Data processing method, device, equipment, computer-readable storage medium and product

Abstract

The present disclosure provides a data processing method, apparatus, device, computer-readable storage medium, and product, relating to the field of artificial intelligence, particularly the field of big data. Applied to a data processing device, the data processing device is respectively connected to a preset data processing model and at least one business system; a specific implementation scheme comprises: obtaining a data processing request, wherein the data processing request includes a data processing result obtained by the data processing model based on user-generated natural language data processing, and identification information of the target business system to be called; determining the business association information corresponding to the target business system; performing data optimization operations on the data processing result based on the business association information to obtain target data; and calling the target business system based on the target data to execute a task matching the target data. This solves the problem that the current data processing model has low accuracy in business processing for specific business fields.

Description

Technical Field

[0001] The present disclosure relates to big data in artificial intelligence, and in particular to a data processing method, apparatus, device, computer-readable storage medium, and product. Background Art

[0002] With the development of artificial intelligence technology, big models are gradually becoming part of users' lives. Users can input natural language into the big models, which then process data based on the natural language and output data processing results that match the natural language.

[0003] Currently, large models are increasingly being used in various business areas. Improving the accuracy of large models in processing specific business areas has become an urgent problem to be solved. Summary of the Invention

[0004] The present disclosure provides a data processing method, apparatus, device, computer-readable storage medium, and product for improving the processing accuracy of a data processing model.

[0005] According to a first aspect of the present disclosure, a data processing method is provided, which is applied to a data processing device, wherein the data processing device is respectively in communication with a preset data processing model and at least one business system; the method comprises:

[0006] Obtaining a data processing request, wherein the data processing request includes a data processing result obtained by the data processing model performing data processing based on the natural language generated by the user, and identification information of a target business system to be called;

[0007] Determining business association information corresponding to the target business system;

[0008] Performing a data optimization operation on the data processing result according to the business association information to obtain target data;

[0009] The target business system is called based on the target data to execute a task matching the target data.

[0010] According to a second aspect of the present disclosure, a data processing device is provided, wherein the data processing device is communicatively connected to a preset data processing model and at least one business system, respectively; and comprises:

[0011] an acquisition module, configured to acquire a data processing request, wherein the data processing request includes a data processing result obtained by the data processing model performing data processing based on the natural language generated by the user, and identification information of a target business system to be called;

[0012] A determination module, configured to determine the business association information corresponding to the target business system;

[0013] An optimization module, configured to perform a data optimization operation on the data processing result according to the business association information to obtain target data;

[0014] A calling module is used to call the target business system based on the target data to execute a task matching the target data.

[0015] According to a third aspect of the present disclosure, there is provided a data processing system comprising a data processing device, at least one business system, and a preset data processing model;

[0016] Wherein, the data processing device is respectively in communication with the at least one business system and the preset data processing model;

[0017] The data processing device is used to obtain a data processing request, wherein the data processing request includes a data processing result obtained by the data processing model performing data processing based on the natural language generated by the user, and identification information of the target business system to be called;

[0018] The data processing device is used to determine the business association information corresponding to the target business system, perform data optimization operations on the data processing results according to the business association information to obtain target data, and call the target business system to execute a task matching the target data based on the target data;

[0019] The business system is used to execute tasks that match the target data.

[0020] According to a fourth aspect of the present disclosure, there is provided an electronic device, including:

[0021] at least one processor; and

[0022] a memory communicatively connected to the at least one processor; wherein,

[0023] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the data processing method described in the first aspect.

[0024] According to a fifth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the data processing method as described in the first aspect.

[0025] According to a sixth aspect of the present disclosure, a computer program product is provided, comprising: a computer program, wherein the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the electronic device executes the method described in the first aspect.

[0026] The technology disclosed herein solves the problem that current data processing models have low accuracy in business processing for specific business areas.

[0027] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0029] Figure 1 A system architecture diagram of the data processing system on which the present disclosure is based;

[0030] Figure 2 A flowchart of a data processing method provided in an embodiment of the present disclosure;

[0031] Figure 3 A schematic diagram of an application scenario provided by an embodiment of the present disclosure;

[0032] Figure 4 A flowchart of a data processing method provided in yet another embodiment of the present disclosure;

[0033] Figure 5 A flowchart of a data processing method provided in yet another embodiment of the present disclosure;

[0034] Figure 6 A schematic diagram of the structure of a data processing device provided in an embodiment of the present disclosure;

[0035] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0037] The present disclosure provides a data processing method, apparatus, device, computer-readable storage medium, and product, which are applied to big data in artificial intelligence to achieve the technical effect of improving the data processing accuracy of data processing models for specific business scenarios.

[0038] It should be noted that the data processing methods, devices, equipment, computer-readable storage media and products provided by the present disclosure can be applied to any application scenario of data processing based on large models.

[0039] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0040] With the development of artificial intelligence (AI), the technology has entered the era of big models. Users can input natural language into big models based on their actual needs. This natural language can be in the form of voice, text, or other forms. Big models can perform semantic analysis on the natural language and perform corresponding data processing operations based on the analysis results. For example, a user can input the natural language "New To-Do Action: Meet Xiaoming at 2:00 tomorrow" into the big model. The big model can then create a new to-do task based on this natural language and send reminders to the user based on this to-do task.

[0041] Currently, large models are increasingly being used in business systems. These models often connect to multiple business systems and provide data processing capabilities for them. However, when these models are integrated with business systems, their accuracy in processing data for specific business needs is often low. Consequently, the output of these models cannot accurately be used to call business systems, thus failing to meet actual user needs.

[0042] In the process of solving the above technical problems, the inventors discovered through research that in order to improve the accuracy of the data processing results output by the large model and make the data processing results more compatible with the business needs of the business system, an intermediate layer can be built between the business system and the large model. This intermediate layer can specifically be the data processing device described in the present disclosure. After obtaining the data processing results output by the large model, the data processing device can perform data optimization operations on the data processing results based on the business-related information corresponding to the preset business system to obtain target data, and then call the business system based on the target data.

[0043] The inventors further discovered that when the large model provides services to multiple different business systems, the call interface information for each business system varies. This interface information includes, but is not limited to, host addresses, request parameters, response formats, and other information. To address the heterogeneous call interface information of different business systems, the data processing device can also convert the heterogeneous call interface information into interface information in a target format that the large model can recognize, in order to enable the large model to provide services to these different business systems.

[0044] In order to enable readers to have a deeper understanding of the implementation principle of this disclosure, the following Figure 1-Figure 7 The embodiments of the present disclosure are further refined.

[0045] Figure 1 This is a system architecture diagram of the data processing system on which the present disclosure is based, such as Figure 1 As shown, the data processing system 11 includes at least a server 12, at least one business system 13, and a data processing model 14. The server 12 is in communication with the at least one business system 13 and the data processing model 14. The server 12 may be provided with a data processing device, which may be written in a language such as C / C++, Java, Shell, or Python.

[0046] Based on the above system architecture, the data processing device is used to obtain a data processing request and input the natural language into the data processing model 14 based on the data processing request, wherein the data processing request includes the natural language generated by the user and the identification information of the target business system to be called;

[0047] The data processing device is used to obtain a data processing request, wherein the data processing request includes a data processing result obtained by the data processing model performing data processing based on the natural language generated by the user, and identification information of the target business system to be called;

[0048] The data processing device is used to determine the business association information corresponding to the target business system, perform data optimization operations on the data processing results according to the business association information to obtain target data, and call the target business system 13 based on the target data to execute a task matching the target data;

[0049] The business system 13 is used to execute tasks that match the target data.

[0050] This can improve the accuracy of the target data and match the data requirements of the business system.

[0051] Figure 2Schematic diagram of a data processing method according to an embodiment of the present disclosure, wherein the data processing method is applied to a data processing device, wherein the data processing device is respectively connected to a preset data processing model and at least one business system in communication; Figure 2 As shown, the method includes:

[0052] Step 201: Obtain a data processing request, wherein the data processing request includes a data processing result obtained by the data processing model performing data processing based on a natural language generated by a user, and identification information of a target business system to be called.

[0053] The present disclosure is implemented by a data processing device that can be coupled to a server. The server can communicate with a data processing model and at least one business system, respectively, so that the data processing device can exchange information with the data processing model and at least one business system, respectively.

[0054] The data processing model can be a large model of artificial intelligence, which can parse the natural language input by the user and perform corresponding data processing operations based on the parsing results. For example, the data processing model can interact with the user based on the natural language input by the user. Alternatively, the data processing model can perform text analysis based on natural language, determine the instructions corresponding to the natural language, and execute the corresponding instructions. Alternatively, the data processing model can create literary content related to natural language based on natural language, etc. The present disclosure does not limit the data processing capabilities of the data processing model based on natural language.

[0055] In this embodiment, the data processing model can provide data processing capabilities to at least one business system and invoke the business system to perform corresponding tasks based on the processed target data. The data processing model can be communicatively connected to the data processing device, and the data processing device can be communicatively connected to at least one business system.

[0056] Based on the above system architecture, the data processing device can obtain a data processing request, wherein the data processing request includes the data processing results obtained by the data processing model based on the natural language generated by the user, and the identification information of the target business system to be called.

[0057] Optionally, the data processing result can be obtained by the user directly inputting natural language into the data processing model. Alternatively, the user inputs natural language into the data processing device, which then inputs the natural language into the data processing model. This disclosure is not limited to this.

[0058] Step 202: Determine the business association information corresponding to the target business system.

[0059] In this embodiment, in order to enable the data processing results output by the data processing model to match the actual business needs of the business system and improve the accuracy of the data processing results, after obtaining the data processing request, the business association information corresponding to the target business system can be obtained based on the identification information of the target business system in the data processing request.

[0060] Among them, the business-related information includes but is not limited to the domain knowledge content of the field in which the business system is located, the data requirements corresponding to the business system, etc., among which the domain knowledge content includes time processing content, location processing content, personnel processing content, domain dictionary content, screening condition content, etc., and the data requirements include but are not limited to data format and other content.

[0061] Step 203: Perform data optimization operations on the data processing results according to the business association information to obtain target data.

[0062] In this embodiment, after the business association information of the business system is obtained, a data optimization operation can be performed on the data processing result based on the business association information to obtain target data.

[0063] The data optimization includes, but is not limited to, vocabulary replacement, supplementation, splitting, and other optimization operations. This allows the obtained target data to match the actual business needs of the business system, thereby improving the accuracy of the data processing results.

[0064] Step 204: Based on the target data, the target business system is called to execute a task matching the target data.

[0065] In this embodiment, after data optimization is performed on the data processing results to obtain target data, the target business system can be called based on the target data to execute tasks that match the target data.

[0066] Figure 3 This is a schematic diagram of an application scenario provided by an embodiment of the present disclosure, such as Figure 3 As shown, users can initiate data processing requests based on actual needs. These data processing requests can include natural language. For example, the natural language could be "Meeting with Xiaoming tomorrow at 2:00 PM." After receiving the data processing request, the data processing device 31 can input the natural language into the data processing model 32. The data processing model 32 can parse the natural language and perform corresponding data processing to obtain data processing results. The data processing device 31 can then optimize the data processing results to obtain target data and feed the target data back to the business system 33.

[0067] Continuing with the above example, the data processing result may be "To-do list: Start a meeting; Object: Me, Xiao Ming; Time: Tomorrow at 2 pm". However, in the data processing result, the data referred to by "Me", "Xiao Ming", and "Tomorrow" are not clear enough, resulting in low accuracy of the data processing result. The data processing device can determine the identity information of "Me" based on the identification information of the currently logged-in user, and determine the identity information of "Xiao Ming" based on the pre-stored address book of users using the business system, and obtain the current time information in real time, and determine the specific time of "tomorrow" based on the current time information. Therefore, based on the above business-related information, the data processing result can be optimized to "To-do list: Start a meeting; Object: Zhang San, Li Ming; Time: 2 pm on July 12, 2023". Through the above data optimization processing, the results of data processing can be improved, allowing users to perform business processing more accurately.

[0068] The data processing method provided in this embodiment establishes a data processing device between a data processing model and at least one business system. This device can then optimize the output of the data processing model based on business-related content. This ensures that the resulting target data matches the actual business needs of the business system, improving the accuracy of the data processing results.

[0069] Figure 4 A flow chart of a data processing method provided by another embodiment of the present disclosure is shown below. Based on any of the above embodiments, before step 201, as shown below: Figure 4 As shown, it also includes:

[0070] Step 401: respectively obtain the interface entry request sent by each business system, wherein the interface entry request includes the interface information corresponding to the business system, and the format of the interface information corresponding to different business systems is different.

[0071] Step 402: parse the interface information to determine the format corresponding to the interface information.

[0072] Step 403: Convert the format of the interface information into a target format that matches the data processing model.

[0073] In this embodiment, the data processing model can often provide pre-processing functions for multiple business systems. However, the interface information corresponding to the call interface of different business systems often varies. This interface information includes, but is not limited to, host address, request parameters, response format, and other information.

[0074] Since the interface information of the data processing model is often different from the interface information of the business system, it is impossible to call the business system directly based on the data processing results. In order to solve the above technical problems, the data processing device can convert the heterogeneous interface information.

[0075] Optionally, before obtaining the data processing request, the data processing device may respectively obtain the interface entry request sent by each of the business systems, wherein the interface entry request includes the interface information corresponding to the business system, and the format of the interface information corresponding to different business systems is different.

[0076] For each piece of interface information, the interface information is parsed to determine the format content corresponding to the interface information, and the format of the interface information is converted into a target format that matches the data processing model.

[0077] The data processing method provided in this embodiment converts the interface information of the heterogeneous calling interfaces of various business parties, so that the data processing device can implement calling operations on different business systems.

[0078] Further, based on any of the above embodiments, step 204 includes:

[0079] The target business system is called based on the target data according to the interface information in the target format to execute a task matching the target data.

[0080] In this embodiment, after the interface information corresponding to each business system is converted into a target format that matches the data processing model, the data processing model can now exchange information with the business system. After obtaining the target data output by the data processing model, the target business system can be called based on the target data according to the interface information in the target format to execute the task that matches the target data.

[0081] The data processing method provided in this embodiment converts the interface information of the heterogeneous calling interfaces of various business parties, so that the data processing device can implement calling operations on different business systems.

[0082] Figure 5 A flow chart of a data processing method provided in another embodiment of the present disclosure is provided. Based on any of the above embodiments, Figure 5 As shown, step 201 includes:

[0083] Step 501: Obtain natural language generated by the user.

[0084] Step 502: Input the natural language into the data processing model to obtain the data processing result.

[0085] Step 503: Generate the data processing request based on the data processing result and the target business system determined by the user.

[0086] In this embodiment, the user can input natural language into the data processing model according to actual needs, and generate a data processing request based on the natural language. Alternatively, the user can input natural language into the data processing device, and the data processing device inputs the natural language into the data processing model.

[0087] Optionally, the data processing device can obtain user-generated natural language and input the natural language into the data processing model to obtain data processing results. Furthermore, the user can also determine the target business system to be called based on actual needs. This allows the generation of a data processing request based on the data processing results and the user-determined target business system.

[0088] The data processing method provided in this embodiment obtains the natural language generated by the user by the data processing device and inputs the natural language into the data processing model, so that the natural language can be pre-processed according to actual needs before being input into the data processing model, thereby further improving the accuracy of data processing.

[0089] Further, based on any of the above embodiments, step 502 includes:

[0090] Perform a keyword recognition operation on the natural language to obtain at least one keyword corresponding to the natural language.

[0091] If the number of keywords corresponding to the natural language is less than a preset threshold, the natural language is input into the data processing model.

[0092] If the number of keywords corresponding to the natural language is greater than a preset threshold, a preset number of target keywords that meet preset conditions are selected from the multiple keywords corresponding to the natural language according to preset data editing information, and the preset number of target keywords are input into the data processing model.

[0093] In this embodiment, when a data processing model is used to process natural language, keywords corresponding to the natural language can be extracted and subsequent data processing can be performed based on the keywords. However, when the natural language is complex, that is, when there are many keywords, the data processing model may require a large amount of computation, affecting the data processing results.

[0094] Therefore, after obtaining the natural language, a keyword recognition operation can be performed on the natural language to obtain at least one keyword corresponding to the natural language. If the number of keywords corresponding to the natural language is less than a preset threshold, that is, the data processing model can accurately process data based on the keyword, then the natural language can be input into the data processing model. Conversely, if the number of keywords corresponding to the natural language is greater than the preset threshold, it may cause the data processing model to have a large amount of calculation, affecting the data processing results. Therefore, according to the preset data editing information, a preset number of target keywords that meet the preset conditions can be selected from the multiple keywords corresponding to the natural language, and the preset number of target keywords can be input into the data processing model.

[0095] The data editing information defines the selection criteria for the target keywords. For example, the keywords can be sorted by importance, and the top N keywords can be selected as target keywords. Alternatively, N keywords with fewer words than a preset threshold can be selected as target keywords. The data editing information can be set by the user according to actual needs, or it can be preset in the data processing device. This disclosure does not impose any restrictions on this.

[0096] The data processing method provided in this embodiment can reduce the computational pressure of the data processing model and improve data processing efficiency by determining a preset number of target keywords corresponding to the natural language when the number of keywords corresponding to the natural language is greater than a preset threshold before inputting the natural language into the data processing model, and inputting the target keywords into the data processing model.

[0097] Optionally, based on any of the above embodiments, the method further includes:

[0098] Determine the task information corresponding to the target data.

[0099] Check whether the task information meets the preset splitting conditions.

[0100] If so, the task information is split according to the preset data editing information to obtain at least one subtask.

[0101] Step 204 includes:

[0102] The target business system is called based on the target data to execute the at least one subtask.

[0103] In this embodiment, after optimizing the data processing results to obtain target data, the business system can be called based on the target data to process the task corresponding to the target data. However, the task corresponding to the target data may be relatively complex and may be composed of multiple simple tasks. The business system may have difficulty processing complex tasks and may not achieve the desired effect.

[0104] Therefore, to improve the accuracy of business processing, after obtaining the target data, the task information corresponding to the target data can be determined. Whether the task information meets the preset splitting conditions can be detected. Factors such as the execution difficulty, execution time, and execution steps corresponding to the task information can be determined, and based on these factors, whether the task information meets the preset splitting conditions can be determined. Alternatively, other methods can be used to determine whether the task information meets the preset splitting conditions, which is not limited by this disclosure.

[0105] Furthermore, if it is detected that the task information meets the preset splitting conditions, the task information can be split according to the preset data editing information to obtain at least one subtask. The data editing information can be set by the user according to actual needs, or it can be preset in the data processing device. This disclosure is not limited to this.

[0106] The data processing method provided by this disclosure detects whether task information meets preset splitting conditions before invoking the business system based on target data. If the conditions are met, the task information is split. This reduces the computational workload of the business system and improves data processing efficiency.

[0107] Optionally, based on any of the above embodiments, the method further includes:

[0108] In response to the data editing operation triggered by the user, parameter arrangement information and / or task splitting information generated by the user is obtained.

[0109] The parameter arrangement information and / or task splitting information is determined as the data editing information.

[0110] In this embodiment, the data editing information can be set by the user according to actual needs. The data editing information can specifically include parameter arrangement information and / or task splitting information. The parameter arrangement information is used to select target keywords from multiple keywords. The task splitting information is used to split complex tasks.

[0111] Optionally, in order to realize the generation of data editing information, in response to the data editing operation triggered by the user, the parameter arrangement information and / or task splitting information generated by the user may be obtained and the parameter arrangement information and / or task splitting information may be determined as the data editing information.

[0112] The data processing method provided by the present disclosure determines data editing information in advance based on parameter arrangement information and / or task splitting information generated by the user, so that during the data processing process, target keywords can be selected and / or complex tasks can be split based on the data editing information, thereby reducing the amount of data in the data processing process and improving the efficiency of data processing.

[0113] Optionally, based on any of the above embodiments, the business association information includes domain knowledge content corresponding to the target business system.

[0114] Step 203 includes:

[0115] Determine business-specific vocabulary in the data processing result.

[0116] The business-specific vocabulary is replaced based on the domain knowledge content to obtain the target data.

[0117] In this embodiment, in order to make the data processing results output by the data processing model match the actual business needs of the business system and improve the accuracy of the data processing results, after obtaining the data processing request, the data processing results can be optimized based on the business association information corresponding to the target business system.

[0118] Optionally, the business association information corresponding to the target business system may be domain knowledge content corresponding to the target business system, wherein the domain knowledge content includes time processing content, location processing content, personnel processing content, domain dictionary content, screening condition content, etc.

[0119] After obtaining the data processing results, they may contain some non-standard business-specific vocabulary. To improve the accuracy of subsequent data processing, the business-specific vocabulary in the data processing results can be identified. Standard vocabulary matching the business-specific vocabulary is identified within the domain-specific content. The business-specific vocabulary is then replaced with the standard vocabulary within the domain knowledge content to obtain the target data.

[0120] The data processing method provided by the present disclosure replaces business-specific vocabulary based on standard vocabulary in domain knowledge content, thereby improving the accuracy of target data and providing a basis for subsequent business calls.

[0121] Optionally, based on any of the above embodiments, the business association information includes data requirement information corresponding to the target business system, and the data requirement information is obtained by parsing interface information in the interface entry request sent by the target business system.

[0122] Step 203 includes:

[0123] The data format of the data processing result is adjusted according to the data requirements corresponding to the business system to obtain the target data.

[0124] In this embodiment, the business-related information includes data requirement information corresponding to the target business system, which is obtained by parsing the interface information in the interface input request sent by the target business system. The data requirement information may include content such as the data format required by the business system.

[0125] After obtaining the data processing results, the data format of the data processing results can be adjusted according to the data requirements of the business system, and the format of the data processing results can be adjusted to the data format corresponding to the data requirements to obtain the target data.

[0126] The data processing method provided by the present disclosure adjusts the data format of the data processing results based on the data requirements of the business system, so that the adjusted target data can better meet the actual needs of the business system.

[0127] Optionally, based on any of the above embodiments, the business association information includes domain knowledge content and data requirement information corresponding to the target business system.

[0128] Step 203 includes:

[0129] Determine the referential vocabulary in the data processing result.

[0130] The reference vocabulary is replaced according to the domain knowledge content and the data demand information to obtain the target data.

[0131] In this embodiment, the business-related information includes domain knowledge content and data requirement information corresponding to the target business system. The domain knowledge content includes time processing content, location processing content, personnel processing content, domain dictionary content, and screening condition content. The data requirement information can include content such as the data format required by the business system.

[0132] After obtaining the data processing results, the referential terms in the data processing results can be determined. For example, the natural language could be "Hold a meeting with Xiaoming at 2 pm tomorrow." The data processing result could be "To-do item: Hold a meeting; Subjects: Me, Xiaoming; Time: 2 pm tomorrow." Here, "me," "Xiaoming," and "tomorrow" are all referential data.

[0133] However, the above reference information is often not clear enough, and subsequent business calls based on the data processing results may not be accurate. Therefore, the reference words can be replaced based on domain knowledge content and data requirement information to obtain the target data.

[0134] Continuing with the previous example, the identity of "I" can be determined based on the identification information of the currently logged-in user, and the identity of "Xiaoming" can be determined based on the pre-stored address book of users using the business system. The current time information can be obtained in real time, and the specific time of "tomorrow" can be determined based on the current time information. This optimizes the data processing results.

[0135] The data processing method provided in this embodiment replaces the referential vocabulary based on domain knowledge content and data demand information, so that the obtained target data can match the actual business needs of the business system, thereby improving the accuracy of the data processing results.

[0136] Figure 6 This is a structural diagram of a data processing device provided in an embodiment of the present disclosure, wherein the data processing device is respectively connected to a preset data processing model and at least one business system for communication. Figure 6 As shown, the device includes: an acquisition module 61, a determination module 62, an optimization module 63, and a call module 64. The acquisition module 61 is used to obtain a data processing request, wherein the data processing request includes the data processing results obtained by the data processing model based on the user-generated natural language, and the identification information of the target business system to be called. The determination module 62 is used to determine the business association information corresponding to the target business system. The optimization module 63 is used to perform data optimization operations on the data processing results based on the business association information to obtain target data. The call module 64 is used to call the target business system based on the target data to execute a task matching the target data.

[0137] Furthermore, based on any of the above embodiments, the device also includes: an acquisition module, used to respectively acquire the interface entry requests sent by each of the business systems, wherein the interface entry requests include interface information corresponding to the business system, and the formats of the interface information corresponding to different business systems are different; a parsing module, used to perform parsing operations on the interface information to determine the format corresponding to the interface information; and a conversion module, used to convert the format of the interface information into a target format that matches the data processing model.

[0138] Further, based on any of the above embodiments, the calling module includes: a calling submodule, configured to call the target business system based on the target data according to the interface information in the target format to execute a task matching the target data.

[0139] Furthermore, based on any of the above embodiments, the acquisition module includes: an acquisition sub-module for acquiring natural language generated by the user; a processing sub-module for inputting the natural language into the data processing model to obtain the data processing result; and a generation sub-module for generating the data processing request based on the data processing result and the target business system determined by the user.

[0140] Furthermore, based on any of the above embodiments, the processing submodule includes: an identification unit, used to perform keyword recognition operations on the natural language to obtain at least one keyword corresponding to the natural language; a first input unit, used to input the natural language into the data processing model if the number of keywords corresponding to the natural language is less than a preset number threshold; a second unit, used to select a preset number of target keywords that meet preset conditions from multiple keywords corresponding to the natural language according to preset data editing information if the number of keywords corresponding to the natural language is greater than a preset number threshold, and input the preset number of target keywords into the data processing model.

[0141] Furthermore, based on any of the above embodiments, the device also includes: a determination module for determining the task information corresponding to the target data; a detection module for detecting whether the task information meets the preset splitting conditions; a splitting module for, if so, performing a splitting operation on the task information according to preset data editing information to obtain at least one subtask; the calling module includes: a calling sub-module for calling the target business system based on the target data to execute the at least one subtask.

[0142] Furthermore, based on any of the above embodiments, the apparatus further includes: an acquisition module configured to acquire, in response to a data editing operation triggered by the user, parameter arrangement information and / or task splitting information generated by the user; and a splitting module configured to determine the parameter arrangement information and / or task splitting information as the data editing information.

[0143] Furthermore, based on any of the above embodiments, the business-related information includes domain knowledge content corresponding to the target business system. The optimization module includes a determination submodule configured to determine business-specific vocabulary in the data processing results. A replacement submodule configured to replace the business-specific vocabulary based on the domain knowledge content to obtain the target data.

[0144] Furthermore, based on any of the above embodiments, the business-related information includes data requirement information corresponding to the target business system, the data requirement information being obtained by parsing interface information in an interface entry request sent by the target business system. The optimization module includes an adjustment submodule for adjusting the data format of the data processing result according to the data requirement corresponding to the business system to obtain the target data.

[0145] Furthermore, based on any of the above embodiments, the business-related information includes domain knowledge content and data requirement information corresponding to the target business system. The optimization module includes a determination submodule for determining referential terms in the data processing results. A replacement submodule for replacing the referential terms based on the domain knowledge content and the data requirement information to obtain the target data.

[0146] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0147] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, including:

[0148] At least one processor. And

[0149] A memory in communication with the at least one processor.

[0150] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the data processing method as described in any of the above embodiments.

[0151] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the data processing method as described in any of the above embodiments.

[0152] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0153] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, such as Figure 7As shown, electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are intended to be examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0154] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0155] Various components in device 700 are connected to I / O interface 705, including an input unit 706, such as a keyboard, mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, optical disk, etc.; and a communication unit 709, such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0156] The computing unit 701 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the data processing method. For example, in some embodiments, the data processing method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the data processing method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the above-described data processing method by any other appropriate means (e.g., by means of firmware).

[0157] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0158] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0159] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0160] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0161] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0162] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship is established by computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and VPS services ("Virtual Private Servers" or simply "VPS"). The server may also be a server in a distributed system or a server integrated with blockchain.

[0163] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0164] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A data processing method, applied to a data processing device, wherein the data processing device is respectively in communication with a preset data processing model and at least one business system; comprising: Obtaining a data processing request, wherein the data processing request includes a data processing result obtained by the data processing model performing data processing based on the natural language generated by the user, and identification information of a target business system to be called; Determining business association information corresponding to the target business system; Performing a data optimization operation on the data processing result according to the business association information to obtain target data; Calling the target business system based on the target data according to the interface information of the target format to execute a task matching the target data; Before obtaining the data processing request, the method further includes: Respectively obtaining an interface entry request sent by each of the business systems, wherein the interface entry request includes interface information corresponding to the business system, and the format of the interface information corresponding to different business systems is different; Parsing the interface information to determine the format of the interface information; The format of the interface information is converted into a target format that matches the data processing model.

2. The method according to claim 1, wherein obtaining the data processing request comprises: Obtain user-generated natural language; Inputting the natural language into the data processing model to obtain the data processing result; The data processing request is generated based on the data processing result and the target business system determined by the user.

3. The method according to claim 2, wherein inputting the natural language into the data processing model comprises: Performing a keyword recognition operation on the natural language to obtain at least one keyword corresponding to the natural language; If the number of keywords corresponding to the natural language is less than a preset number threshold, inputting the natural language into the data processing model; If the number of keywords corresponding to the natural language is greater than a preset threshold, a preset number of target keywords that meet preset conditions are selected from the multiple keywords corresponding to the natural language according to preset data editing information, and the preset number of target keywords are input into the data processing model.

4. The method according to claim 1, further comprising: Determining task information corresponding to the target data; Detecting whether the task information meets the preset splitting conditions; If so, performing a splitting operation on the task information according to preset data editing information, or performing a splitting operation on the task information based on the data processing model to obtain at least one subtask; The calling the target business system based on the target data to execute a task matching the target data includes: The target business system is called based on the target data to execute the at least one subtask.

5. The method according to claim 3 or 4, further comprising: In response to the data editing operation triggered by the user, obtaining parameter arrangement information and / or task splitting information generated by the user; The parameter arrangement information and / or task splitting information is determined as the data editing information.

6. The method according to any one of claims 1 to 4, wherein the business association information includes domain knowledge content corresponding to the target business system; The performing a data optimization operation on the data processing result according to the business association information to obtain target data includes: determining business-specific vocabulary in the data processing results; The business-specific vocabulary is replaced based on the domain knowledge content to obtain the target data.

7. The method according to any one of claims 1 to 4, wherein the business association information includes data requirement information corresponding to the target business system, and the data requirement information is obtained by parsing interface information in the interface entry request sent by the target business system; The performing a data optimization operation on the data processing result according to the business association information to obtain target data includes: The data format of the data processing result is adjusted according to the data requirements corresponding to the business system to obtain the target data.

8. The method according to any one of claims 1 to 4, wherein the business association information includes domain knowledge content and data requirement information corresponding to the target business system; The performing a data optimization operation on the data processing result according to the business association information to obtain target data includes: Determining a referential vocabulary in the data processing result; The reference vocabulary is replaced according to the domain knowledge content and the data demand information to obtain the target data.

9. A data processing device, the data processing device being communicatively connected to a preset data processing model and at least one business system; comprising: an acquisition module, configured to acquire a data processing request, wherein the data processing request includes a data processing result obtained by the data processing model performing data processing based on the natural language generated by the user, and identification information of a target business system to be called; A determination module, configured to determine the business association information corresponding to the target business system; An optimization module, configured to perform a data optimization operation on the data processing result according to the business association information to obtain target data; The calling module includes a calling submodule, wherein the calling submodule is configured to call the target business system based on the target data according to the interface information of the target format to execute a task matching the target data; The device further comprises: an acquisition module, configured to respectively acquire the interface entry request sent by each of the business systems, wherein the interface entry request includes the interface information corresponding to the business system, and the format of the interface information corresponding to different business systems is different; A parsing module, configured to parse the interface information and determine a format corresponding to the interface information; The conversion module is used to convert the format of the interface information into a target format that matches the data processing model.

10. The apparatus according to claim 9, wherein the acquisition module comprises: The acquisition submodule is used to obtain the natural language generated by the user; a processing submodule, configured to input the natural language into the data processing model to obtain the data processing result; The generating submodule is used to generate the data processing request based on the data processing result and the target business system determined by the user.

11. The apparatus according to claim 10, wherein the processing submodule comprises: a recognition unit, configured to perform a keyword recognition operation on the natural language to obtain at least one keyword corresponding to the natural language; a first input unit, configured to input the natural language into the data processing model if the number of keywords corresponding to the natural language is less than a preset number threshold; The second unit is used to select a preset number of target keywords that meet preset conditions from multiple keywords corresponding to the natural language according to preset data editing information if the number of keywords corresponding to the natural language is greater than a preset number threshold, and input the preset number of target keywords into the data processing model.

12. The apparatus according to claim 9, further comprising: A determination module, configured to determine task information corresponding to the target data; A detection module, used to detect whether the task information meets the preset splitting conditions; a splitting module, configured to, if yes, split the task information according to preset data editing information to obtain at least one subtask; The calling module includes: The calling submodule is configured to call the target business system based on the target data to execute the at least one subtask.

13. The device according to claim 11 or 12, further comprising: an acquisition module, configured to acquire parameter arrangement information and / or task splitting information generated by the user in response to a data editing operation triggered by the user; A splitting module is used to determine the parameter arrangement information and / or task splitting information as the data editing information.

14. The apparatus according to any one of claims 9 to 12, wherein the business association information includes domain knowledge content corresponding to the target business system; The optimization module includes: A determination submodule, configured to determine business-specific vocabulary in the data processing result; The replacement submodule is used to perform a replacement operation on the business-specific vocabulary based on the domain knowledge content to obtain the target data.

15. The apparatus according to any one of claims 9 to 12, wherein the business association information comprises data requirement information corresponding to the target business system, the data requirement information being obtained by parsing interface information in an interface entry request sent by the target business system; The optimization module includes: The adjustment submodule is used to adjust the data format of the data processing result according to the data requirements corresponding to the business system to obtain the target data.

16. The apparatus according to any one of claims 9 to 12, wherein the business association information includes domain knowledge content and data requirement information corresponding to the target business system; The optimization module includes: A determination submodule, configured to determine a referential vocabulary in the data processing result; The replacement submodule is used to perform a replacement operation on the reference vocabulary according to the domain knowledge content and the data demand information to obtain the target data.

17. A data processing system comprising a data processing device, at least one business system, and a preset data processing model; in, The data processing device is communicatively connected to the at least one business system and the preset data processing model respectively; The data processing device is used to obtain a data processing request, wherein the data processing request includes a data processing result obtained by the data processing model performing data processing based on the natural language generated by the user, and identification information of the target business system to be called; The data processing device is used to determine the business association information corresponding to the target business system, perform data optimization operations on the data processing results according to the business association information to obtain target data, and call the target business system based on the target data according to the interface information of the target format to execute a task matching the target data; The business system is used to execute tasks matching the target data; Before obtaining the data processing request, the data processing device is also used to respectively obtain the interface entry request sent by each of the business systems, wherein the interface entry request includes the interface information corresponding to the business system, and the format of the interface information corresponding to different business systems is different; the interface information is parsed to determine the format corresponding to the interface information; and the format of the interface information is converted into a target format that matches the data processing model.

18. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the data processing method according to any one of claims 1 to 8.

19. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the data processing method according to any one of claims 1 to 8.

20. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the data processing method according to any one of claims 1 to 8.

Images