Artificial intelligence-based copywriting processing method and device, computer equipment and medium

Abstract

The invention belongs to the field of artificial intelligence and the field of financial science and technology, and relates to a document processing method and device based on artificial intelligence, computer equipment and a storage medium, and the method comprises the steps: receiving an original document set uploaded by a client, and carrying out the document comparison of the original document set and a maintenance document set to determine a changed document; obtaining an updated copywriting set based on the changed copywriting; obtaining the document type of the first document to be translated from the updated document set; if the copywriting type is a first preset type, preprocessing the first copywriting to obtain a second copywriting; calling a large language model to translate the second copywriting to obtain a first translation result; adjusting the translation result based on the adjustment strategy to obtain a second translation result; combining the first translation result and the second translation result to obtain a target translation document; and updating the maintenance copywriting set based on the target translation copywriting. In addition, the target translation copywriting may be stored in a blockchain. According to the method, the maintenance efficiency and accuracy of the maintenance copywriting set are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology and the field of financial technology, and in particular to a document processing method, device, computer equipment and storage medium based on artificial intelligence. Background Art

[0002] With the acceleration of globalization and the rapid development of mobile Internet technology, mobile applications (Apps) have become an indispensable part of people's daily lives. In order to attract and retain users worldwide, improve user experience and enhance market competitiveness, App multilingualization has become a crucial strategy. Multilingualization not only means that applications can transcend language barriers and cover a wider international market, but is also directly related to the improvement of user engagement, the enhancement of satisfaction, the shaping of brand image and the establishment of user loyalty.

[0003] At present, the mainstream solution for achieving App multilingualization mainly adopts a technical solution based on dynamic multilingual packages. This solution stores the translated copy files in the form of multilingual packages in the cloud or server. When the App is running, it dynamically downloads the corresponding language packages from the cloud to the local cache according to the user's language preferences. Subsequently, the original copy on the interface is replaced with the translated copy through the built-in mapping relationship or localization framework. This solution improves the efficiency and flexibility of updating language resources and reduces the frequency of re-releasing the App due to language updates. However, the dynamic multilingual package solution is highly dependent on manual maintenance and updating of translation files, and has a low degree of automation. This not only increases labor costs, but may also lead to uneven translation quality and affect user experience. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a text processing method, device, computer equipment and storage medium based on artificial intelligence to solve the technical problem that the dynamic multilingual package solution adopted by the existing App multilingualization is highly dependent on manual maintenance and updating of translation files, and has a low degree of automation, which not only increases labor costs, but also may lead to uneven translation quality and affect user experience.

[0005] In order to solve the above technical problems, the present application embodiment provides a document processing method based on artificial intelligence, which adopts the following technical solutions:

[0006] Receiving the original copy set uploaded by the client, and comparing the original copy set with the preset maintenance copy set to determine the corresponding change copy;

[0007] Recording the changed documents into a preset temporary storage structure to obtain a corresponding updated document set;

[0008] Acquire a first document to be translated from the updated document set, and acquire a document type of the first document; wherein the first document is any document included in the updated document set;

[0009] If the document type is a first preset type, preprocessing the first document to obtain a corresponding second document;

[0010] Calling a preset large language model to translate the second text to obtain a corresponding first translation result;

[0011] Adjusting the translation result based on a preset adjustment strategy to obtain a corresponding second translation result;

[0012] Merging the first translation result and the second translation result to obtain a corresponding target translation copy;

[0013] The maintenance document set is updated based on the target translation document.

[0014] Furthermore, the step of comparing the original document set with the preset maintenance document set to determine the corresponding change document specifically includes:

[0015] Get the preset data comparison script;

[0016] Executing the data comparison script to compare the original copy set with the maintenance copy set to obtain corresponding copy comparison results;

[0017] Based on the text comparison result, the changed text included in the original text set is identified.

[0018] Furthermore, the step of obtaining the text type of the first text specifically includes:

[0019] Obtaining annotation information corresponding to the first copy;

[0020] Performing information analysis on the annotation information based on preset annotation rules to obtain corresponding analysis results;

[0021] A copywriting type of the first copywriting is generated based on the analysis result.

[0022] Furthermore, the step of adjusting the translation result based on a preset adjustment strategy to obtain a corresponding second translation result specifically includes:

[0023] Call the preset editing interface;

[0024] Displaying the first translation result in the editing interface;

[0025] receiving an editing process corresponding to the first translation result input by an operator in the editing interface, and obtaining an edited translation result;

[0026] The edited translation result is used as the second translation result.

[0027] Furthermore, the step of merging the first translation result and the second translation result to obtain a corresponding target translation text specifically includes:

[0028] Storing the first translation result in a preset automatic translation database table;

[0029] storing the second translation result in a preset adjustment database table, and generating an editing mark corresponding to the second translation result in the manual translation database;

[0030] Generate a corresponding merge strategy based on the edit mark;

[0031] Based on the merging strategy, data merging is performed on the automatic translation database table and the adjustment database table to obtain corresponding merged data;

[0032] The target translation document is generated based on the merged data.

[0033] Furthermore, after the step of obtaining the text type of the first text, the method further includes:

[0034] If the text type is a second preset type, obtaining language environment information corresponding to the first text;

[0035] Sending the first copy and the language environment information to a designated business backend corresponding to the first copy;

[0036] Receiving a third translation result corresponding to the first text returned by the designated business backend;

[0037] The maintenance document set is updated based on the third translation result.

[0038] Furthermore, after the step of updating the maintenance document set based on the target translation document, the method further includes:

[0039] Determining whether a copy acquisition request sent by the client is received;

[0040] If so, detecting whether the client is in a cold start state;

[0041] If the client is in a cold start state, obtaining the latest version of the specified copy maintenance set;

[0042] The specified copy maintenance set is sent to the client.

[0043] In order to solve the above technical problems, the embodiment of the present application further provides a document processing device based on artificial intelligence, which adopts the following technical solution:

[0044] A comparison module, used for receiving an original copy set uploaded by a client, and comparing the original copy set with a preset maintenance copy set to determine a corresponding change copy;

[0045] A storage module, used to record the changed document into a preset temporary storage structure to obtain a corresponding updated document set;

[0046] A first acquisition module, configured to acquire a first document to be translated from the updated document set, and acquire a document type of the first document; wherein the first document is any document included in the updated document set;

[0047] A preprocessing module, configured to preprocess the first document to obtain a corresponding second document if the document type is a first preset type;

[0048] A translation module, used for calling a preset large language model to translate the second text to obtain a corresponding first translation result;

[0049] An adjustment module, used to adjust the translation result based on a preset adjustment strategy to obtain a corresponding second translation result;

[0050] A merging module, used to merge the first translation result and the second translation result to obtain a corresponding target translation copy;

[0051] The first updating module is used to update the maintenance document set based on the target translation document.

[0052] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0053] Receiving the original copy set uploaded by the client, and comparing the original copy set with the preset maintenance copy set to determine the corresponding change copy;

[0054] Recording the changed documents into a preset temporary storage structure to obtain a corresponding updated document set;

[0055] Acquire a first document to be translated from the updated document set, and acquire a document type of the first document; wherein the first document is any document included in the updated document set;

[0056] If the document type is a first preset type, preprocessing the first document to obtain a corresponding second document;

[0057] Calling a preset large language model to translate the second text to obtain a corresponding first translation result;

[0058] Adjusting the translation result based on a preset adjustment strategy to obtain a corresponding second translation result;

[0059] Merging the first translation result and the second translation result to obtain a corresponding target translation copy;

[0060] The maintenance document set is updated based on the target translation document.

[0061] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0062] Receiving the original copy set uploaded by the client, and comparing the original copy set with the preset maintenance copy set to determine the corresponding change copy;

[0063] Recording the changed documents into a preset temporary storage structure to obtain a corresponding updated document set;

[0064] Acquire a first document to be translated from the updated document set, and acquire a document type of the first document; wherein the first document is any document included in the updated document set;

[0065] If the document type is a first preset type, preprocessing the first document to obtain a corresponding second document;

[0066] Calling a preset large language model to translate the second text to obtain a corresponding first translation result;

[0067] Adjusting the translation result based on a preset adjustment strategy to obtain a corresponding second translation result;

[0068] Merging the first translation result and the second translation result to obtain a corresponding target translation copy;

[0069] The maintenance document set is updated based on the target translation document.

[0070] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0071] The present application first receives an original copy set uploaded by a client, and compares the original copy set with a preset maintenance copy set to determine a corresponding change copy; then records the change copy into a preset temporary storage structure to obtain a corresponding update copy set; then obtains a first copy to be translated from the update copy set, and obtains a copy type of the first copy; wherein the first copy is any copy included in the update copy set; if the copy type is a first preset type, preprocesses the first copy to obtain a corresponding second copy; subsequently calls a preset large language model to translate the second copy to obtain a corresponding first translation result; and further adjusts the translation based on a preset adjustment strategy. The translation result is adjusted to obtain a corresponding second translation result; the first translation result and the second translation result are merged to obtain a corresponding target translation copy; finally, the maintenance copy set is updated based on the target translation copy. In this way, the present application can automatically and quickly complete the update processing of the maintenance copy set based on the use of a large language model and an adjustment strategy, thereby realizing automated and intelligent maintenance processing of the maintenance copy set, effectively reducing the burden of manually maintaining translation files, reducing the maintenance cost of the maintenance copy set, and improving the efficiency and accuracy of translation, as well as improving the maintenance efficiency and intelligence of the maintenance copy set, and effectively maintaining the latest and accuracy of the maintenance copy set. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0073] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0074] Figure 2 A flowchart of an embodiment of a method for copywriting processing based on artificial intelligence according to the present application;

[0075] Figure 3 is a structural schematic diagram of an embodiment of an artificial intelligence-based document processing device according to the present application;

[0076] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0078] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0079] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0080] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0081] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0082] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0083] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0084] It should be noted that the artificial intelligence-based document processing method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based document processing device is generally set in the server / terminal device.

[0085] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0086] Continue to refer Figure 2 , showing a flow chart of an embodiment of a method for document processing based on artificial intelligence according to the present application. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted. The method for document processing based on artificial intelligence provided in the embodiment of the present application can be applied to any scenario that requires document processing, and the method for document processing based on artificial intelligence can be applied to products in these scenarios, for example, the maintenance and processing of insurance documents in the field of finance and insurance. The method for document processing based on artificial intelligence includes the following steps:

[0087] Step S201, receiving an original document set uploaded by a client, and performing a document comparison between the original document set and a preset maintenance document set to determine a corresponding change document.

[0088] In this embodiment, the electronic device (e.g. Figure 1The server / terminal device shown in the figure) can obtain the original copy set through a wired connection or a wireless connection. It should be pointed out that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future. The executor of this application is specifically a server. When the client is cold started (such as the first time the client is started or reopened after a long period of non-use), the original copy set in the local original copy library will be automatically uploaded to the translation center of the server. Among them, the above-mentioned specific implementation process of comparing the original copy set with the preset maintenance copy set to determine the corresponding change copy will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0089] Step S202, recording the changed document into a preset temporary storage structure to obtain a corresponding updated document set.

[0090] In this embodiment, the obtained change documents are recorded in a new temporary storage structure as an update document set.

[0091] Step S203: acquiring a first document to be translated from the update document set, and acquiring the document type of the first document.

[0092] In this embodiment, the first document is any document included in the update document set. The specific implementation process of obtaining the document type of the first document will be further described in detail in the subsequent specific embodiments of the present application, and will not be elaborated on here. In addition, the document type may include a first preset type or a second preset type.

[0093] Step S204: if the text type is a first preset type, preprocessing the first text to obtain a corresponding second text.

[0094] In this embodiment, the above-mentioned preprocessing refers to converting the first text into an input format required by a large language model, thereby obtaining a corresponding second text.

[0095] Step S205: calling a preset large language model to translate the second text to obtain a corresponding first translation result.

[0096] In this embodiment, the large language model can be called through an API or SDK, and the second text to be translated is sent to the large language model for translation, and the first translation result returned by the large language model is received and saved for subsequent processing.

[0097] Step S206: adjusting the translation result based on a preset adjustment strategy to obtain a corresponding second translation result.

[0098] In this embodiment, the specific implementation process of adjusting the translation result based on the preset adjustment strategy to obtain the corresponding second translation result will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0099] Step S207: merging the first translation result and the second translation result to obtain a corresponding target translation copy.

[0100] In this embodiment, the specific implementation process of merging the first translation result and the second translation result to obtain the corresponding target translation text will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0101] Step S208: updating the maintenance document set based on the target translation document.

[0102] In this embodiment, the target translation document can be converted into the format required for database operation. Then, a database transaction is used to ensure the atomicity of the entire update process. By traversing the target translation document, the following update operation is performed on each record (copy): Check whether there is a record with the same original key in the maintenance document set. If it exists, update the record (replace the copy content, update the timestamp, etc.). If it does not exist, insert a new record.

[0103] You can perform some basic queries to verify that the update is working as expected, and use unit tests or integration tests to ensure the correctness of the update logic. In addition, you can log the time, success / failure status, and any relevant error information of the update operation. Use a monitoring system to track the performance and reliability of the update operation.

[0104] The present application first receives an original copy set uploaded by a client, and compares the original copy set with a preset maintenance copy set to determine a corresponding change copy; then records the change copy into a preset temporary storage structure to obtain a corresponding update copy set; then obtains a first copy to be translated from the update copy set, and obtains a copy type of the first copy; wherein the first copy is any copy included in the update copy set; if the copy type is a first preset type, preprocesses the first copy to obtain a corresponding second copy; subsequently calls a preset large language model to translate the second copy to obtain a corresponding first translation result; and further adjusts the translation based on a preset adjustment strategy. The translation result is adjusted to obtain a corresponding second translation result; the first translation result and the second translation result are merged to obtain a corresponding target translation copy; finally, the maintenance copy set is updated based on the target translation copy. In this way, the present application can automatically and quickly complete the update processing of the maintenance copy set based on the use of a large language model and an adjustment strategy, thereby realizing automated and intelligent maintenance processing of the maintenance copy set, effectively reducing the burden of manually maintaining translation files, reducing the maintenance cost of the maintenance copy set, and improving the efficiency and accuracy of translation, as well as improving the maintenance efficiency and intelligence of the maintenance copy set, and effectively maintaining the latest and accuracy of the maintenance copy set.

[0105] In some optional implementations, the step S201 of comparing the original document set with the preset maintenance document set to determine the corresponding change document includes the following steps:

[0106] Get the preset data comparison script.

[0107] In this embodiment, a timed processing script, i.e., the data comparison script, is pre-written and is used to run regularly (e.g., every hour / day) to compare the original document set with the maintenance document set. Specifically, a database query (e.g., SQL JOIN or EXISTS) is used to find the changed document.

[0108] The data comparison script is executed to compare the original document set with the maintenance document set to obtain corresponding document comparison results.

[0109] In this embodiment, by executing the above data comparison script, the original document set and the maintenance document set can be automatically compared, and a corresponding document comparison result can be generated, which includes the changed document.

[0110] Based on the text comparison result, the changed text included in the original text set is identified.

[0111] In this embodiment, the key of the modified document exists in the original document set but does not exist in the maintenance document set or the content is different.

[0112] The present application obtains a preset data comparison script; then executes the data comparison script to compare the original copy set with the maintenance copy set to obtain a corresponding copy comparison result; and subsequently identifies the change copy included in the original copy set based on the copy comparison result. The present application can automatically and accurately complete the comparison process of comparing the original copy set with the preset maintenance copy set through the use of the data comparison script, thereby improving the processing efficiency of the copy comparison and ensuring the data accuracy of the obtained change copy.

[0113] In some optional implementations of this embodiment, the obtaining of the text type of the first text in step S203 includes the following steps:

[0114] Obtain annotation information corresponding to the first text.

[0115] In this embodiment, the copy in the client is pre-divided into two types (a first preset type and a second preset type). The first preset type of copy is a copy configured by an operation staff or designed by a product staff. The characteristics of this type of copy are that it is relatively short, relatively fixed, and has a low frequency of change; the second preset type of copy is a title copy of the content or insurance. This type of copy is generally long and complex and changeable. Among them, the first preset type can also be called a fixed copy, and the second preset type can also be called a variable copy. In addition, the difference between the first preset type of copy and the second preset type of copy can be distinguished by annotations, and different annotations can be given to the two types of copy in the text control.

[0116] The annotation information is analyzed based on preset annotation rules to obtain corresponding analysis results.

[0117] In this embodiment, corresponding annotation rules are defined in advance for two types of copy. Specifically, a first type of copy annotation corresponding to fixed copy is provided: it can be marked with the prefix "UI_" or the suffix "_Hint", such as "UI_Login Tips" or "Wrong Password_Hint". And a second type of copy annotation corresponding to variable copy is provided: it can be marked with the prefix "Info_" or the suffix "_Policy", such as "Info_Product Features" or "Privacy Policy_Policy". Among them, each copy is annotated in the design document or resource file. For example, in the comment area of ​​the design draft, or in a special copy resource file, the copy is annotated according to the above-mentioned annotation rules. Specifically, during programming implementation, corresponding annotations can be added to the code of the text control according to the annotations in the design document or resource file. For example, data-* attributes or custom attributes are used to store copy type information in HTML, which can be distinguished by comments or specific field tags in Android or iOS development.

[0118] A copywriting type of the first copywriting is generated based on the analysis result.

[0119] In this embodiment, prefix information or suffix information can be obtained from the above analysis results, and then the matching copy type can be determined according to the prefix information or suffix information. For example, if the analysis result contains the prefix "UI_" or the suffix "_Hint", it can be determined that the copy type matching the first copy is the first preset type (fixed copy).

[0120] The present application obtains annotation information corresponding to the first document; then analyzes the annotation information based on preset annotation rules to obtain corresponding analysis results; and subsequently generates the document type of the first document based on the analysis results. The present application obtains annotation information corresponding to the first document, and then analyzes the annotation information based on the use of annotation rules, so as to quickly and accurately generate the document type of the first document, effectively ensuring the accuracy of the document type of the first document.

[0121] In some optional implementations, step S206 includes the following steps:

[0122] Call the preset editing interface.

[0123] In this embodiment, an editable Web interface (i.e., editing interface) is developed in advance to display the translation results. The editing interface should allow operators to filter the translation results by language, time, and other conditions.

[0124] The first translation result is displayed in the editing interface.

[0125] In this embodiment, the operator can view the first translation result through the above-mentioned editing interface and evaluate the accuracy and fluency of the first translation result.

[0126] An editing process corresponding to the first translation result input by the operator in the editing interface is received, and the edited translation result is obtained.

[0127] In this embodiment, for unsatisfactory translation results in the first translation result, the operator can directly edit and modify them on the editing interface and generate corresponding edited translation results, wherein the editing history and modifier information of the editing process input in the editing interface are recorded at the same time.

[0128] The edited translation result is used as the second translation result.

[0129] This application calls a preset editing interface; then displays the first translation result in the editing interface; then receives the editing processing corresponding to the first translation result input by the operator in the editing interface, and obtains the edited translation result; and subsequently uses the edited translation result as the second translation result. This application provides operators with an editing and modification function for the first translation result based on the use of the editing interface intelligence, so that operators can perform corresponding editing processing on the first translation result generated by the large language model according to their actual needs, thereby obtaining the required second translation result, which effectively improves the work experience of operators and is conducive to improving the data accuracy and data reliability of the target translation copy generated based on the first translation result and the second translation result.

[0130] In some optional implementations, step S207 includes the following steps:

[0131] The first translation result is stored in a preset automatic translation database table.

[0132] In this embodiment, the automatic translation database table is a pre-constructed database table for storing automatic translation results, that is, the first translation results.

[0133] The second translation result is stored in a preset adjustment database table, and an editing mark corresponding to the second translation result is generated in the manual translation database.

[0134] In this embodiment, the above adjustment database table is a pre-constructed database table for storing manually edited translation results, that is, the above second translation results. And a field (i.e., edit mark) is added to the above adjustment database table to mark which texts have been manually edited. Among them, the priority of the manually edited translation results is higher than the translation results of the corresponding large language model. In addition, the above automatic translation database table and the adjustment database table contain the original key of the text for subsequent merging and updating. The above original key can be, for example, the original text ID or a combination of language code + text ID.

[0135] A corresponding merge strategy is generated based on the edit mark.

[0136] In this embodiment, the strategy content of the above-mentioned merge strategy includes: traversing all records (translation results) in the adjustment database table. For each record, check whether there is a record with the same original key in the automatic translation database table. If there is a record with the same original key, the record in the adjustment database table is used first (because manual editing has a higher priority). If there is no record with the same original key, the record in the adjustment database table is directly regarded as a new record.

[0137] Based on the merging strategy, data merging processing is performed on the automatic translation database table and the adjustment database table to obtain corresponding merged data.

[0138] In this embodiment, according to the policy content of the above-mentioned merging policy, the automatic translation database table and the adjustment database table can be merged to obtain corresponding merged data. The merged data includes records that are automatically translated by the large language model and not edited, as well as all manually edited records. In addition, during the data merging process, data conflicts may be encountered, especially when the automatically translated and manually edited documents both point to the same original document. The strategy for resolving conflicts is to give priority to the results after manual editing. And the conflict log can be recorded for future audit or further processing.

[0139] The target translation document is generated based on the merged data.

[0140] In this embodiment, the above-mentioned combined data can be directly used as the final target translation copy.

[0141] The present application stores the first translation result into a preset automatic translation database table; and stores the second translation result into a preset adjustment database table, and generates an editing mark corresponding to the second translation result in the manual translation database; then generates a corresponding merge strategy based on the editing mark; then merges the data of the automatic translation database table and the adjustment database table based on the merge strategy to obtain corresponding merged data; and subsequently generates the target translation copy based on the merged data. The present application stores the first translation result into a preset automatic translation database table; and stores the second translation result into a preset adjustment database table, and generates an editing mark corresponding to the second translation result in the manual translation database; then merges the data of the automatic translation database table and the adjustment database table based on the use of the merge strategy corresponding to the editing mark, so as to realize the rapid and accurate generation of the corresponding target translation copy, and ensure the accuracy and reliability of the obtained target translation copy data. It is beneficial for the subsequent automatic and rapid updating of the maintenance copy set based on the target translation copy, thereby realizing the automated and intelligent maintenance processing of the maintenance copy set, effectively reducing the burden of manual maintenance of translation files, reducing the maintenance cost of the maintenance copy set, improving the maintenance efficiency and intelligence of the maintenance copy set, and effectively maintaining the latest and accuracy of the maintenance copy set.

[0142] In some optional implementations of this embodiment, after step S203, the electronic device may further perform the following steps:

[0143] If the text type is the second preset type, the language environment information corresponding to the first text is obtained.

[0144] In this embodiment, the second preset type is a variable copy. For long, complex and variable copy such as content or insurance titles, the translation responsibility will be intelligently handed over to the original copy provider, and the client's language environment parameters will be combined to achieve flexible translation processing of the copy. The above language environment information is the current language environment information matching the first copy, for example, it can include simplified Chinese, English, etc.

[0145] The first copy and the language environment information are sent to a designated business backend corresponding to the first copy.

[0146] In this embodiment, the designated business backend is the business backend corresponding to the original copy provider of the first copy (such as content editor, insurance product designer, etc.). The first copy and the language environment information can be passed as parameters to the designated business backend. Among them, the original copy provider has prepared multi-language translation resources in advance, including professional translation teams or translation tools, to ensure that long and complex copies can be translated accurately and efficiently. And unified translation standards and specifications are formulated to ensure the accuracy and consistency of the translation results.

[0147] A third translation result corresponding to the first text and returned by the designated business background is received.

[0148] In this embodiment, after receiving the request including the first text and the language environment information, the designated business background first checks whether there is a ready-made translation text available. If there is, it returns directly; if not, the translation process is triggered. Specifically, if the designated business background has real-time translation capabilities, it will directly call the translation API or translation tool for translation. If it does not have real-time translation capabilities, it is necessary to send the translation task to the original text provider for processing, and then obtain the final third translation result.

[0149] The maintenance document set is updated based on the third translation result.

[0150] In this embodiment, the process of updating the maintenance document set based on the third translation result can refer to the above-mentioned process of updating the maintenance document set based on the target translation document, which will not be described in detail here.

[0151] If the present application detects that the document type is the second preset type, the language environment information corresponding to the first document is obtained; then the first document and the language environment information are sent to the designated business background corresponding to the first document; then the third translation result corresponding to the first document returned by the designated business background is received; and the maintenance document set is subsequently updated based on the third translation result. When the present application detects that the document type is the second preset type, the language environment information corresponding to the first document is intelligently obtained, and the designated business background corresponding to the first document is called to translate the first document and the language environment information to obtain the third translation result, thereby achieving more flexible and professional translation processing and ensuring the data accuracy of the third translation result. Subsequently, by updating the maintenance document set based on the third translation result, the automatic and intelligent maintenance processing of the maintenance document set is realized, which effectively reduces the burden of manually maintaining translation files, reduces the maintenance cost of the maintenance document set, and improves the maintenance efficiency and maintenance intelligence of the maintenance document set.

[0152] In some optional implementations of this embodiment, after step S208, the electronic device may further perform the following steps:

[0153] Determine whether a copy acquisition request sent by the client is received.

[0154] In this embodiment, the above-mentioned copy acquisition request is a request triggered by the client for pulling the latest copy maintenance set. Specifically, the above-mentioned copy acquisition request is an HTTP GET request sent by the client, which is used to request the latest maintenance copy set.

[0155] If so, detect whether the client is in a cold start state.

[0156] In this embodiment, it is possible to detect whether the client is cold started in the startup logic of the client, wherein the cold start may include, for example, the first startup or the startup after long-term non-use.

[0157] If the client is in a cold start state, the latest version of the specified copy maintenance set is obtained.

[0158] In this embodiment, during the maintenance process of the copy maintenance set, a version mark is performed on each generated copy maintenance set.

[0159] The specified copy maintenance set is sent to the client.

[0160] In this embodiment, after receiving the returned copy set data (specified copy maintenance set), the client will parse the specified copy maintenance set and save it in the local storage of the client, so that the local translation center of the client can translate the copy according to the latest maintenance copy set and display it in the corresponding text control in real time, thus completing the processing of local translation display.

[0161] This application determines whether a copy acquisition request sent by the client is received; if so, detects whether the client is in a cold start state; if the client is in a cold start state, obtains the latest version of the specified copy maintenance set; and subsequently sends the specified copy maintenance set to the client. When this application receives a copy acquisition request sent by the client, if it detects that the client is in a cold start state, it will automatically and intelligently send the latest version of the specified copy maintenance set to the client, and then the local translation center of the client will translate the copy according to the latest maintenance copy set, and display it in real time in the corresponding text control, so that the local translation display processing can be completed intelligently and accurately.

[0162] In some optional implementations, the process of displaying the text in the client includes: in the client application, the function of setting the text of the text control (such as TextView, Label, etc.) is intercepted (hooked) by programming means (such as AspectJ of Android, Aspects of iOS, etc.). In the intercepted function, the text to be set (i.e., the original text) is extracted. Then the local translation is attempted by sending the captured original text to the local translation center in the application. If the corresponding translation text exists in the local translation center, the translation text is directly displayed in the corresponding text control. If the corresponding translation text does not exist in the local translation center, the original text is displayed. The original text is then deduplicated and stored in the local original text library. Later, when the client is cold started next time, the text set in the local original text library is uploaded to the translation center of the server.

[0163] For the first preset type of copywriting, this application uses aspect technology to automatically collect online copywriting, upload it to the translation platform of the server, regularly perform incremental translation through the large language model, and then send the translated copywriting set to the client. Automatic translation of copywriting is achieved, labor costs are reduced, and the workload of multilingualization is effectively reduced.

[0164] In some optional implementations, the user information obtained is subject to the user's consent and complies with relevant laws and policies.

[0165] In addition, the non-Company software tools or components that appear in the embodiments of the present application are merely examples and do not represent actual use.

[0166] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0167] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned target translation documents, the above-mentioned target translation documents can also be stored in a node of a blockchain.

[0168] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0169] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0170] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0171] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0172] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0173] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a document processing device based on artificial intelligence, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0174] like Figure 3As shown, the artificial intelligence-based document processing device 300 described in this embodiment includes: a comparison module 301, a storage module 302, a first acquisition module 303, a preprocessing module 304, a translation module 305, an adjustment module 306, a merging module 307 and a first updating module 308. Among them:

[0175] The comparison module 301 is used to receive the original document set uploaded by the client, and compare the original document set with the preset maintenance document set to determine the corresponding change document;

[0176] The storage module 302 is used to record the changed document into a preset temporary storage structure to obtain a corresponding updated document set;

[0177] A first acquisition module 303 is used to acquire a first document to be translated from the updated document set, and acquire a document type of the first document; wherein the first document is any document included in the updated document set;

[0178] A preprocessing module 304, configured to preprocess the first document to obtain a corresponding second document if the document type is a first preset type;

[0179] A translation module 305 is used to call a preset large language model to translate the second text to obtain a corresponding first translation result;

[0180] An adjustment module 306, configured to adjust the translation result based on a preset adjustment strategy to obtain a corresponding second translation result;

[0181] A merging module 307 is used to merge the first translation result and the second translation result to obtain a corresponding target translation copy;

[0182] The first updating module 308 is used to update the maintenance document set based on the target translation document.

[0183] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based document processing method in the aforementioned implementation mode, and will not be repeated here.

[0184] In some optional implementations of this embodiment, the comparison module 301 includes:

[0185] The first acquisition submodule is used to acquire a preset data comparison script;

[0186] An execution submodule, used for executing the data comparison script to compare the original copy set with the maintenance copy set to obtain a corresponding copy comparison result;

[0187] The identification submodule is used to identify the changed documents included in the original document set based on the document comparison result.

[0188] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based document processing method in the aforementioned implementation mode, and will not be repeated here.

[0189] In some optional implementations of this embodiment, the first acquisition module 303 includes:

[0190] A second acquisition submodule, used to acquire annotation information corresponding to the first copy;

[0191] An analysis submodule, used to analyze the annotation information based on preset annotation rules to obtain corresponding analysis results;

[0192] The first generating submodule is used to generate a text type of the first text based on the analysis result.

[0193] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based document processing method in the aforementioned implementation mode, and will not be repeated here.

[0194] In some optional implementations of this embodiment, the adjustment module 306 includes:

[0195] Call submodule, used to call the preset editing interface;

[0196] A display submodule, used for displaying the first translation result in the editing interface;

[0197] An editing submodule, configured to receive an editing operation corresponding to the first translation result inputted by an operator in the editing interface, and obtain an edited translation result;

[0198] A determination submodule is configured to use the edited translation result as the second translation result.

[0199] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based document processing method in the aforementioned implementation mode, and will not be repeated here.

[0200] In some optional implementations of this embodiment, the merging module 307 includes:

[0201] A storage submodule, used for storing the first translation result in a preset automatic translation database table;

[0202] A second generating submodule, configured to store the second translation result in a preset adjustment database table, and generate an editing mark corresponding to the second translation result in the manual translation database;

[0203] A third generation submodule, used to generate a corresponding merge strategy based on the edit mark;

[0204] A merging submodule, used for performing data merging processing on the automatic translation database table and the adjustment database table based on the merging strategy to obtain corresponding merged data;

[0205] The fourth generating submodule is used to generate the target translation copy based on the merged data.

[0206] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based document processing method in the aforementioned implementation mode, and will not be repeated here.

[0207] In some optional implementations of this embodiment, the document processing device based on artificial intelligence further includes:

[0208] A second acquisition module, configured to acquire language environment information corresponding to the first text if the text type is a second preset type;

[0209] A first sending module, used for sending the first copy and the language environment information to a designated business backend corresponding to the first copy;

[0210] A receiving module, configured to receive a third translation result corresponding to the first text returned by the designated business backend;

[0211] The second updating module is used to update the maintenance document set based on the third translation result.

[0212] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based document processing method in the aforementioned implementation mode, and will not be repeated here.

[0213] In some optional implementations of this embodiment, the document processing device based on artificial intelligence further includes:

[0214] A judgment module, used to judge whether a copy acquisition request sent by the client is received;

[0215] A detection module, used for detecting whether the client is in a cold start state;

[0216] A third acquisition module is used to acquire the latest version of the specified copy maintenance set if the client is in a cold start state;

[0217] The second sending module is used to send the specified copy maintenance set to the client.

[0218] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based document processing method in the aforementioned implementation mode, and will not be repeated here.

[0219] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0220] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0221] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0222] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of a copywriting processing method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0223] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the artificial intelligence-based copy processing method.

[0224] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0225] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based copy processing method.

[0226] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0227] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A copywriting processing method based on artificial intelligence, characterized in that: The steps include: Receiving the original copy set uploaded by the client, and comparing the original copy set with the preset maintenance copy set to determine the corresponding change copy; Recording the changed documents into a preset temporary storage structure to obtain a corresponding updated document set; Acquire a first document to be translated from the updated document set, and acquire a document type of the first document; wherein the first document is any document included in the updated document set; If the document type is a first preset type, preprocessing the first document to obtain a corresponding second document; Calling a preset large language model to translate the second text to obtain a corresponding first translation result; Adjusting the translation result based on a preset adjustment strategy to obtain a corresponding second translation result; Merging the first translation result and the second translation result to obtain a corresponding target translation copy; The maintenance document set is updated based on the target translation document.

2. The method for copywriting processing based on artificial intelligence according to claim 1, characterized in that: The step of comparing the original document set with the preset maintenance document set to determine the corresponding change document specifically includes: Get the preset data comparison script; Executing the data comparison script to compare the original copy set with the maintenance copy set to obtain corresponding copy comparison results; Based on the text comparison result, the changed text included in the original text set is identified.

3. The method for copywriting processing based on artificial intelligence according to claim 1, characterized in that: The step of obtaining the text type of the first text specifically includes: Obtaining annotation information corresponding to the first copy; Performing information analysis on the annotation information based on preset annotation rules to obtain corresponding analysis results; A copywriting type of the first copywriting is generated based on the analysis result.

4. The method for copywriting processing based on artificial intelligence according to claim 1, characterized in that: The step of adjusting the translation result based on a preset adjustment strategy to obtain a corresponding second translation result specifically includes: Call the preset editing interface; Displaying the first translation result in the editing interface; receiving an editing process corresponding to the first translation result input by an operator in the editing interface, and obtaining an edited translation result; The edited translation result is used as the second translation result.

5. The method for copywriting processing based on artificial intelligence according to claim 1, characterized in that: The step of merging the first translation result and the second translation result to obtain a corresponding target translation text specifically includes: Storing the first translation result in a preset automatic translation database table; storing the second translation result in a preset adjustment database table, and generating an editing mark corresponding to the second translation result in the manual translation database; Generate a corresponding merge strategy based on the edit mark; Based on the merging strategy, data merging is performed on the automatic translation database table and the adjustment database table to obtain corresponding merged data; The target translation document is generated based on the merged data.

6. The method for copywriting processing based on artificial intelligence according to claim 1, characterized in that: After the step of obtaining the text type of the first text, the method further includes: If the text type is a second preset type, obtaining language environment information corresponding to the first text; Sending the first copy and the language environment information to a designated business backend corresponding to the first copy; Receiving a third translation result corresponding to the first text returned by the designated business backend; The maintenance document set is updated based on the third translation result.

7. The method for copywriting processing based on artificial intelligence according to claim 1, characterized in that: After the step of updating the maintenance copy set based on the target translation copy, the method further includes: Determining whether a copy acquisition request sent by the client is received; If so, detecting whether the client is in a cold start state; If the client is in a cold start state, obtaining the latest version of the specified copy maintenance set; The specified copy maintenance set is sent to the client.

8. A document processing device based on artificial intelligence, characterized in that: include: A comparison module, used for receiving an original copy set uploaded by a client, and comparing the original copy set with a preset maintenance copy set to determine a corresponding change copy; A storage module, used to record the changed document into a preset temporary storage structure to obtain a corresponding updated document set; A first acquisition module, configured to acquire a first document to be translated from the updated document set, and acquire a document type of the first document; wherein the first document is any document included in the updated document set; A preprocessing module, configured to preprocess the first document to obtain a corresponding second document if the document type is a first preset type; A translation module, used for calling a preset large language model to translate the second text to obtain a corresponding first translation result; An adjustment module, used to adjust the translation result based on a preset adjustment strategy to obtain a corresponding second translation result; A merging module, used to merge the first translation result and the second translation result to obtain a corresponding target translation copy; The first updating module is used to update the maintenance document set based on the target translation document.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the artificial intelligence-based document processing method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the artificial intelligence-based document processing method as described in any one of claims 1 to 7 are implemented.

Images