Data processing method and system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a data processing method and system, electronic equipment, a storage medium and a computer program product. The method comprises the steps that a server side responds to a data operation request sent by a client side, the data operation request is analyzed, and request parameters are acquired; performing user intention recognition on a data operation session text carried in the request parameter through a chat generation type pre-training transformation model to obtain an intention recognition result; and converting the intention recognition result based on application logic to obtain a structured parameter, calling a preset data service based on the structured parameter, and obtaining a data processing result corresponding to the data operation session text. Compared with the prior art in which a user manually obtains and analyzes data by operating a database or operating tools corresponding to different product function points, the method has the advantage that the efficiency and accuracy of data processing are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method, a data processing system, an electronic device, a storage medium and a computer program product. Background Art

[0002] Merchants on e-commerce websites will accumulate a large amount of scenario data in various intermediate links of operating stores, including but not limited to one or more of the following: product click data, inquiry data, communication data, transaction data, fulfillment and logistics data, etc. For merchants, they can understand the store's own operating status and assist in decision-making based on the above data. For platforms, they can obtain industry information or merchant reports based on the above data. In the prior art, the above scenario data and analysis results can be obtained by the following methods: merchant users or platform users develop programs to read complex database tables, obtain various data respectively, and then analyze and process the data; or, merchant users or platforms industrialize scenario data to obtain data reading and analysis tools corresponding to different functions.

[0003] However, the above-mentioned data acquisition and analysis methods in the prior art require users to manually acquire and analyze data by operating databases or operating tools corresponding to different product functional points. Not only is the efficiency of data acquisition and analysis low, but the accuracy of data processing cannot be guaranteed in the face of complex data. Summary of the invention

[0004] The embodiment of the present application provides a data processing method, which can improve the efficiency and accuracy of data processing.

[0005] Correspondingly, an embodiment of the present application also provides a data processing method, a data processing system, an electronic device, a storage medium and a computer program product to ensure the implementation and application of the above-mentioned data processing method.

[0006] In order to solve the above problems, the embodiment of the present application discloses a data processing method, which is applied to the server, and the method includes:

[0007] In response to a data operation request sent by a client, the data operation request is parsed to obtain request parameters;

[0008] Performing user intent recognition on the data operation conversation text carried in the request parameter through a chat generation pre-trained transformation model to obtain an intent recognition result;

[0009] Converting the intention recognition result based on application logic to obtain structured parameters;

[0010] The preset data service is called based on the structured parameters to obtain the data processing result corresponding to the data operation conversation text.

[0011] The present application embodiment discloses a data processing method, which is applied to a client, and the method includes:

[0012] In response to a user triggering a preset data operation, obtaining a data operation conversation text input by the user;

[0013] Generate a data operation request based on the data operation session text;

[0014] Sending the data operation request to a preset server to trigger the preset server to perform a first data processing operation, wherein the first data processing operation includes: responding to the data operation request sent by the client, parsing the data operation request and obtaining request parameters; performing user intent recognition on the data operation conversation text carried in the request parameters through a chat generation pre-trained transformation model to obtain intent recognition results; performing conversion processing on the intent recognition results based on application logic to obtain structured parameters; calling a preset data service based on the structured parameters to obtain a data processing result corresponding to the data operation conversation text;

[0015] Obtain and display the data processing results.

[0016] The embodiment of the present application discloses a data processing system, including: a client and a server, wherein the server further includes: an intelligent arrangement module, a data service gateway and a plurality of preset data services,

[0017] The client is used for acquiring a data operation session text input by the user in response to the user triggering a preset data operation, and generating a data operation request based on the data operation session text;

[0018] The client is further used to send the data operation request to the intelligent orchestration module;

[0019] The intelligent orchestration module is used to respond to the data operation request sent by the client, parse the data operation request, obtain the request parameters, and then perform user intent recognition on the data operation conversation text carried in the request parameters through the chat generation pre-trained transformation model to obtain the intent recognition result, and transform the intent recognition result based on the application logic to obtain the structured parameters;

[0020] The intelligent orchestration module is further used to access the data service gateway based on the structured parameters;

[0021] The data service gateway is further used to call the preset data service based on the structured parameter to obtain the data processing result corresponding to the data operation session text;

[0022] The client is also used to obtain and display the data processing results.

[0023] The embodiment of the present application further discloses a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method described in the embodiment of the present application.

[0024] The embodiment of the present application also discloses a computer program product, including a computer program / computer executable instructions, characterized in that when the computer program / computer executable instructions are executed by a processor in an electronic device, the method described in the embodiment of the present application is implemented.

[0025] Compared with the prior art, the embodiments of the present application have the following advantages:

[0026] The server responds to the data operation request sent by the client, parses the data operation request, obtains the request parameters, and then uses the chat generation pre-trained transformation model to identify the user intention of the data operation conversation text carried in the request parameters to obtain the intention recognition result; then, an engineering link is used to transform the intention recognition result based on the application logic to obtain structured parameters, and the preset data service is called based on the structured parameters to obtain the data processing result corresponding to the data operation conversation text. Compared with the prior art in which users manually obtain and analyze data by operating the database or operating the tools corresponding to different product function points, the efficiency and accuracy of data processing are effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is one of the step flow charts of the data processing method disclosed in the embodiment of the present application;

[0028] Figure 2 It is a schematic diagram of the structure of the data processing system disclosed in the embodiment of the present application;

[0029] Figure 3 This is the second step flow chart of the data processing method disclosed in the embodiment of the present application;

[0030] Figure 4 This is the third step flow chart of the data processing method disclosed in the embodiment of the present application;

[0031] Figure 5 This is the fourth step flow chart of the data processing method disclosed in the embodiment of the present application;

[0032] Figure 6It is a schematic diagram of a specific implementation architecture of the data processing system disclosed in the embodiment of the present application;

[0033] Figure 7 It is a schematic diagram of the structure of an exemplary device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0035] In the prior art, the data provided by e-commerce platforms are mostly split into various product function items in the form of word / product / person and store / industry combinations. When merchants want to understand their own and industry performance, they need to query and summarize data from multiple function items, and the data acquisition efficiency is low. On the other hand, for platform data processing personnel, when analyzing platform trends, they need to search for specified database tables in the database, and use intelligent tools or write database operation statements to process data. This requires high data processing technical capabilities of platform data processing personnel, and they often encounter problems such as inconsistent indicator caliber and missing indicators, resulting in inaccurate data processing results.

[0036] The data processing method disclosed in the embodiment of the present application uses a free dialogue to understand the user's intention through a large model, calls the corresponding data processing tool through the ability of an artificial intelligence entity, and finally returns the data processing result to the user after summarizing the data processing result through a large model, thereby eliminating the cost of the user to obtain data through database operations or product function points, thereby improving data acquisition efficiency. Moreover, during the entire data acquisition process, users who use data only need to enter query text, which not only has high data acquisition efficiency, but also the data acquisition operation is completed through a preset data processing tool, and the reliability and accuracy of the acquired data are higher.

[0037] The data processing method disclosed in the embodiment of the present application is applied to the server side of the data processing system. Figure 2As shown, the data processing system includes: a client and a server. The server further includes: an intelligent orchestration module, a data service gateway, and an application pool, wherein the application pool includes multiple preset data services. Among them, the client obtains the data operation conversation text input by the user, obtains the preset data operation selected by the user, and displays the obtained data processing results by displaying the human-computer conversation interface. On the other hand, the client is also used to configure the basic information such as the call interface name, interface protocol, interface parameter mapping, parameter description, interface return result description of the data service, and publish the data service to the application pool. The preset data service can be deployed on the server in the form of an application program, and the preset data service is used to query the database table based on the data query statement, perform data analysis, and generate data processing results. The data service gateway is used to dispatch the data operation request to the corresponding preset data service in the application pool according to the parameters carried in the data operation request sent by the client to obtain the data processing result.

[0038] The following further illustrates a specific solution for implementing the data processing method on the server side of the data processing system.

[0039] Reference Figure 1 , the data processing method includes: steps 102 to 108.

[0040] Step 102: In response to the data operation request sent by the client, the data operation request is parsed to obtain request parameters.

[0041] In specific implementation, the server parses the data operation request according to the communication protocol with the client and the format information of the data operation request to obtain the request parameters of the data operation request. In the embodiment of the present application, the specific implementation method of parsing the data operation request and obtaining the request parameters is not limited.

[0042] Optionally, the request parameters include, but are not limited to, one or more of the following: a client identifier, a data operation session text, an operation identifier indicating whether the data operation request matches a preset data operation, etc.

[0043] For example, a plurality of preset data operations are predefined on the server side, and the data processing results corresponding to each preset data operation are pre-generated and stored, and the operation identifier corresponding to each preset data operation is set. Accordingly, a data operation list can be set on the client side, and each table item in the list corresponds to a preset data operation. The user can select the preset data operation to be currently executed through the data operation list. After the user selects a preset data operation, the client generates a data operation request with the operation identifier corresponding to the preset data operation selected by the user as a request parameter, and sends the generated data operation request to the server side. After receiving the data operation request sent by the client, the server side can obtain the operation identifier of the preset data operation as a request parameter by parsing the data operation request.

[0044] For another example, the client is provided with an edit box for data operation session text, and the user can enter the data operation session text in the edit box to describe the current data operation requirements, and then trigger the data query function button, thereby triggering the client to generate a data operation request with the data operation session text entered in the edit box as a request parameter, and send the data operation request to the server. After receiving the data operation request sent by the client, the server can obtain the data operation session text as a request parameter by parsing the data operation request.

[0045] Step 104: Use a chat generation pre-trained transformation model to perform user intent recognition on the data operation conversation text carried in the request parameter to obtain an intent recognition result.

[0046] In an embodiment of the present application, the chat generative pre-trained transformation model may be a version such as ChatGPT4.0 (Chat Generative Pre-trained Transformer).

[0047] In some optional embodiments, the method of performing user intent recognition on the data operation conversation text carried in the request parameters through a chat generation-based pre-trained transformation model to obtain an intent recognition result includes: identifying, through a chat generation-based pre-trained transformation model, a query intent matching the data operation conversation text carried in the request parameters; performing query parameter extraction on the data operation conversation text through the chat generation-based pre-trained transformation model to obtain query parameters; and using the query intent and the query parameters as an intent recognition result.

[0048] The query intent is determined according to a specific query scenario. Taking an e-commerce scenario as an example, the query intent includes but is not limited to any of the following: querying data such as market, region, commodity, store, industry trend, etc. The query parameter matches the query intent.

[0049] In some optional embodiments, a prompt word can be generated according to the data operation conversation text carried in the request parameter, and the chat generation type pre-trained transformation model can be called based on the prompt word to trigger the chat generation type pre-trained transformation model to generate a query intent according to the data operation conversation text.

[0050] Optionally, multiple query intentions can be pre-set according to specific application scenarios, and then the chat generation pre-trained transformation model is triggered to identify the query intention that matches the data operation session text from the preset query intentions.

[0051] Afterwards, a prompt word is generated according to the data operation conversation text carried in the request parameter, and the chat generation type pre-trained transformation model is called based on the prompt word, triggering the chat generation type pre-trained transformation model to extract a query parameter of a preset parameter type from the data operation conversation text. For example, the chat generation type pre-trained transformation model is triggered to extract query parameters such as time period and industry name from the data operation conversation text.

[0052] Taking ChatGPT4.0, a chat generation pre-trained transformation model, as an example, the data operation conversation text "Which third-level industries under the category of drinkware and accessories have a large number of inquiries" carried in the request parameter is used as the question input by the user, triggering the chat generation pre-trained transformation model to identify the data field currently inquired by the user, determine the type of question the user asks, and as the query intention, the query intention can be obtained as "check the market". On the other hand, the chat generation pre-trained transformation model can also be called to extract the query parameters for calling the data service from the data operation conversation text, thereby obtaining the conditional parameters therein: such as the category parameter "drinkware and accessories", the sorting parameter, i.e. the sorting indicator "inquiry volume" and the sorting rule "descending", and the result parameter "third-level industry".

[0053] In some optional embodiments, the query intent may also affect the query parameters, that is, different query parameters are required when querying different data sources. For example, a prompt word may be generated according to the data operation conversation text carried in the request parameter and the generated query intent, and the chat generation type pre-trained transformation model may be called based on the prompt word to trigger the chat generation type pre-trained transformation model to extract query parameters of a preset parameter type that matches the query intent from the data operation conversation text.

[0054] Next, the query intent and the query parameters may be used together as an intent recognition result obtained from the data operation session text.

[0055] Step 106: transform the intention recognition result based on application logic to obtain structured parameters.

[0056] The query intent, query parameters and other intent recognition results generated by the chat generation pre-trained transformation model in the above steps are semi-structured parameters, which include parameters that cannot be recognized and processed by the preset data service and cannot be directly used to query the data source. It is necessary to further transform the intent recognition results to obtain structured parameters that can be processed by the preset data service.

[0057] For example, there is no value such as "drinkware and accessories" in the data source, only a specific category identification (such as cate_id). Therefore, if the query parameter "drinkware and accessories" parsed by the chat generation type pre-trained transformation model is directly transmitted to the preset data service to query the data source, the preset data service cannot obtain data matching the query parameter, and the query parameter "drinkware and accessories" generated by the chat generation type pre-trained transformation model must be converted into the operation indicator name "cate_id" recognized by the preset data service.

[0058] In an embodiment of the present application, an engineering link is used to perform subsequent processing on the intent recognition result, so as to obtain the data to be queried. For example, the intent recognition result is sent to a pre-set data service, which determines the target data source according to the query intent type (such as market query), searches for indicators according to indicator descriptions (such as inquiry volume, tertiary industry), retrieves the indicator name, converts semi-structured parameters into built-in parameters that can be recognized by the preset data service (such as converting "drinking utensils and accessories" into category id), and assigns values ​​to the built-in parameters to finally obtain structured parameters. The structured parameters are pre-configured interface parameters for the data service gateway and the preset data service.

[0059] In some optional embodiments, the intent recognition result includes: query intent and query parameters, and the intent recognition result is converted based on application logic to obtain structured parameters, including: sub-step S1, sub-step S2 and sub-step S3.

[0060] Sub-step S1, determining the query data source corresponding to the query intent according to the preset application logic.

[0061] Among them, the query data source corresponding to the query intent is pre-set according to specific application requirements, and the embodiment of the present application does not limit the application logic for determining the query data source corresponding to the query intent.

[0062] Sub-step S2, searching and converting the query parameters according to the preset application logic and based on the preset indicator library to obtain database operation parameters corresponding to the query parameters.

[0063] Optionally, the preset indicator library includes: relationship pairs of operation indicator names and indicator descriptions.

[0064] When this application is implemented, it is first necessary to enter the relevant operation indicators of the data to be queried into the indicator library in the form of metadata in advance according to the data range supported by the data processing system and the preset application logic to generate a preset indicator library. For example, the industry, number of inquiries, number of clicks, number of visitors, number of orders and other indicators are stored in the database in the form of a relationship pair between the operation indicator name and the indicator description for subsequent indicator retrieval. Among them, the relationship pair between the operation indicator name and the indicator description can be expressed as: (operation indicator name, indicator description).

[0065] For example, establish a corresponding relationship between the indicator description "category search" and the operation indicator name "cate_id", establish a corresponding relationship between the indicator description "inquiry volume search" and the operation indicator name "fb_cnt", and establish a corresponding relationship between the indicator description "third-level category search" and the operation indicator name "cate_lv3_id". After that, store the established corresponding relationship in the preset indicator library.

[0066] In an embodiment of the present application, the query parameters that do not meet the requirements of the calling interface of the preset data service are used as query parameters that need to be converted, and the query parameters that need to be converted are converted based on the preset index library, and the query parameters that do not meet the requirements of the access interface of the data service gateway and the calling interface of the preset data service are converted into a form that meets the requirements of the access interface of the data service gateway and the calling interface of the preset data service. For example, the country name extracted from the data operation session text is converted into the country code built into the preset data service, and the commodity category name extracted from the data operation session text is converted into the category identification built into the preset data service.

[0067] In some optional embodiments, the preset indicator library includes: a relationship pair between an operation indicator name and an indicator description, and the query parameters are searched and transformed based on the preset indicator library according to the preset application logic to obtain database operation parameters corresponding to the query parameters, including: searching the relationship pair with the query parameters as the indicator description to obtain the operation indicator name that matches the query parameters; and assigning a value to the operation indicator name to obtain the database operation parameters.

[0068] During the operation of the system, after obtaining the data processing parameters, first, by comparing the query parameters that need to be converted (for example, recorded as "target query parameters") with the indicator descriptions in the preset indicator library, the indicator descriptions that match the target query parameters are obtained. Then, according to the corresponding relationship, the operation indicator name corresponding to the indicator description that matches the target query parameter is used as the operation indicator name corresponding to the target query parameter. Taking the query parameters obtained by user intent recognition based on the data operation conversation text including "inquiry volume retrieval" as an example, by searching the aforementioned preset indicator library, the operation indicator name corresponding to the query parameter "inquiry volume retrieval" can be obtained as "fb_cnt".

[0069] By searching the preset indicator library, the operation indicator name corresponding to the query parameter to be converted can be obtained, and the operation indicator name is the interface parameter supported by the data service to be called.

[0070] Furthermore, default parameter values ​​or query parameters identified in the intent recognition results may be used to assign values ​​to operation indicator names corresponding to the converted query parameters to obtain database operation parameters.

[0071] Among them, the default parameter value can be determined according to the specific application scenario.

[0072] During the specific implementation process, the data operation conversation text input by the user may include parameter values ​​required for the data processing operation, or may not include parameter values ​​required for the data processing parameters. For example, when the data operation conversation text input by the user is "query the order change trend of commodity A in the past month", the data operation conversation text is subjected to intent recognition, and the query parameters obtained include "order change trend" and "commodity A". At the same time, it also includes the query parameter "in the past month" as a time period, wherein the query parameter "in the past month" is the time period of the query parameter "order change trend". For another example, when the data operation conversation text input by the user is "query the order change trend of commodity A", the data operation conversation text is subjected to intent recognition, and the query parameters obtained include "order change trend" and "commodity A". In this case, it is necessary to assign a default time period to the query parameter "order change trend", such as 30 days.

[0073] During the specific implementation, there is no need to perform conversion processing on the query parameters that can be identified by the preset data service.

[0074] Sub-step S3, acquiring structured parameters based on the query data source and the database operation parameters.

[0075] Next, the query data source and the database operation parameters may be assembled according to the interface parameter rules of the data service to generate structured parameters that meet the calling requirements of the data service interface.

[0076] Step 108: Calling a preset data service based on the structured parameters to obtain a data processing result corresponding to the data operation conversation text.

[0077] In some optional embodiments, the server also includes: a data service gateway and a preset data service, and calling the preset data service based on the structured parameters to obtain the data processing result corresponding to the data operation session text includes: accessing the data service gateway based on the structured parameters, and the data service gateway addressing the preset data service according to the structured parameters, and calling the addressed preset data service to obtain data; using the obtained data as the data processing result corresponding to the data operation session text.

[0078] The structured parameters include: the query data source and the database operation parameters. Optionally, the data service gateway addresses the preset data service according to the structured parameters, including: the data service gateway addresses the preset data service based on the query data source as the target data service, and then calls the target preset data service based on the database operation parameters to obtain data.

[0079] Optionally, the operator configures the call identifier, interface parameters, interface parameter mapping relationship, and interface protocol of the preset data service by the data service gateway in advance through the client of the data processing system, and publishes the preset data service to the application pool of the data processing system. When the data service gateway receives the database operation parameters sent by the client, the data service gateway first selects the preset data service from the application pool according to the query intent in the database operation parameters as the target data service to be called; then, the data service gateway maps the query parameter network in the database operation parameters according to the interface parameter mapping relationship to obtain the interface parameters of the target data service; finally, the data service gateway calls the target data service based on the mapped interface parameters, thereby forwarding the data query request to the target data service.

[0080] The target data service performs data reading and analysis operations according to the interface parameters, generates data processing results, and outputs the generated data processing results to the corresponding client.

[0081] In the embodiments of the present application, different data services access the specified data source and perform preset database query operations and data analysis and processing operations based on the specified interface parameters to obtain data processing results. Among them, the specific implementation scheme of the preset data service is the prior art and will not be repeated in the embodiments of the present application.

[0082] In summary, the data processing method disclosed in the embodiment of the present application is that the server responds to the data operation request sent by the client, parses the data operation request, obtains the request parameters, and then uses the chat generation pre-trained transformation model to identify the user intent of the data operation conversation text carried in the request parameters to obtain the intent recognition result; then, an engineering link is used to transform the intent recognition result based on the application logic to obtain structured parameters, and the preset data service is called based on the structured parameters to obtain the data processing result corresponding to the data operation conversation text. Compared with the prior art in which users manually obtain and analyze data by operating the database or operating the tools corresponding to different product function points, the efficiency and accuracy of data processing are effectively improved.

[0083] On the other hand, the data processing method disclosed in the embodiment of the present application only uses a large model to perform intent recognition and parameter extraction. After obtaining the semi-structured parameters, the request is forwarded to the engineering link. The engineering application will perform operations such as operation indicator search, indicator value conversion, and default value filling to finally obtain complete structured parameters. After that, the database query statement is spliced ​​to read the actual data. The parameter conversion, data reading and processing process based on the semi-structured parameters is executed based on the data processing logic, not the algorithm model processing. Compared with the data processing by the algorithm model from text parsing to data acquisition, this method takes less time and the system response time is significantly reduced.

[0084] Based on the above embodiments, the present application also discloses a data processing method, such as Figure 3 As shown, the data processing method further includes: step 103 and step 1031 before step 104.

[0085] Step 103 , judging whether the data operation request matches the preset data operation based on the request parameters, if so, jumping to executing step 1031 , otherwise, jumping to executing step 104 .

[0086] Step 1031: Call a preset data service to obtain a data processing result corresponding to a preset data operation matching the data operation request.

[0087] In some optional embodiments, before performing user intent recognition on the data operation conversation text carried in the request parameters through a chat generation-type pre-trained transformation model and obtaining the intent recognition result, the method further includes: judging whether the data operation request matches a preset data operation based on the request parameters; if the data operation request matches the preset data operation, calling a preset data service to obtain a data processing result corresponding to the preset data operation matching the data operation request; if the data operation request does not match the preset data operation, jumping to the step of performing user intent recognition on the data operation conversation text carried in the request parameters through a chat generation-type pre-trained transformation model and obtaining the intent recognition result.

[0088] In some embodiments of the present application, in order to improve the data operation response time, multiple preset data operations can be set in the preset data service, and the data processing results can be pre-acquired for each preset data operation, and then the information of the preset data operation and the data processing results are bound and stored in the preset data service. During the operation of the data processing system, the preset data service provides a data call interface so that the client can directly obtain the corresponding data processing results based on the preset data operation. The information of the preset data operation includes but is not limited to one or more of the following information: request description text, operation identifier.

[0089] The preset data operation is pre-set based on application requirements. The preset data operation includes but is not limited to the following questions: general questions, questions preset in combination with the merchant's main categories. Among them, general questions are, for example, "What are the recent hot-selling products on the international site", and questions preset in combination with the merchant's main categories are, for example, "What are the recent hot-selling consumer electronics products in the United States".

[0090] Correspondingly, the request description text of each preset data operation can be displayed on the client, and a selection operation entry for the preset data operation can be set, and the user can select the preset data operation through the selection operation entry. After the user selects a preset data operation through the selection operation entry, the client sets the operation identifier corresponding to the preset data operation selected by the user in the corresponding field in the data operation request and sends it to the server. If the user does not select the preset data operation, but manually enters the data operation conversation text describing the data operation through a human-computer conversation with the client, then the operation identifier in the data operation request indicating whether the data operation request matches the preset data operation can be set to an invalid value. In this way, the server can determine whether the current data operation request matches the preset data operation by whether the value of the corresponding field in the data operation request is a valid operation identifier, and, in the case where the current data operation request matches the preset data operation, further determine which preset data operation the current data operation request matches.

[0091] In other optional embodiments, the server may also use artificial intelligence technology to match and identify the data operation session text input by the user with the request description text of the preset data operation. If the match is successful, it can be considered that the current data operation request matches the preset data operation, and the preset data operation corresponding to the successfully matched request description text is used as the preset data operation matched by the current data operation request.

[0092] In specific implementation, if it is determined that the data operation request matches any preset data operation, the data operation request can be matched with the preset data operation as the target preset data operation. Thereafter, the operation identifier of the target preset data operation is used as a parameter to call the preset data service, thereby directly obtaining the preset data processing result corresponding to the preset request through the preset data service.

[0093] On the contrary, if it is determined that the data operation request does not match any preset data operation, it is necessary to further call the chat generation pre-trained transformation model to identify the user intent of the data operation conversation text carried in the request parameter, and transform the intent recognition result based on the application logic to obtain structured parameters; then, call the preset data service based on the structured parameters to obtain the data processing result corresponding to the data operation conversation text.

[0094] Since the data processing results corresponding to the preset data operations are generated in advance, it is no longer necessary to call the chat generation pre-trained transformation model for intent recognition and subsequent parameter search, conversion processing and other operations for such data operation requests. Instead, the engineering link is directly used to obtain the data processing results corresponding to the preset data operations, effectively reducing the response delay of the data processing system.

[0095] In order to implement the above data processing method, this embodiment also discloses a data processing method, using a client. Figure 4 , the method includes: step 402 to step 408.

[0096] Step 402: in response to the user triggering a preset data operation, obtaining a data operation conversation text input by the user.

[0097] Step 404: Generate a data operation request based on the data operation session text.

[0098] Step 406: Send the data operation request to the preset server to trigger the preset server to perform the first data processing operation.

[0099] As mentioned above, the user can enter the data operation session text in the edit box set by the client to describe the current data operation requirements, and then trigger the data query function button to trigger the client to use the data operation session text entered in the edit box as a request parameter, generate a data operation request, and send the data operation request to the server.

[0100] After receiving the data operation request sent by the client, the server responds to the data operation request and performs the data processing operation.

[0101] Among them, the first data processing operation includes: responding to the data operation request sent by the client, parsing the data operation request, and obtaining request parameters; performing user intent recognition on the data operation conversation text carried in the request parameters through a chat generation pre-trained transformation model to obtain intent recognition results; transforming the intent recognition results based on application logic to obtain structured parameters; calling a preset data service based on the structured parameters to obtain a data processing result corresponding to the data operation conversation text.

[0102] The specific implementation methods of the server side performing each step of the first data processing operation are described above and will not be repeated here.

[0103] Step 408: Obtain and display the data processing result.

[0104] After the server obtains the data processing result corresponding to the data operation session text, the client obtains the query data and displays the query data on the client interface.

[0105] In summary, the data processing method disclosed in the embodiment of the present application is that the client responds to the user triggering a preset data operation, obtains the data operation conversation text input by the user, and generates a data operation request based on the data operation conversation text, and then sends the data operation request to the preset server. The preset server responds to the data operation request sent by the client, parses the data operation request, obtains the request parameters, and then uses the chat generation type pre-trained transformation model to perform user intent recognition on the data operation conversation text carried in the request parameters to obtain the intent recognition result; then, an engineering link is used to transform the intent recognition result based on the application logic to obtain structured parameters, and the preset data service is called based on the structured parameters to obtain the data processing result corresponding to the data operation conversation text. Compared with the prior art in which users manually obtain and analyze data by operating the database or operating the tools corresponding to different product function points, the method effectively improves the efficiency and accuracy of data processing.

[0106] On the other hand, Figure 5The method further includes: step 410 , step 412 and step 414 .

[0107] Step 410: in response to a user triggering a preset data operation, obtaining a preset data operation selected by the user.

[0108] For the specific implementation of the operation of the client obtaining the preset data selected by the user, please refer to the relevant description in the above embodiment, which will not be repeated here.

[0109] Step 412: Generate a data operation request based on the operation identifier of the preset data operation.

[0110] For example, the operation identifier of the preset data operation selected by the user may be set to a corresponding field of the data operation request, thereby generating a data operation request.

[0111] Step 414: Send the data operation request to the preset server to trigger the preset server to perform a second data processing operation.

[0112] Among them, the second data processing operation includes: responding to a data operation request sent by the client, parsing the data operation request, and obtaining request parameters; judging whether the data operation request matches a preset data operation based on the request parameters; and when the data operation request matches the preset data operation, calling a preset data service to obtain a data processing result corresponding to the preset data operation that matches the data operation request.

[0113] The specific implementation method of the server side performing each step of the second data processing operation can be found in the relevant description in the previous embodiment, which will not be repeated here.

[0114] After sending the data operation request to the preset server to trigger the preset server to perform the second data processing operation, the client jumps to execute step 408 to obtain and display the data processing result.

[0115] In summary, the data processing method disclosed in this embodiment pre-sets data processing results corresponding to some data operations (i.e., preset data operations) and sets a human-computer interaction interface on the client for users to select preset data operations. After the user selects a preset data operation that matches his or her needs, the client does not need to call a large model to perform operations such as intent recognition, parameter parsing, and transfer processing, but instead directly uses an engineering link to obtain the data processing results corresponding to the preset data operations, thereby effectively reducing the response delay of the data processing system.

[0116] In order to implement the above embodiments, the present application also discloses a data processing system, such as Figure 2As shown, the data processing system includes: a client and a server, wherein the server further includes: an intelligent orchestration module, a data service gateway, and multiple preset data services. Each of the preset data services can be used to perform a specified data processing operation. For example, the preset data services include: a data service for querying the sales trend of a specified product, a data service for analyzing industry dynamics, etc.

[0117] The client is used for acquiring a data operation session text input by the user in response to the user triggering a preset data operation, and generating a data operation request based on the data operation session text;

[0118] The client is further used to send the data operation request to the intelligent orchestration module;

[0119] The intelligent orchestration module is used to respond to the data operation request sent by the client, parse the data operation request, obtain the request parameters, and then perform user intent recognition on the data operation conversation text carried in the request parameters through the chat generation pre-trained transformation model to obtain the intent recognition result, and transform the intent recognition result based on the application logic to obtain the structured parameters;

[0120] The intelligent orchestration module is further used to access the data service gateway based on the structured parameters;

[0121] The data service gateway is further used to call the preset data service based on the structured parameter to obtain the data processing result corresponding to the data operation session text;

[0122] The client is also used to obtain and display the data processing results.

[0123] In some optional embodiments, the client is further used to, in response to a user triggering a preset data operation, obtain a preset data operation selected by the user, and generate a data operation request based on an operation identifier of the preset data operation; and send the data operation request to the intelligent orchestration module;

[0124] The intelligent orchestration module is further used to respond to a data operation request sent by a client, parse the data operation request, obtain request parameters, and determine whether the data operation request matches a preset data operation based on the request parameters;

[0125] The intelligent orchestration module is further configured to, when the data operation request matches the preset data operation, access the data service gateway based on the preset data operation matched by the data operation request;

[0126] The data service gateway is further used to call a preset data service to obtain a data processing result corresponding to a preset data operation matching the data operation request.

[0127] The specific implementation of each step performed by the client and the data service gateway can be found in the relevant description in the above embodiment, which will not be repeated here. The specific implementation of the preset data service can be found in the previous technology, which will not be repeated in the embodiment of this application.

[0128] Combine the following Figure 6 The schematic diagram of the architecture of the data processing system shown illustrates the specific implementation of the data processing system disclosed in the embodiments of the present application.

[0129] like Figure 6 As shown, the client can be implemented based on a browser. On the one hand, the maintenance personnel of the data processing system log in to the configuration center through the browser to configure interface parameters, interface parameter mapping, etc., and perform configuration operations such as preset data service release, and store the configuration results in the database of the server. On the other hand, the user can enter the data operation session text or select the preset data operation through the browser to perform the data operation.

[0130] Among them, the browser generates a data operation request based on the user's data operation, and sends the data operation request to the intelligent orchestration module (such as the AI ​​orchestration platform RLab) on the server side. Among them, the browser transmits the data operation request to the service application Service-Support-Center through network communication based on the http data transmission and reception protocol. After that, the service application Service-Support-Center and the intelligent orchestration module establish a two-way data flux channel for transmitting the exchange data (such as data processing results) between the client and the server. The intelligent orchestration module parses the data operation request and determines whether the data operation request matches the preset data operation of the data processing system. If so, it directly accesses the data service gateway (such as ApiBank), and the data service gateway calls the preset data service to obtain the data processing results; otherwise, the intelligent orchestration module calls ChatGPT to identify the user's intention, parses the user's intention, obtains unstructured parameters, and converts them into calls. After that, it accesses the data service gateway, and the data service gateway distributes the data operation request to the preset data service to obtain data.

[0131] During the specific implementation process, the server builds its own set of indicator metadata and constructs a preset indicator library. The intelligent orchestration module extracts parameters from data operation requests, searches for corresponding operation descriptions in the preset indicator library, converts some indicator descriptions into operation indicator values ​​(such as country code, category identification), and obtains structured parameters.

[0132] Afterwards, the intelligent orchestration module sends the structured parameters to the data service gateway, and the data service gateway generates an interface call to a corresponding preset data service based on the structured parameters, and calls the corresponding preset data service to obtain data.

[0133] In summary, the embodiment of the present application also discloses a data processing system, which obtains the data operation conversation text input by the user in response to the user triggering the preset data operation through the client, and generates a data operation request based on the data operation conversation text, and then sends the data operation request to the data service gateway; then, the data service gateway parses the data operation request, obtains the request parameters, and performs user intent recognition on the data operation conversation text carried in the request parameters through the chat generation type pre-trained transformation model to obtain the intent recognition result, and transforms the intent recognition result based on the application logic to obtain the structured parameter; finally, the data service gateway is also used to call the preset data service based on the structured parameter, obtain the data processing result corresponding to the data operation conversation text, and the client obtains and displays the data processing result. In the whole data acquisition process, the user only needs to input the data operation conversation text to obtain the corresponding data processing result through the data processing system. Compared with the prior art in which the user manually obtains and analyzes data by operating the database or operating the tools corresponding to different product function points, the efficiency and accuracy of data processing are effectively improved.

[0134] On the other hand, the data processing system disclosed in this embodiment pre-sets data processing results corresponding to some data operations (i.e., preset data operations) and sets a human-computer interaction interface on the client for users to select preset data operations. After the user selects a preset data operation that matches his or her needs, the client does not need to call a large model to perform operations such as intent recognition, parameter parsing, and transfer processing, but instead directly uses an engineering link to obtain the data processing results corresponding to the preset data operation, thereby effectively reducing the response delay of the data processing system.

[0135] It should be noted that, for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present application are not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present application.

[0136] On the basis of the above embodiment, this embodiment further provides a data processing device, which is applied to a server, and the device includes:

[0137] A request parameter acquisition module, used to respond to a data operation request sent by a client, parse the data operation request, and acquire request parameters;

[0138] An intention recognition module is used to recognize the user intention of the data operation conversation text carried in the request parameter through a chat generation pre-trained transformation model to obtain an intention recognition result;

[0139] A structured parameter acquisition module, used to convert the intention recognition result based on application logic to obtain structured parameters;

[0140] The data processing result acquisition module is used to call the preset data service based on the structured parameters to obtain the data processing result corresponding to the data operation conversation text.

[0141] Optionally, before performing user intent recognition on the data operation conversation text carried in the request parameter through the chat generation pre-trained transformation model and obtaining the intent recognition result, the device further includes:

[0142] A preset operation determination module, configured to determine whether the data operation request matches a preset data operation based on the request parameters;

[0143] a judgment execution module, configured to, when the data operation request matches the preset data operation, call a preset data service to obtain a data processing result corresponding to the preset data operation matching the data operation request; and

[0144] In the case that the data operation request does not match the preset data operation, the process jumps to the step of performing user intent recognition on the data operation conversation text carried in the request parameter through the chat generation pre-trained transformation model to obtain the intent recognition result.

[0145] Optionally, the intent recognition result includes: query intent and query parameters, and the conversion processing of the intent recognition result based on the application logic to obtain structured parameters includes:

[0146] Determine the query data source corresponding to the query intent according to the preset application logic;

[0147] According to the preset application logic, the query parameters are searched and converted based on the preset indicator library to obtain the database operation parameters corresponding to the query parameters;

[0148] Based on the query data source and the database operation parameter, a structured parameter is obtained.

[0149] Optionally, the preset indicator library includes: a relationship pair of an operation indicator name and an indicator description, and the query parameter is searched and converted based on the preset indicator library according to the preset application logic to obtain a database operation parameter corresponding to the query parameter, including:

[0150] Using the query parameter as an indicator description to search for the relationship pair, and obtaining an operation indicator name matching the query parameter;

[0151] The operation index name is assigned a value to obtain a database operation parameter.

[0152] Optionally, the intention recognition module is further used to:

[0153] Identify the query intent matched by the data operation conversation text carried in the request parameter through a chat generation pre-trained transformation model;

[0154] Extracting query parameters from the data operation conversation text by using the chat generation pre-trained transformation model to obtain query parameters;

[0155] The query intent and the query parameters are used as intent recognition results.

[0156] Optionally, the server further includes: a data service gateway and a preset data service, and the data processing result acquisition module is further used to:

[0157] The data service gateway is accessed based on the structured parameters, the data service gateway addresses the preset data service according to the structured parameters, and calls the addressed preset data service to obtain data;

[0158] The acquired data is used as the data processing result corresponding to the data operation conversation text.

[0159] Based on the above embodiment, this embodiment further provides a data processing device, which is applied to a client, and the device includes:

[0160] A data operation conversation text acquisition module, used for acquiring the data operation conversation text input by the user in response to the user triggering the preset data operation;

[0161] A data operation request generating module, used for generating a data operation request based on the data operation session text;

[0162] The data processing result acquisition module is used to send the data operation request to the preset server to trigger the preset server to perform a first data processing operation, wherein the first data processing operation includes: responding to the data operation request sent by the client, parsing the data operation request and obtaining request parameters; performing user intent recognition on the data operation conversation text carried in the request parameters through a chat generation pre-trained transformation model to obtain intent recognition results; performing conversion processing on the intent recognition results based on application logic to obtain structured parameters; calling a preset data service based on the structured parameters to obtain data processing results corresponding to the data operation conversation text;

[0163] The data processing result display module is used to obtain and display the data processing results.

[0164] Optionally, the device further comprises:

[0165] A preset data operation acquisition module, used to acquire a preset data operation selected by a user input in response to a user triggering a preset data operation;

[0166] The data operation request generating module is further used to generate a data operation request based on the operation identifier of the preset data operation;

[0167] The data processing result acquisition module is also used to send the data operation request to the preset server to trigger the preset server to perform a second data processing operation, wherein the second data processing operation includes: responding to the data operation request sent by the client, parsing the data operation request and obtaining request parameters; judging whether the data operation request matches the preset data operation based on the request parameters; and when the data operation request matches the preset data operation, calling the preset data service to obtain the data processing result corresponding to the preset data operation that matches the data operation request.

[0168] The data processing device disclosed in the embodiment of the present application is used to implement the above-mentioned data processing method. The specific implementation of each module of the device refers to the specific implementation of the corresponding steps in the above-mentioned method embodiment, which will not be repeated here.

[0169] In summary, the data processing device disclosed in the example of the present application, by the server side responding to the data operation request sent by the client, parses the data operation request, obtains the request parameters, and then, through the chat generation type pre-trained transformation model, performs user intent recognition on the data operation conversation text carried in the request parameters to obtain the intent recognition result; then, adopts the engineering link, transforms the intent recognition result based on the application logic to obtain structured parameters, and calls the preset data service based on the structured parameters to obtain the data processing result corresponding to the data operation conversation text. Compared with the prior art in which users manually obtain and analyze data by operating the database or operating the tools corresponding to different product function points, the efficiency and accuracy of data processing are effectively improved.

[0170] On the other hand, the data processing device disclosed in the embodiment of the present application only uses a large model to perform intent recognition and parameter extraction. After obtaining the semi-structured parameters, the request is forwarded to the engineering link. The engineering application will perform operations such as operation indicator search, indicator value conversion, and default value filling, and finally obtain complete structured parameters. After that, the database query statement is spliced ​​to read the actual data. The parameter conversion, data reading and processing process based on the semi-structured parameters is executed based on the data processing logic, not the algorithm model processing. Compared with the data processing by the algorithm model from text parsing to data acquisition, this method takes less time and the system response time is significantly reduced.

[0171] The embodiment of the present application also provides a non-volatile readable storage medium, which stores one or more modules (programs). When the one or more modules are applied to a device, the device can execute instructions (instructions) of each method step in the embodiment of the present application.

[0172] The embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method described in the embodiment of the present application.

[0173] The embodiment of the present application also provides an electronic device, comprising: a processor, and a memory connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described in the embodiment of the present application. In the embodiment of the present application, the electronic device includes a server, a terminal device, and other devices.

[0174] The embodiment of the present application also discloses a computer program product, including a computer program / computer executable instructions, characterized in that when the computer program / computer executable instructions are executed by a processor in an electronic device, the method described in the embodiment of the present application is implemented.

[0175] The embodiments of the present disclosure may be implemented as a device configured as desired using any appropriate hardware, firmware, software, or any combination thereof, and the device may include electronic devices such as a server (cluster), a terminal, etc. Figure 7 An exemplary apparatus 700 that can be used to implement various embodiments described in this application is schematically illustrated.

[0176] For one embodiment, Figure 7 An exemplary apparatus 700 is shown having one or more processors 702, a control module (chip set) 704 coupled to at least one of the processor(s) 702, a memory 706 coupled to the control module 704, a non-volatile memory (NVM) / storage device 708 coupled to the control module 704, one or more input / output devices 710 coupled to the control module 704, and a network interface 712 coupled to the control module 704.

[0177] The processor 702 may include one or more single-core or multi-core processors, and the processor 702 may include any combination of general-purpose processors or special-purpose processors (such as graphics processors, application processors, baseband processors, etc.). In some embodiments, the device 700 can be used as a server, terminal, or other device described in the embodiments of the present application.

[0178] In some embodiments, the apparatus 700 may include one or more computer-readable media (e.g., memory 706 or NVM / storage device 708) having instructions 714 and one or more processors 702 combined with the one or more computer-readable media and configured to execute the instructions 714 to implement a module to perform the actions described in the present disclosure.

[0179] For one embodiment, the control module 704 may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) 702 and / or any suitable device or component in communication with the control module 704 .

[0180] The control module 704 may include a memory controller module to provide an interface to the memory 706. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0181] The memory 706 may be used, for example, to load and store data and / or instructions 714 for the device 700. For one embodiment, the memory 706 may include any suitable volatile memory, such as a suitable DRAM. In some embodiments, the memory 706 may include double data rate type four synchronous dynamic random access memory (DDR4 SDRAM).

[0182] For one embodiment, control module 704 may include one or more input / output controllers to provide an interface to NVM / storage device 708 and input / output device(s) 710 .

[0183] For example, NVM / storage 708 may be used to store data and / or instructions 714. NVM / storage 708 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0184] NVM / storage device 708 may include storage resources that are part of the device on which apparatus 700 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 708 may be accessed via (one or more) input / output devices 710 over a network.

[0185] (One or more) input / output devices 710 may provide an interface for the apparatus 700 to communicate with any other appropriate device, and the input / output device 710 may include a communication component, an audio component, a sensor component, etc. The network interface 712 may provide an interface for the apparatus 700 to communicate through one or more networks, and the apparatus 700 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and / or protocols, for example, accessing a wireless network based on a communication standard, such as Bluetooth, WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof for wireless communication.

[0186] For one embodiment, at least one of the processor(s) 702 may be packaged together with the logic of one or more controllers (e.g., a memory controller module) of the control module 704. For one embodiment, at least one of the processor(s) 702 may be packaged together with the logic of one or more controllers of the control module 704 to form a system-in-package (SiP). For one embodiment, at least one of the processor(s) 702 may be integrated on the same die with the logic of one or more controllers of the control module 704. For one embodiment, at least one of the processor(s) 702 may be integrated on the same die with the logic of one or more controllers of the control module 704 to form a system-on-chip (SoC).

[0187] In various embodiments, the apparatus 700 may be, but is not limited to, a terminal device such as a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). In various embodiments, the apparatus 700 may have more or fewer components and / or a different architecture. For example, in some embodiments, the apparatus 700 includes one or more cameras, a keyboard, a liquid crystal display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an application-specific integrated circuit (ASIC), and a speaker.

[0188] Among them, the main control chip can be used as a processor or control module in the detection device, sensor data, location information, etc. are stored in a memory or NVM / storage device, the sensor group can be used as an input / output device, and the communication interface may include a network interface.

[0189] The embodiment of the present application also provides an electronic device, including: a processor; and a memory, on which executable code is stored, and when the executable code is executed, the processor executes one or more methods as described in the embodiment of the present application. In the embodiment of the present application, the memory can store various data, such as target files, file and application association data, and user behavior data, so as to provide a data basis for various processing.

[0190] The embodiments of the present application also provide one or more machine-readable media on which executable codes are stored. When the executable codes are executed, the processor executes one or more methods described in the embodiments of the present application.

[0191] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0192] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0193] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0194] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0195] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0196] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0197] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0198] The data processing method, data processing system, electronic device, storage medium and computer program product provided by the present application are introduced in detail above. The principles and implementation methods of the present application are explained in this article using specific examples. The description of the above embodiments is only used to help understand the method of the present application and its core idea. 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 method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A data processing method, applied to a server, characterized in that: The method comprises: In response to a data operation request sent by a client, the data operation request is parsed to obtain request parameters; Performing user intent recognition on the data operation conversation text carried in the request parameter through a chat generation pre-trained transformation model to obtain an intent recognition result; Converting the intention recognition result based on application logic to obtain structured parameters; The preset data service is called based on the structured parameters to obtain the data processing result corresponding to the data operation conversation text.

2. The method according to claim 1, characterized in that The method further comprises: performing user intent recognition on the data operation conversation text carried in the request parameter by using a chat generation pre-trained transformation model, and obtaining the intent recognition result before the method further comprises: Determining whether the data operation request matches a preset data operation based on the request parameters; In the case where the data operation request matches the preset data operation, calling a preset data service to obtain a data processing result corresponding to the preset data operation matching the data operation request; In the case that the data operation request does not match the preset data operation, the process jumps to the step of performing user intent recognition on the data operation conversation text carried in the request parameter through the chat generation pre-trained transformation model to obtain the intent recognition result.

3. The method according to claim 1, characterized in that The intent recognition result includes: query intent and query parameters. The intent recognition result is converted based on the application logic to obtain structured parameters, including: Determine the query data source corresponding to the query intent according to the preset application logic; According to the preset application logic, the query parameters are searched and converted based on the preset indicator library to obtain the database operation parameters corresponding to the query parameters; Based on the query data source and the database operation parameter, a structured parameter is obtained.

4. The method according to claim 3, characterized in that The preset indicator library includes: a relationship pair between an operation indicator name and an indicator description. The query parameter is searched and converted based on the preset indicator library according to the preset application logic to obtain a database operation parameter corresponding to the query parameter, including: Using the query parameter as an indicator description to search for the relationship pair, and obtaining an operation indicator name matching the query parameter; The operation index name is assigned a value to obtain a database operation parameter.

5. The method according to claim 1, characterized in that The method of performing user intent recognition on the data operation conversation text carried in the request parameter by using the chat generation pre-trained transformation model to obtain the intent recognition result includes: Identify the query intent matched by the data operation conversation text carried in the request parameter through a chat generation pre-trained transformation model; Extracting query parameters from the data operation conversation text by using the chat generation pre-trained transformation model to obtain query parameters; The query intent and the query parameters are used as intent recognition results.

6. The method according to claim 1, characterized in that The server also includes: a data service gateway and a preset data service, and the calling of the preset data service based on the structured parameter to obtain the data processing result corresponding to the data operation conversation text includes: Accessing the data service gateway based on the structured parameters, the data service gateway addressing the preset data service according to the structured parameters, and calling the addressed preset data service to obtain data; The acquired data is used as the data processing result corresponding to the data operation conversation text.

7. A data processing method, applied to a client, characterized in that: The method comprises: In response to a user triggering a preset data operation, obtaining a data operation conversation text input by the user; Generate a data operation request based on the data operation session text; Sending the data operation request to a preset server to trigger the preset server to perform a first data processing operation, wherein the first data processing operation includes: responding to the data operation request sent by the client, parsing the data operation request and obtaining request parameters; performing user intent recognition on the data operation conversation text carried in the request parameters through a chat generation pre-trained transformation model to obtain intent recognition results; performing conversion processing on the intent recognition results based on application logic to obtain structured parameters; calling a preset data service based on the structured parameters to obtain a data processing result corresponding to the data operation conversation text; Obtain and display the data processing results.

8. The method according to claim 7, characterized in that The method further comprises: In response to a user triggering a preset data operation, obtaining a preset data operation selected by a user input; Generate a data operation request based on the operation identifier of the preset data operation; The data operation request is sent to a preset server to trigger the preset server to perform a second data processing operation, wherein the second data processing operation includes: in response to the data operation request sent by the client, parsing the data operation request and obtaining request parameters; judging whether the data operation request matches a preset data operation based on the request parameters; and when the data operation request matches the preset data operation, calling a preset data service to obtain a data processing result corresponding to the preset data operation that matches the data operation request.

9. A data processing system, characterized in that: The system includes: a client and a server, wherein the server further includes: an intelligent arrangement module, a data service gateway and a plurality of preset data services, The client is used for acquiring a data operation session text input by the user in response to the user triggering a preset data operation, and generating a data operation request based on the data operation session text; The client is further used to send the data operation request to the intelligent orchestration module; The intelligent orchestration module is used to respond to the data operation request sent by the client, parse the data operation request, obtain the request parameters, and then perform user intent recognition on the data operation conversation text carried in the request parameters through the chat generation pre-trained transformation model to obtain the intent recognition result, and transform the intent recognition result based on the application logic to obtain the structured parameters; The intelligent orchestration module is further used to access the data service gateway based on the structured parameters; The data service gateway is further used to call the preset data service based on the structured parameter to obtain the data processing result corresponding to the data operation session text; The client is also used to obtain and display the data processing results.

10. The system according to claim 9, characterized in that The client is further configured to, in response to a user triggering a preset data operation, obtain a preset data operation selected by the user, and generate a data operation request based on an operation identifier of the preset data operation; and send the data operation request to the intelligent orchestration module; The intelligent orchestration module is further used to respond to a data operation request sent by a client, parse the data operation request, obtain request parameters, and determine whether the data operation request matches a preset data operation based on the request parameters; The intelligent orchestration module is further configured to, when the data operation request matches the preset data operation, access the data service gateway based on the preset data operation matched by the data operation request; The data service gateway is further used to call a preset data service to obtain a data processing result corresponding to a preset data operation matching the data operation request.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

13. A computer program product comprising a computer program / computer executable instructions, characterized in that: When the computer program / computer executable instructions are executed by a processor in an electronic device, the method according to any one of claims 1 to 8 is implemented.

Images