Text processing method, device, electronic device and computer storage medium

Abstract

The present invention provides a text processing method, device, electronic device, and computer storage medium, comprising obtaining a to-be-processed file carried by a service request submitted by a user; determining subject data corresponding to the to-be-processed file based on the type of the service request; extracting key fields from the subject data based on historical tree-structured data corresponding to the service request type, the historical tree-structured data being obtained by processing files carried by service requests within a historical timeframe; constructing corresponding target tree-structured data based on the relationships between the key fields when it is determined that the key fields meet preset conditions; and generating an execution script corresponding to the service request based on the target tree-structured data. The above method can improve processing efficiency and accuracy.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a text processing method, device, electronic device and computer storage medium. Background Art

[0002] With the continuous development of computer technology, the types of services provided by the banking industry are also increasing. In order to better handle service requests, text processing of service requests submitted by users is often performed manually. Due to the continuous increase in service types, a large amount of manpower is required, resulting in low efficiency and prone to processing errors. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a text processing method, device, electronic device, and computer storage medium to solve the problems of low text processing efficiency and proneness to processing errors in the prior art.

[0004] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0005] A first aspect of an embodiment of the present invention provides a text processing method, the method comprising:

[0006] Obtain the pending files carried in the service request submitted by the user;

[0007] Determining, based on the type corresponding to the service request, body data corresponding to the file to be processed;

[0008] extracting key fields from the main body data based on historical tree-structured data corresponding to the service request type, the historical tree-structured data being obtained by processing files carried by service requests within a historical period;

[0009] When it is determined that the key fields meet the preset conditions, constructing corresponding target tree structure data according to the relationship between the key fields;

[0010] An execution script corresponding to the service request is generated based on the target tree structure data.

[0011] Optionally, determining the body data corresponding to the file to be processed based on the type corresponding to the service request includes:

[0012] determining a target rule corresponding to the type of the service request;

[0013] Based on the target rule, subject data corresponding to the target rule is determined.

[0014] Optionally, the process of obtaining historical tree structure data by processing files carried by service requests within a historical time includes:

[0015] Get the text carried by all service requests in the historical time;

[0016] For each text, the text is analyzed and processed to obtain historical key fields;

[0017] Determining the relationship between the historical key fields based on the type corresponding to the service request;

[0018] Based on the relationship between the historical key fields, corresponding historical tree structure data is constructed.

[0019] Optionally, extracting key fields from the main body data based on the historical tree structure data corresponding to the service request type includes:

[0020] Determining a corresponding target historical key field based on the historical tree structure data corresponding to the service request type;

[0021] Data corresponding to the target historical key field is extracted from the subject data, and the data is used as the key field.

[0022] Optionally, constructing corresponding target tree structure data according to the relationship between the key fields includes:

[0023] Determining the relationship between the key fields based on the type corresponding to the service request;

[0024] Based on the relationship between the key fields, corresponding target tree structure data is constructed.

[0025] A second aspect of an embodiment of the present invention provides a text processing device, comprising:

[0026] An acquisition unit, used to acquire a file to be processed carried in a service request submitted by a user;

[0027] a determining unit, configured to determine the body data corresponding to the file to be processed based on the type corresponding to the service request;

[0028] an extraction unit, configured to extract key fields from the main body data based on historical tree structure data corresponding to the service request type, the historical tree structure data being obtained by processing files carried by service requests within a historical period;

[0029] A construction unit, configured to construct corresponding target tree structure data according to the relationship between the key fields when it is determined that the key fields meet the preset conditions;

[0030] An execution unit is configured to generate an execution script corresponding to the service request based on the target tree structure data.

[0031] Optionally, the determining unit is specifically configured to: determine a target rule corresponding to the type of the service request; and determine subject data corresponding to the target rule based on the target rule.

[0032] Optionally, the extraction unit is specifically used to: determine the corresponding target historical key field based on the historical tree structure data corresponding to the service request type; extract data corresponding to the target historical key field from the main data, and use the data as the key field.

[0033] A third aspect of an embodiment of the present invention shows an electronic device, which is used to run a program, wherein the program, when running, executes the text processing method shown in the first aspect of the embodiment of the present invention.

[0034] A fourth aspect of an embodiment of the present invention shows a computer storage medium, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the text processing method shown in the first aspect of the embodiment of the present invention.

[0035] Based on the above-mentioned embodiments of the present invention, a text processing method, device, electronic device, and computer storage medium are provided. The method includes: obtaining a to-be-processed file carried by a service request submitted by a user; determining the main body data corresponding to the to-be-processed file based on the type of the service request; extracting key fields from the main body data based on historical tree structure data corresponding to the service request type, wherein the historical tree structure data is obtained by processing files carried by service requests within a historical period; when it is determined that the key fields meet preset conditions, constructing corresponding target tree structure data based on the relationships between the key fields; and generating an execution script corresponding to the service request based on the target tree structure data. In the embodiments of the present invention, manual processing is not required. In the current online service request form, some key text elements need to be extracted from it as input source data for subsequent implementation work. Based on the type of the service request, determining the main body data corresponding to the to-be-processed file; then, extracting key fields from the main body data based on the historical tree structure data corresponding to the service request type; when it is determined that the key fields meet preset conditions, constructing corresponding target tree structure data based on the relationships between the key fields; and generating an execution script corresponding to the service request based on the target tree structure data. The above method can not only improve processing efficiency but also improve accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0037] Figure 1 A flowchart illustrating a text processing method according to an embodiment of the present invention is provided;

[0038] Figure 2 A schematic diagram of a multi-branch tree structure shown in an embodiment of the present invention;

[0039] Figure 3 A schematic structural diagram of a text processing device according to an embodiment of the present invention;

[0040] Figure 4 The figure is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0042] In this application, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0043] In an embodiment of the present invention, manual processing is not required. In the current online service request form, some key text elements need to be extracted from it as input source data for subsequent implementation work. Based on the type corresponding to the service request, the main body data corresponding to the file to be processed is determined; then, through the historical tree structure data corresponding to the service request type, the key fields in the main body data are extracted; when it is determined that the key fields meet the preset conditions, the corresponding target tree structure data is constructed according to the relationship between the key fields; based on the target tree structure data, an execution script corresponding to the service request is generated. The above method can not only improve processing efficiency, but also improve accuracy.

[0044] See also Figure 1 , which is a flow chart of a text processing method according to an embodiment of the present invention, the method includes:

[0045] Step S101: Obtain the to-be-processed file carried in the service request submitted by the user.

[0046] In the specific implementation of step S101 , the service request page is accessed according to a preset execution frequency, so as to obtain the to-be-processed file carried in the service request by using a script corresponding to the service request submitted by the user.

[0047] It should be noted that the scripts corresponding to the service request submitted by the user are scripts of various types written in advance according to the page features of the online service request, and a direct relationship between the service request type and each script is established.

[0048] It should be further explained that the script can be a python script in the computer programming language.

[0049] Step S102: Based on the type corresponding to the service request, determine the body data corresponding to the file to be processed.

[0050] It should be noted that the specific implementation of step S102 of determining the main body data corresponding to the to-be-processed file based on the type corresponding to the service request includes the following steps:

[0051] Step S11: Determine a target rule corresponding to the type of the service request.

[0052] In the specific implementation of step S11 , a rule corresponding to the service request is obtained from a plurality of preset rules and is set as a target rule.

[0053] It should be noted that the preset rules are rules that are set based on multiple experiences and are in line with each type of request.

[0054] Step S12: determining the subject data corresponding to the target rule based on the target rule.

[0055] In the specific implementation of step S12, the service request number and the corresponding main content that meet the target rules are captured.

[0056] Step S103: extracting key fields from the main body data based on the historical tree structure data corresponding to the service request type.

[0057] In step S103, the historical tree structure data is obtained by processing files carried by service requests within a historical period.

[0058] It should be noted that the process of obtaining historical tree structure data by processing the files carried by service requests within the historical time includes the following steps:

[0059] Step S21: Obtain the text carried by all service requests within a historical period.

[0060] It should be noted that the historical time period is set based on multiple experiments, for example, it can be set to the past three months.

[0061] Step S22: For each text, analyze and process the text to obtain historical key fields.

[0062] In the specific implementation of step S22 , according to the service request type corresponding to each service request, a sampling statistics is performed on the service requests within the historical time period to determine the service request body content of each service request.

[0063] It should be noted that the sampling rate of sampling statistics must ensure that all text element structure types are covered as much as possible.

[0064] The service request body content includes at least two historical key fields, namely target text elements, which are useful elements set in advance.

[0065] Step S23: Based on the type corresponding to the service request, determine the relationship between the historical key fields.

[0066] In the specific implementation of step S23 , for each service request body content, the association relationship between each target text element is analyzed and the corresponding combination rules are summarized.

[0067] It should be noted that the specific implementation process of step S23 can be achieved through technologies such as machine learning.

[0068] For example, the service request body content q corresponding to service request A contains four target text elements, ABCD, as shown in the following example.

[0069] …[Text Element A]…[Text Element B]…[Text Element C]…[Text Element D]…

[0070] Among them, “…” is a non-useful text element.

[0071] For example, if the service request body content q corresponding to the service request A contains four target text elements ABCD, the association relationship between each target text element is analyzed and the following corresponding rules are summarized.

[0072] Rule 1: Text element A can correspond to one or more combinations of text element B, text element C, and text element D. Therefore, text element A must come before text element B, text element C, and text element D, and can be expressed as text element A…text element A….

[0073] Rule 2: Text element B can correspond to one or more combinations of text element C and text element D. Text element B can be before text element C or after text element D, so it is expressed as text element B (text element C...text element D) or (text element C...text element D) text element B.

[0074] Rule 3: The combination of text element C and text element D corresponds to only one text element B.

[0075] Rule 4: The relationship between text element C and text element D is many-to-many, expressed as text element C text element D, text element C text element D text element D… text element D, text element C text element C… text element C text element D, text element C text element C… text element C text element D text element D… text element D.

[0076] Step S24: Based on the relationship between the historical key fields, corresponding historical tree structure data is constructed.

[0077] In the specific implementation of step S23 , an initial history tree structure is drawn based on the one-to-one, one-to-many, many-to-one or many-to-many relationships between elements in the combination rules between the history key fields obtained above.

[0078] It should be noted that the initial history tree structure is an N-layer multi-branch tree structure, where N is a positive integer greater than or equal to 2.

[0079] For example, if the service request body q corresponding to service request A contains four target text elements, ABCD. Based on the one-to-one, one-to-many, many-to-one, or many-to-many relationships between elements in the combination rules between the target text elements obtained above, that is, find all combinations of text element C and text element D, as well as text element A and text element B corresponding to the combination of text element C and text element D, and draw a three-layer multi-branch tree structure based on the above relationships, such as Figure 2 shown.

[0080] In an embodiment of the present invention, the specific implementation of step S103 of extracting key fields from the subject data based on the historical tree structure data corresponding to the service request type includes the following steps:

[0081] Step S31: Determine the corresponding target historical key field based on the historical tree structure data corresponding to the service request type.

[0082] In the specific implementation of step S31 , the historical tree structure data corresponding to the service request type is parsed to determine the corresponding target historical key field.

[0083] Step S32: extracting data corresponding to the target historical key field from the main body data, and using the data as the key field.

[0084] In the specific implementation of step S32, data corresponding to the target historical key field is searched from the main body data by configuring a regular expression, and is used as the key field, ie, the file element.

[0085] Step S104: Determine whether the key field meets the preset conditions. If it is determined that the key field meets the preset conditions, execute step S105. If it is determined that the key field does not meet the preset conditions, return to execute step S103, that is, filter the key field again.

[0086] In the process of implementing step S104, it is determined whether there is any missing field based on the key field, that is, whether all text elements can be filtered out, that is, it is determined whether each target historical key field has a corresponding key field. If there is a corresponding key field, it is determined that the field where it appears is not missing, and step S105 is executed. If there is no corresponding key field, it is determined that the field where it appears is missing, and the process returns to step S103, that is, the key field is filtered again.

[0087] It should be noted that the preset conditions are set according to actual conditions, such as whether there are any missing fields.

[0088] Step S105: construct corresponding target tree structure data according to the relationship between the key fields.

[0089] It should be noted that the specific implementation of step S105 includes the following steps:

[0090] Step S41: Determine the relationship between the key fields based on the type corresponding to the service request.

[0091] In the specific implementation of step S41 , the association relationship between the key fields is analyzed based on the type corresponding to the service request.

[0092] Step S42: Based on the relationship between the key fields, construct corresponding target tree structure data.

[0093] In the specific implementation of step S42 , the target tree structure data is drawn based on the one-to-one, one-to-many, many-to-one or many-to-many relationships between elements among the key fields obtained above.

[0094] Step S106: Generate an execution script corresponding to the service request based on the target tree structure data.

[0095] In the specific implementation of step S106 , the target tree structure data is input into an automated script generation model to generate an execution script corresponding to the service request.

[0096] It should be noted that the automated script generation model is developed in advance based on set standards.

[0097] In an embodiment of the present invention, manual processing is not required. In the current online service request form, some key text elements need to be extracted from it as input source data for subsequent implementation work. Based on the type corresponding to the service request, the main body data corresponding to the file to be processed is determined; then, through the historical tree structure data corresponding to the service request type, the key fields in the main body data are extracted; when it is determined that the key fields meet the preset conditions, the corresponding target tree structure data is constructed according to the relationship between the key fields; based on the target tree structure data, an execution script corresponding to the service request is generated. The above method can not only improve processing efficiency, but also improve accuracy.

[0098] Corresponding to the text processing method shown in the above embodiment of the present invention, the embodiment of the present invention also discloses a text processing device, such as Figure 3 FIG. 1 is a schematic diagram showing a structure of a text processing device according to an embodiment of the present invention, wherein the device includes:

[0099] The acquisition unit 301 is configured to acquire the to-be-processed file carried in the service request submitted by the user.

[0100] The determining unit 302 is configured to determine the body data corresponding to the file to be processed based on the type corresponding to the service request.

[0101] The extraction unit 303 is configured to extract key fields from the main body data based on historical tree structure data corresponding to the service request type, wherein the historical tree structure data is obtained by processing files carried by service requests within a historical period.

[0102] The construction unit 304 is configured to construct corresponding target tree structure data according to the relationship between the key fields when it is determined that the key fields meet the preset conditions.

[0103] The execution unit 305 is configured to generate an execution script corresponding to the service request based on the target tree structure data.

[0104] It should be noted that the specific principles and execution processes of each unit in the text processing device disclosed in the above embodiment of the present invention are the same as the text processing method shown in the above embodiment of the present invention. Please refer to the corresponding parts of the text processing method disclosed in the above embodiment of the present invention, and no further details will be given here.

[0105] In an embodiment of the present invention, manual processing is not required. In the current online service request form, some key text elements need to be extracted from it as input source data for subsequent implementation work. Based on the type corresponding to the service request, the main body data corresponding to the file to be processed is determined; then, through the historical tree structure data corresponding to the service request type, the key fields in the main body data are extracted; when it is determined that the key fields meet the preset conditions, the corresponding target tree structure data is constructed according to the relationship between the key fields; based on the target tree structure data, an execution script corresponding to the service request is generated. The above method can not only improve processing efficiency, but also improve accuracy.

[0106] Optionally, based on the text processing device shown in the above embodiment of the present invention, the determination unit 302 is specifically used to: determine a target rule corresponding to the type of the service request; and determine the subject data corresponding to the target rule based on the target rule.

[0107] Optionally, based on the text processing device shown in the above-mentioned embodiment of the present invention, the extraction unit 303 is specifically used to: determine the corresponding target historical key field based on the historical tree structure data corresponding to the service request type; extract data corresponding to the target historical key field from the main data, and use the data as the key field.

[0108] Optionally, based on the text processing device shown in the above-mentioned embodiment of the present invention, a construction unit 304 of historical tree structure data obtained by processing the files carried by the service requests within the historical time is specifically used to: obtain the text carried by all service requests within the historical time; for each text, analyze and process the text to obtain historical key fields; based on the type corresponding to the service request, determine the relationship between the historical key fields; based on the relationship between the historical key fields, construct corresponding historical tree structure data.

[0109] Optionally, based on the text processing device shown in the above-mentioned embodiment of the present invention, a construction unit 304 for constructing corresponding target tree structure data according to the relationship between the key fields is specifically used to: determine the relationship between the key fields based on the type corresponding to the service request; and construct corresponding target tree structure data based on the relationship between the key fields.

[0110] Based on the text processing device disclosed in the above embodiment of the present disclosure, each of the above modules can be implemented by a hardware device consisting of a processor and a memory. Specifically, each of the above modules is stored in the memory as a program unit, and the processor executes the program unit stored in the memory to implement text processing.

[0111] The processor contains a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and image security can be hardened by adjusting kernel parameters.

[0112] The present disclosure provides a computer storage medium, which includes a text processing program, wherein the program is executed by a processor to implement Figure 1 The text processing method.

[0113] The embodiment of the present disclosure provides a processor for running a program, wherein the program is executed when it is running. Figure 1 Public text processing methods.

[0114] The present disclosure provides an electronic device 40, such as Figure 4 , which is a structural diagram of an electronic device 40 provided in an embodiment of the present disclosure.

[0115] The electronic device in the embodiments of the present disclosure may be a server, a PC, a PAD, a mobile phone, etc.

[0116] The electronic device includes at least one processor 401 , at least one memory 403 connected to the processor, and a bus 402 .

[0117] The processor 401 and the memory 403 communicate with each other via the bus 402. The processor 401 is configured to execute the program stored in the memory 403.

[0118] Memory 403 is used to store a program, which is at least used to: obtain a file to be processed carried by a service request submitted by a user; determine the main body data corresponding to the file to be processed based on the type corresponding to the service request; extract key fields in the main body data based on historical tree structure data corresponding to the service request type, the historical tree structure data being obtained by processing files carried by service requests within a historical time; when it is determined that the key fields meet preset conditions, construct corresponding target tree structure data according to the relationship between the key fields; and generate an execution script corresponding to the service request based on the target tree structure data.

[0119] The present application also provides a computer program product, which, when executed on an electronic device, is adapted to execute a program for initializing the following method steps:

[0120] Obtain a file to be processed carried by a service request submitted by a user; determine the main body data corresponding to the file to be processed based on the type corresponding to the service request; extract key fields in the main body data based on historical tree structure data corresponding to the service request type, the historical tree structure data being obtained by processing files carried by service requests within a historical time; when it is determined that the key fields meet preset conditions, construct corresponding target tree structure data according to the relationship between the key fields; and generate an execution script corresponding to the service request based on the target tree structure data.

[0121] The present application is described with reference to the flowcharts and / or block diagrams of the methods, 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 device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0122] In a typical configuration, the device includes one or more processors (CPUs), memory, and a bus. The device may also include input / output interfaces, network interfaces, and the like.

[0123] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip. Memory is an example of a computer-readable medium.

[0124] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0125] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For relevant parts, refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0126] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0127] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A text processing method, characterized in that: The method comprises: Obtain the pending files carried in the service request submitted by the user; determining a target rule corresponding to the type of the service request; determining, based on the target rule, subject data corresponding to the target rule; Determining a corresponding target historical key field based on historical tree structure data corresponding to the service request type; the historical tree structure data is constructed based on the relationship between the historical key fields; and a mapping relationship exists between the service request type and the historical key fields; Extracting data corresponding to the target historical key field from the main body data and using the data as the key field, the historical tree structure data is obtained by processing files carried by service requests within a historical period; When it is determined that the key fields meet the preset conditions, corresponding target tree structure data is constructed according to the relationship between the key fields; the preset conditions include whether there is a field missing; The target tree structure data is input into an automated script generation model to generate an execution script corresponding to the service request.

2. The method according to claim 1, characterized in that The process of obtaining the historical tree structure data by processing the files carried by the service requests within the historical time includes: Get the text carried by all service requests in the historical time; For each text, the text is analyzed and processed to obtain historical key fields; Determining the relationship between the historical key fields based on the type corresponding to the service request; Based on the relationship between the historical key fields, corresponding historical tree structure data is constructed.

3. The method according to claim 1, characterized in that Constructing corresponding target tree structure data according to the relationship between the key fields, including: Determining the relationship between the key fields based on the type corresponding to the service request; Based on the relationship between the key fields, corresponding target tree structure data is constructed.

4. A text processing device, characterized in that: The device comprises: An acquisition unit, used to acquire a file to be processed carried in a service request submitted by a user; a determining unit, configured to determine a target rule corresponding to the type of the service request; and determine subject data corresponding to the target rule based on the target rule; An extraction unit is configured to determine a corresponding target historical key field based on historical tree structure data corresponding to the service request type; extract data corresponding to the target historical key field from the main body data, and use the data as the key field, wherein the historical tree structure data is obtained by processing files carried by service requests within a historical time period; the historical tree structure data is constructed based on relationships between the historical key fields; and a mapping relationship exists between the service request type and the historical key fields; A construction unit is configured to construct corresponding target tree structure data according to the relationship between the key fields when it is determined that the key fields meet a preset condition; the preset condition includes whether there is a field missing; The execution unit is used to input the target tree structure data into an automated script generation model to generate an execution script corresponding to the service request.

5. An electronic device, characterized in that: The electronic device is used to run a program, wherein the program executes the text processing method according to any one of claims 1 to 3 when running.

6. A computer storage medium, characterized in that The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the text processing method according to any one of claims 1 to 3.

Images