module, the interim results generated by the streaming are directly cached. Finally, as Figure 4 As shown, the front end directly queries the cached data corresponding to the current task through the task ID, which is the staged streaming output result. If it exists, the diagnostic conclusion generated in the current stage is directly returned. The use of quasi-streaming output here is mainly to solve the problem of slow AI model generation speed and avoid long waiting time during user use. This implementation method is equivalent to the front-end page continuously actively pulling to continuously output and present the generated intermediate results, reducing the user's waiting time, until the back-end has received the streaming content, and informs the front-end through the identifier that the streaming generation result has been completed, at which time the front-end will end data pulling. Asynchronous streaming output is achieved through this distributed cache, and the query efficiency can be accelerated by caching the results, which is beneficial to improving the user experience.

[0086] The conclusive content generated by the specific AI model may exist in the form of text, or may generate other types of content. In addition, in addition to generating conclusive content through the AI ​​model, the data related to the target scenario queried from the data base table may be expressed in the form of a chart by accessing an existing interface, and returned together with the conclusive content generated by the AI ​​model. For example, Figure 5As shown in the figure, for the scenario of "main first-level category performance", the conclusions generated by the AI ​​model can include two aspects: "offline export analysis" and "international site demand analysis". Figure 3 The text content shown may be the specific content generated by the AI ​​model. In addition, it may also include the change curve of "export volume", the change curve of parameters such as "visitor scale index", "L1+ buyer scale index", "deep communication scale index", etc. Among them, the parameter information shown in the above specific charts may be related to the data used in the data analysis process of the AI ​​model.

[0087] In summary, through the embodiment of the present application, a data base table containing data source information corresponding to multiple data diagnosis scenarios can be pre-established; prompt information template configuration information is obtained, and the prompt information template configuration information includes the association relationship information between the prompt information template and the scenario identifier; the prompt information template at least includes information describing the purpose of data diagnosis. After receiving a request for data diagnosis for a target scenario, the data corresponding to the target scenario can be queried from the data base table, converted into a standard data structure, and the target prompt information template corresponding to the target scenario can be determined according to the association relationship information in the prompt information template configuration information. Then, the target prompt information template can be integrated with the data expressed by the standard data structure corresponding to the target scenario to obtain prompt information, and the prompt information can be input into the artificial intelligence AI model so that the AI ​​model generates conclusion content that meets the corresponding data diagnosis purpose through data analysis. In this way, since the setting of multi-scenario diagnosis Prompt can be realized through the solution of configuring the Prompt template, and data extraction from the data base table can be completed by writing simple data query statements according to the specifications, and the Prompt template and the extracted data are automatically constructed into a Prompt for a specific business scenario, the development cost is lower. Moreover, with the help of the content generation capability of the AI ​​model, it is possible to generate fluent diagnostic words and opinions in natural language, which provides a better user experience. In addition, through the configurable Prompt construction scheme, this scheme only requires simple development to complete the Prompt change, which has better scalability.

[0088] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the scheme described herein within the scope permitted by applicable laws and regulations, subject to the requirements of applicable laws and regulations of the country where the user is located (for example, with the user's explicit consent, effective notification to the user, etc.).

[0089] Corresponding to the method embodiment provided in the embodiment of the present application, the embodiment of the present application also provides a data diagnosis device, see Figure 6 , the device may include:

[0090] A data base table establishing unit 601 is used to establish a data base table containing data source information corresponding to a plurality of data diagnosis scenarios;

[0091] The prompt information template configuration information acquisition unit 602 is used to acquire prompt information template configuration information, wherein the prompt information template configuration information includes association relationship information between the prompt information template and the scene identifier; the prompt information template at least includes information describing the purpose of data diagnosis;

[0092] The data and template acquisition unit 603 is used to, after receiving a request for data diagnosis for a target scene, query and obtain data corresponding to the target scene from the data base table, convert the data into a standard data structure, and determine the target prompt information template corresponding to the target scene according to the association relationship information in the prompt information template configuration information;

[0093] The prompt information integration unit 604 is used to obtain prompt information by integrating the target prompt information template with the data expressed by the standard data structure corresponding to the target scene, and input the prompt information to the artificial intelligence AI model, so that the AI ​​model generates conclusion content that meets the corresponding data diagnosis purpose through data analysis.

[0094] In a specific implementation, the prompt information template may also include: content for adding business meaning information to the data in the data source, so that the AI ​​model generates the conclusion content based on understanding the business meaning of the data.

[0095] Among them, the content used to add business meaning information to the data in the data source can specifically include: content in the form of parameter variables, so that in the process of integrating prompt information, the data of the corresponding parameters can be determined according to the data pulled from the data base table to generate the prompt information.

[0096] Alternatively, the content used to add business meaning information to the data in the data source includes: content in the form of list variables, so that in the process of integrating prompt information, the prompt information is generated after determining the data in each row and column according to the row and column information defined in the list.

[0097] In addition, the device may also include:

[0098] A chart display unit is used to express the data related to the target scenario queried from the data base table in the form of a chart, and return it together with the conclusion content generated by the AI ​​model.

[0099] In addition, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0100] And an electronic device, comprising:

[0101] one or more processors; and

[0102] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of the method described in any one of the aforementioned method embodiments.

[0103] A computer program product includes a computer program / computer executable instructions, which, when executed by a processor in an electronic device, implement the steps of the method described in the aforementioned method embodiment.

[0104] in, Figure 7 The architecture of the electronic device is shown as an example, which may include a processor 710, a video display adapter 711, a disk drive 712, an input / output interface 713, a network interface 714, and a memory 720. The processor 710, the video display adapter 711, the disk drive 712, the input / output interface 713, the network interface 714, and the memory 720 may be communicatively connected via a communication bus 730.

[0105] Among them, the processor 710 can be implemented by a general-purpose CPU (Central Processing Unit, processor), a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc., to execute relevant programs to implement the technical solution provided in this application.

[0106] The memory 720 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 720 can store an operating system 721 for controlling the operation of the electronic device 700, and a basic input and output system (BIOS) for controlling the low-level operation of the electronic device 700. In addition, a web browser 723, a data storage management system 724, and a data diagnosis processing system 725, etc. can also be stored. The above-mentioned data diagnosis processing system 725 can be an application program that specifically implements the aforementioned steps in the embodiment of the present application. In short, when the technical solution provided by the present application is implemented by software or firmware, the relevant program code is stored in the memory 720 and is called and executed by the processor 710.

[0107] The input / output interface 713 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0108] The network interface 714 is used to connect to a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0109] The bus 730 comprises a pathway for transmitting information between the various components of the device (eg, the processor 710, the video display adapter 711, the disk drive 712, the input / output interface 713, the network interface 714, and the memory 720).

[0110] It should be noted that, although the above device only shows a processor 710, a video display adapter 711, a disk drive 712, an input / output interface 713, a network interface 714, a memory 720, a bus 730, etc., in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include components necessary for implementing the solution of the present application, and does not necessarily include all the components shown in the figure.

[0111] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0112] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0113] The data diagnosis method, device and electronic device provided by the present application are described in detail above. The principles and implementation methods of the present application are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A data diagnosis method, characterized in that: include: Establish a data base table containing data source information corresponding to multiple data diagnosis scenarios; Acquire prompt information template configuration information, wherein the prompt information template configuration information includes association relationship information between the prompt information template and the scene identifier; the prompt information template at least includes information describing the purpose of data diagnosis; After receiving a request for data diagnosis for a target scene, query and obtain data corresponding to the target scene from the data base table, convert the data into a standard data structure, and determine a target prompt information template corresponding to the target scene according to the association relationship information in the prompt information template configuration information; The prompt information is obtained by integrating the target prompt information template with the data expressed by the standard data structure corresponding to the target scene, and the prompt information is input into the artificial intelligence AI model, so that the AI ​​model generates conclusion content that meets the corresponding data diagnosis purpose through data analysis.

2. The method according to claim 1, characterized in that The prompt information template also includes: content for adding business meaning information to the data in the data source, so that the AI ​​model generates the conclusion content based on understanding the business meaning of the data.

3. The method according to claim 2, characterized in that The content used to add business meaning information to the data in the data source includes: content in the form of parameter variables, so that in the process of integrating prompt information, the data corresponding to the parameters is determined according to the data pulled from the data base table to generate the prompt information.

4. The method according to claim 2, characterized in that: The content used to add business meaning information to the data in the data source includes: content in the form of list variables, so that in the process of integrating prompt information, the prompt information is generated after determining the data in each row and column according to the row and column information defined in the list.

5. The method according to claim 1, characterized in that Also includes: The data related to the target scenario queried from the data base table is expressed in the form of a chart and returned together with the conclusion content generated by the AI ​​model.

6. A data diagnostic device, characterized in that: include: A data base table establishing unit, used to establish a data base table containing data source information corresponding to a plurality of data diagnosis scenarios; A prompt information template configuration information acquisition unit, used to acquire prompt information template configuration information, wherein the prompt information template configuration information includes association relationship information between the prompt information template and the scene identifier; The prompt information template at least includes information describing the purpose of data diagnosis; A data and template acquisition unit, configured to, upon receiving a request for data diagnosis for a target scene, query and acquire data corresponding to the target scene from the data base table, convert the data into a standard data structure, and determine a target prompt information template corresponding to the target scene according to the association relationship information in the prompt information template configuration information; The prompt information integration unit is used to obtain prompt information by integrating the target prompt information template with the data expressed by the standard data structure corresponding to the target scene, and input the prompt information to the artificial intelligence AI model, so that the AI ​​model generates conclusion content that meets the corresponding data diagnosis purpose through data analysis.

7. The device according to claim 6, characterized in that The prompt information template also includes: content for adding business meaning information to the data in the data source, so that the AI ​​model generates the conclusion content based on understanding the business meaning of the data.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 5 are implemented.

9. An electronic device, characterized in that: include: one or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions, wherein when the program instructions are read and executed by the one or more processors, the steps of the method according to any one of claims 1 to 5 are executed.

10. A computer program product comprising a computer program / computer executable instructions, characterized in that: The computer program / computer executable instructions implement the steps of the method according to any one of claims 1 to 5 when executed by a processor in an electronic device.

Images