Intelligent editing method, device, electronic device and storage medium for platform data

Abstract

The present disclosure relates to a method, device, electronic device and storage medium for intelligent editing of platform data, the method comprising: in response to receiving a natural language editing instruction for the current platform data of a target platform, generating a query instruction according to the natural language editing instruction and the platform data; calling a generative pre-trained converter GPT model based on the query instruction to obtain an operation instruction output by the GPT model; and executing the operation instruction to edit the platform data when the operation instruction output by the GPT model conforms to the specified editing format of the platform data. According to the embodiment of the present disclosure, the GPT model can be effectively used to assist the target platform to automatically and intelligently edit the platform data.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a method, device, electronic device and storage medium for intelligent editing of platform data. Background Art

[0002] With the continuous iteration and upgrading of the GPT (Generative Pre-Trained Transformer) model, it has become a development trend to use the GPT model to assist humans in realizing intelligent operations to improve productivity and reduce operating costs. Summary of the invention

[0003] In view of this, the present disclosure proposes a method, device, electronic device and storage medium for intelligent editing of platform data, which can use the GPT model to assist the target platform to automatically and intelligently edit platform data.

[0004] According to one aspect of the present disclosure, a method for intelligently editing platform data is provided, comprising: in response to receiving a natural language editing instruction for current platform data of a target platform, generating a query instruction according to the natural language editing instruction and the platform data; calling a generative pre-trained transformer GPT model based on the query instruction to obtain an operation instruction output by the GPT model; and executing the operation instruction to edit the platform data when the operation instruction output by the GPT model conforms to a specified editing format of the platform data.

[0005] In a possible implementation, the query instruction is generated based on the natural language editing instruction and the platform data, including: converting the platform data into JSON data in JSON format and generating corresponding JSON description data, wherein the JSON description data is used to describe the format and specifications of the JSON data; filling the natural language editing instruction, the JSON data and the JSON description data into a preset query template to obtain a query instruction.

[0006] In one possible implementation, the query instruction is used to instruct the GPT model to convert natural language editing instructions into operation instructions that conform to the JSON patch format, wherein the specified editing format includes the JSON patch format, and the JSON patch format is a format for describing changes made to JSON data.

[0007] In a possible implementation, the JSON description data includes JSON Schema data, and the JSON patch format includes JSON Patch format.

[0008] In one possible implementation, after calling the generative pre-trained transformer GPT model based on the query instruction and obtaining the operation instructions output by the GPT model, the method also includes: detecting whether the operation instructions output by the GPT model conform to the JSON patch format; when the operation instructions output by the GPT model conform to the JSON patch format, determining that the operation instructions output by the GPT model conform to the specified editing format of the platform data; or, when the operation instructions output by the GPT model do not conform to the JSON patch format, the operation instructions output by the GPT model do not conform to the specified editing format of the platform data.

[0009] In one possible implementation, the method further includes: when the operation instructions output by the GPT model do not conform to the specified editing format of the platform data, displaying the operation instructions output by the GPT model, the displayed operation instructions are used to guide the user to issue natural language auxiliary instructions, and the natural language auxiliary instructions are used to assist the GPT model to output operation instructions that conform to the specified editing format; in response to receiving the natural language auxiliary instructions issued for the displayed operation instructions, calling the GPT model based on the natural language auxiliary instructions to obtain the operation instructions re-output by the GPT model; when the operation instructions re-output by the GPT model conform to the specified editing format, executing the operation instructions re-output by the GPT model to edit the platform data.

[0010] In one possible implementation, the natural language editing instruction includes an object to be edited in the platform data and an editing method of the object, wherein the object includes at least one of the following: layout of page components, page component configuration, general page configuration, and functional controls; the editing method includes at least one of the following: adding, deleting, modifying, moving, and copying.

[0011] According to another aspect of the present disclosure, there is provided an intelligent editing device for platform data, comprising: an instruction generation module, for generating a query instruction in response to receiving a natural language editing instruction for current platform data of a target platform according to the natural language editing instruction and the platform data; a model calling module, for calling a generative pre-trained transformer GPT model based on the query instruction to obtain an operation instruction output by the GPT model; and an instruction execution module, for executing the operation instruction output by the GPT model to edit the platform data when the operation instruction conforms to a specified editing format of the platform data.

[0012] In a possible implementation, the query instruction is generated based on the natural language editing instruction and the platform data, including: converting the platform data into JSON data in JSON format and generating corresponding JSON description data, wherein the JSON description data is used to describe the format and specifications of the JSON data; filling the natural language editing instruction, the JSON data and the JSON description data into a preset query template to obtain a query instruction.

[0013] In one possible implementation, the query instruction is used to instruct the GPT model to convert natural language editing instructions into operation instructions that conform to the JSON patch format, wherein the specified editing format includes the JSON patch format, and the JSON patch format is a format for describing changes made to JSON data.

[0014] In a possible implementation, the JSON description data includes JSON Schema data, and the JSON patch format includes JSON Patch format.

[0015] In one possible implementation, after calling the generative pre-trained transformer GPT model based on the query instruction and obtaining the operation instructions output by the GPT model, the device also includes: a format detection module, used to detect whether the operation instructions output by the GPT model conform to the JSON patch format; when the operation instructions output by the GPT model conform to the JSON patch format, determining that the operation instructions output by the GPT model conform to the specified editing format of the platform data; or, when the operation instructions output by the GPT model do not conform to the JSON patch format, the operation instructions output by the GPT model do not conform to the specified editing format of the platform data.

[0016] In one possible implementation, the device also includes: a display module, which is used to display the operation instructions output by the GPT model when the operation instructions output by the GPT model do not conform to the specified editing format of the platform data, and the displayed operation instructions are used to guide the user to issue natural language auxiliary instructions, and the natural language auxiliary instructions are used to assist the GPT model to output operation instructions that conform to the specified editing format; the model calling module 112 is also used to respond to receiving natural language auxiliary instructions issued for the displayed operation instructions, call the GPT model based on the natural language auxiliary instructions, and obtain the operation instructions re-output by the GPT model; the instruction execution module 113 is also used to execute the operation instructions re-output by the GPT model when the operation instructions re-output by the GPT model conform to the specified editing format to edit the platform data.

[0017] In one possible implementation, the natural language editing instruction includes an object to be edited in the platform data and an editing method of the object, wherein the object includes at least one of the following: layout of page components, page component configuration, general page configuration, and functional controls; the editing method includes at least one of the following: adding, deleting, modifying, moving, and copying.

[0018] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0019] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0020] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0021] According to an embodiment of the present disclosure, by calling the GPT model based on the natural language editing instructions issued by the user and the query instructions generated by the current platform data of the target platform, the GPT model converts the natural language editing instructions into operation instructions that conform to the specified editing format, and executes the operation instructions to edit the platform data. This enables the GPT model to assist the target platform in automatically and intelligently editing the platform data. Compared with manually editing the platform data, the editing efficiency of the platform data can be improved and the labor cost can be reduced.

[0022] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0024] Figure 1 A schematic diagram showing an application scenario according to an embodiment of the present disclosure.

[0025] Figure 2 A schematic diagram of an interface of a target platform according to an embodiment of the present disclosure is shown.

[0026] Figure 3A schematic diagram of an interface of a target platform according to an embodiment of the present disclosure is shown.

[0027] Figure 4 A schematic diagram of an interface of a target platform according to an embodiment of the present disclosure is shown.

[0028] Figure 5 A schematic diagram of an interface of a target platform according to an embodiment of the present disclosure is shown.

[0029] Figure 6 A schematic diagram of an interface of a target platform according to an embodiment of the present disclosure is shown.

[0030] Figure 7 A schematic diagram of an interface of a target platform according to an embodiment of the present disclosure is shown.

[0031] Figure 8 A schematic diagram of an interface of a target platform according to an embodiment of the present disclosure is shown.

[0032] Fig. 9 A flow chart of a method for intelligently editing platform data according to an embodiment of the present disclosure is shown.

[0033] Fig.10 A schematic diagram showing an intelligent editing process of platform data according to an embodiment of the present disclosure.

[0034] Fig.11 A block diagram of an intelligent editing device for platform data according to an embodiment of the present disclosure is shown.

[0035] Fig.12 A block diagram of an electronic device 1900 according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0036] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0037] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0038] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0039] In order to better understand the solutions of the embodiments of the present application, the relevant terms and concepts that may be involved in the embodiments of the present application are first introduced below.

[0040] (1) JSON data: JSON (JavaScript Object Notation) is a lightweight data exchange format.

[0041] (2) JSON Schema: used to describe the format and specifications of JSON data; JSON Schema is a powerful tool for describing and validating JSON data structures.

[0042] (3) GPT model: Generative pre-trained transformer model, which is a series of artificial intelligence language models. The GPT model involved in the embodiments of the present disclosure may be a GPT model service provided by a third party, or may be a self-developed GPT model. The embodiments of the present disclosure do not limit the type, structure, etc. of the GPT model.

[0043] (4) Natural language: usually refers to a language that evolves naturally with culture, such as Chinese, English, French, Spanish, Portuguese, Japanese, Korean, Italian, German, etc.

[0044] (5) Token: The GPT model series usually uses tokens to process text. Tokens are common character sequences in text. The model response time will increase with the number of returned tokens.

[0045] (6)JSON Patch: is a format for describing changes made to JSON data.

[0046] As shown above, using the GPT model to assist humans in realizing intelligent operations has become a development trend. The embodiments of the present disclosure mainly realize the use of the GPT model to assist the target platform in automatically and intelligently editing platform data. Compared with manually editing platform data, it can improve the editing efficiency of platform data and reduce manual operation costs.

[0047] Among them, the target platform can be a client platform, a web platform, etc., for example, it can be an operation platform, a management platform, a form-based middle and back-end, and a low-code platform, etc. The platform data can be understood as data that can be edited by users in the target platform, for example, the layout of page components, page component configuration, page general configuration, function controls, etc., wherein the page components can, for example, include at least picture components, video components, pit components, button components, text components, etc., the page component configuration can, for example, include the text color, text font, function buttons in the page components (such as "change" button, "more" button) and other configurations, the layout of the page components can, for example, include the number of columns, rows, and positions of the page components, etc., the function controls can, for example, include controls with certain functions such as viewing page operation logs, editing page themes, and previewing pages, the page general configuration can, for example, include the page name of the configured page, the business logic of the page, the function buttons in the page (such as a return button, a third-party platform jump button), etc., the embodiment of the present disclosure does not limit the type and quantity of platform data that can be edited by users in the target platform.

[0048] For example, Figure 1 An intelligent editing system 100 for platform data is shown. The intelligent editing system 100 can utilize the GPT model to assist the target platform in automatically and intelligently editing platform data. The intelligent editing system 100 can be integrated into the target platform, for example. The target platform integrated with the intelligent editing system 100 can be deployed on a terminal device (such as a personal computer) or a server (such as a computer device cluster in the cloud). Figure 2 A schematic diagram of an interface of a target platform integrated with the above-mentioned intelligent editing system 100 is shown. The platform interface of the target platform contains platform data that can be edited, that is, a tiled pit component, which includes 2×2 pits, each pit including a picture and text. The user can enter a natural language editing instruction "Change all text colors to gray" in the input box below the platform interface to instruct the target platform to change all texts in the current platform data to gray. After obtaining the natural language editing instruction, the target platform can send the natural language editing instruction and the current platform data to the intelligent editing system 100. The intelligent editing system 100 can generate a query instruction based on the natural language editing instruction and the current platform data, and call the GPT model based on the query instruction to convert the natural language editing instruction into an operation instruction executable by the platform and execute the above operation instruction on the target platform. The operation instruction executable by the platform is an operation instruction that conforms to the specified editing format of the platform data. For example, it can be converted into the following operation instruction:

[0049] [{

[0050] "op":"replace",

[0051] "path":" / titleColor",

[0052] "value":"grey"

[0053] }].

[0054] After executing the above operation instructions on the target platform, for example, the following can be obtained: Figure 3 A platform interface is shown. Figure 3 The text of the platform data has all turned gray, such as Figure 3 As shown, a card may pop up above the input box to display the natural language editing instructions that the user has entered, and may also display the processing result "Completed" of the intelligent editing system 100, indicating that the natural language editing instructions issued by the user have been completed.

[0055] It should be understood that the user can enter at least one natural language editing instruction in the input box in the platform interface according to actual needs. For example, if the user is Figure 3 Continue to input "Open Switch, change the number of display lines to 1" for the platform data shown, and you can get Figure 4 The platform data shown, wherein "Change" can be a function button; for example, the user can also Figure 3 The platform data shown can be obtained by inputting the natural language instruction of "view page operation log" Figure 5 The operation log list shown on the right side of the interface is a function control for viewing the page operation log. The operation log list can display information such as the operation content, operation time, and operator. The "Details" button can be used to view the details of modifying the page layout, and the "Restore" button can be used to restore the operation of deleting components; for example, users can also Figure 2 The platform data shown in the figure is input into "Add single image component and single video component", and the Figure 6 The platform data shown can also be obtained by entering "Move the single video component to the top" Figure 7 The platform data shown can also be obtained by entering "delete single image component" Figure 8 Platform data shown, etc.

[0056] It should be understood that the above Figures 1 to 8 The application scenarios shown are some exemplary embodiments provided by the embodiments of the present disclosure. Figures 2 to 8 The interface shown may be part or all of the interface in the target platform. The user may customize the type of target platform, the interface of the target platform, the type of platform data, the editing method of platform data, the input method of natural language editing instructions, etc. according to actual needs, and the embodiments of the present disclosure are not limited to this.

[0057] In the process of researchers trying to use the GPT model to assist the target platform to realize automatic and intelligent editing of platform data, they found some problems that need to be solved: First, how to find a general pattern to describe the business logic of the target platform to the GPT model, so that the GPT model can output the correct content according to the natural language editing instructions issued by the user, or how to abstract the business logic of the target platform into a form that the GPT model can understand, so that the GPT model can output the correct operation instructions after receiving the natural language instructions; Second, how to shorten the response time of the GPT model while ensuring that the GPT model can assist the target platform to accurately complete data editing, that is, to reduce the amount of token data output by the GPT model as much as possible, and avoid the GTP model from responding and timing out due to the large amount of output token data. Therefore, the researchers believe that it is necessary to design a GTP model that can understand the user's operation intentions, and to design a set of standard formats for data exchange between the target platform and the GPT model, so as to reduce the amount of data output by the GPT model while accurately conveying the user's operation intentions to the platform.

[0058] Based on this, the embodiments of the present disclosure provide an intelligent editing method for platform data. The intelligent editing method for platform data of the embodiments of the present disclosure can be applied to the target platform, and can realize the standardization of the communication data format between the GPT model and the target platform, so that the GPT model understands the business logic of the target platform, that is, the GPT model understands the structure and meaning of the platform data to be processed, that is, understands the user's operation intentions, and at the same time can reduce the response time of the GPT model, so that after the user issues a natural language editing instruction, the target platform can efficiently complete the automatic modification of the platform data.

[0059] The intelligent editing method of platform data of the embodiment of the present disclosure can be deployed on various terminal devices through software or hardware modification. The terminal device involved in the embodiment of the present disclosure may refer to a device with a wireless connection function. The function of wireless connection refers to connecting to other terminal devices through wireless connection methods such as wifi and Bluetooth. The terminal device involved in the embodiment of the present disclosure may also have the function of communicating through a wired connection. The terminal device involved in the embodiment of the present disclosure may be a touch screen, a non-touch screen, or a screenless terminal device. The touch screen can control the terminal device by clicking and sliding on the display screen with a finger or a stylus. The non-touch screen device can be connected to an input device such as a mouse, a keyboard, a touch panel, and the terminal device is controlled by the input device. For example, the device without a screen can be a Bluetooth speaker without a screen. For example, the terminal device of the present application can be a smart phone, a netbook, a tablet computer, a laptop computer, a wearable electronic device (such as a smart bracelet, a smart watch, etc.), a TV, a virtual reality device, a stereo, an electronic ink, and the like.

[0060] The intelligent editing method of platform data of the embodiment of the present disclosure can also be deployed on a server, which can be located in the cloud or locally, and can be a physical device or a virtual device, such as a virtual machine, a container, etc., with a wireless communication function, wherein the wireless communication function can be set in the chip (system) or other parts or components of the server. It can refer to a device with a wireless connection function, and the wireless connection function refers to the ability to connect to other servers or terminal devices through wireless connection methods such as Wi-Fi and Bluetooth. The server involved in the embodiment of the present disclosure may also have the function of communicating through a wired connection. For example, the server involved in the embodiment of the present disclosure can be located in the cloud, communicate with the terminal device, receive the natural language editing instructions sent by the terminal device, and use the intelligent editing method of platform data deployed on the server to complete the editing of the platform data based on the natural language editing instructions and return the editing results to the terminal device to display the editing results of the platform data to the user.

[0061] The following Fig. 9 and Fig.10 , the intelligent editing method of platform data provided by the embodiment of the present disclosure is introduced in detail.

[0062] Fig. 9 A flowchart of a method for intelligently editing platform data according to an embodiment of the present disclosure is shown. The method can be used in the intelligent editing system 100 of platform data, and the method can be executed by the terminal device or server, such as Fig. 9 As shown, the intelligent editing method includes:

[0063] Step S91, in response to receiving a natural language editing instruction for the current platform data of the target platform, generating a query instruction according to the natural language editing instruction and the platform data.

[0064] In actual applications, users can send natural language editing instructions to the target platform through text input or voice input. The natural language editing instructions can be understood as instructions for editing platform data described in natural language. Specifically, the natural language editing instructions can include objects to be edited in the platform data and the editing methods of the objects. The objects can include but are not limited to at least one of the following: layout of page components, page component configuration, page general configuration, and functional controls; the editing methods can include but are not limited to at least one of the following: add, delete, modify, move, and copy. For example, add a single image component; delete all components; modify the text color in the tiled pit component; move the first pit in the tiled pit component to the second; copy the first component in the page, and the new component name is "single image component_34ac", and insert it at the bottom of the page, etc.

[0065] Among them, the object to be edited can be understood as part or all of the plane data currently indicated by the natural language editing instruction. For example, the object to be edited in the natural language editing instruction "change all text color to orange" can be the text color, and the editing method can be to change it to orange.

[0066] It should be understood that since the platform data can be edited more than once, each time a new natural language editing instruction is received, a query instruction can be generated based on the currently received natural language editing instruction and the current platform data of the target platform, so that the GPT model can accurately output operation instructions based on the current platform data.

[0067] Optionally, based on the natural language editing instructions and the platform data, a query instruction is generated, for example, it may include: filling the natural language editing instructions and the platform data into a preset query template to obtain the query instruction. The query template may include instruction information for instructing the GPT model how to process the natural language editing instructions and the platform data, so as to instruct the GPT model to output an operation instruction for editing the platform data. It should be understood that those skilled in the art can customize the content, structure, etc. of the query template according to actual needs, and the embodiments of the present disclosure are not limited to this.

[0068] As described above, in the process of using the GPT model to assist the target platform in automatically and intelligently editing platform data, there is a problem of how to abstract the business logic of the target platform into a form that the GPT model can understand, so as to output the correct operation instructions after receiving the natural language instructions. Based on this, in a possible implementation method, the above-mentioned generation of query instructions based on the natural language editing instructions and platform data may include:

[0069] Convert the platform data into JSON data in JSON format and generate corresponding JSON description data, where the JSON description data is used to describe the format and specification of the JSON data;

[0070] Fill the natural language editing instruction, JSON data and JSON description data into the preset query template to obtain the query instruction.

[0071] Among them, by converting the platform data into JSON data and the corresponding JSON description data, it is equivalent to realizing the standardization of the communication data format between the GPT model and the target platform, so that the business logic of the target platform can be abstracted into a form that the GPT model can understand, and the GPT model can understand the structure and meaning of the platform data, so that the GPT model does not need to pay attention to the business logic of the platform itself, but only needs to deal with the editing of the JSON data. It should be understood that those skilled in the art can use data processing techniques known in the art to convert platform data into JSON data in JSON format and generate corresponding JSON description data, and this is not limited to the embodiments of the present disclosure. Among them, the JSON description data may include JSON Schema data.

[0072] For example, the JSON data is as follows:

[0073] {

[0074] 'width':200,

[0075] 'height':180,

[0076] }

[0077] And a JSON description data corresponding to the above JSON data:

[0078] {

[0079] 'type':'object',

[0080] 'title':'hlw-yk-single-picture',

[0081] 'description':'Single image component',

[0082] 'properties':{

[0083] 'width':{

[0084] 'type':'integer',

[0085] 'title':'Image width',

[0086] 'description':'Note: This must be the margin for a 750 width resolution'

[0087] },

[0088] 'height':{

[0089] 'type':'integer',

[0090] 'title':'Picture height',

[0091] 'description':'Note: This must be the margin for a 750 width resolution'

[0092] },

[0093] }

[0094] }

[0095] }

[0096] The above JSON data and JSON description data represent the JSON data and JSON description data of a single image component used in the platform page. This single image component has two configuration items, namely, image width and image width; the JSON data contains the specific values ​​of image width and image width "200" and "180", and the JSON description data contains the format and specification of the JSON data of the single image component, such as: 'type':'integer', 'title':'image height', 'description':'Note: must be the margin under 750 width resolution' and other information. It should be understood that the platform data currently available for editing on the target platform can be abstracted into JSON data and JSON description data in the above manner, so that the GPT model can understand the structure and meaning of the platform data to be processed.

[0097] As described above, those skilled in the art can customize the content, structure, etc. of the query template according to actual needs. For example, the query template may be preset with instruction information that instructs the GPT model to convert natural language editing instructions into a specified editing format that conforms to the platform data, so as to instruct the GPT model to process data according to the instruction information.

[0098] In one possible implementation, the specified editing format may include a JSON patch format, which is a format for describing changes made to JSON data, and the JSON patch format includes a JSON Patch format. Based on this, the above query instruction can be used to instruct the GPT model to convert the natural language editing instruction into an operation instruction that conforms to the JSON patch format, so that the GPT model does not need to output the modified full JSON data or partial JSON data, thereby shortening the response time of the GPT model and reducing the calling cost of the GPT model.

[0099] Exemplarily, the present disclosure provides a query template as shown below:

[0100] Please modify the JSON data according to the following process:

[0101] 1. Receive JSON data and JSON Schema data.

[0102] 2. Obtain natural language editing instructions, including the object to be edited and the editing method.

[0103] 3. Convert natural language editing instructions into JSON Patch format output.

[0104] 4. If the description is vague, please ask me again.

[0105] The following are the JSON data and JSON Schema data:

[0106] JSON data is ${{JSON data}}, and JSON Schema data is ${{JSON Schema data}}.

[0107] Modify JSON data according to ${{natural language editing instructions}}."

[0108] Among them, ${{}} is a placeholder character in the query template, which can be replaced with corresponding data according to different business scenarios. That is, the natural language editing instructions, JSON data and JSON description data can be filled into ${{JSON data}}, ${{JSON Schema data}} and ${{natural language editing instructions}} in the above query template respectively to obtain a complete query instruction.

[0109] The query instructions generated by the query template can instruct the GPT model to convert natural language editing instructions into operation instructions that conform to the JSON patch format without outputting other instructions, which can reduce the data volume of the operation instructions output by the GPT model, and help reduce the response time of the GPT model. It should be understood that the above query template is an exemplary implementation provided by the embodiment of the present disclosure, and those skilled in the art can design the specific content and specific format of the query template according to actual needs.

[0110] Optionally, in some possible implementations, if the amount of converted JSON data is small, after abstracting the platform data into JSON data in JSON format and generating corresponding JSON Schema data, the query instruction generated using the natural language editing instruction, JSON data, and JSON Schema data can also instruct the GPT model to directly output the modified full JSON data according to the query instruction; or the GPT model can also be instructed to output part of the JSON data modified by the instruction according to the query instruction. In these cases, the specified editing format that conforms to the platform data can also include the JSON format.

[0111] It should be understood that once the amount of the full JSON data is large, the number of tokens output by the GPT model will increase, resulting in an increase in the interface response time of the GPT model, or even a response timeout. Although only the natural language editing instruction is output to indicate that the amount of the modified JSON data is reduced relative to the amount of the full JSON data, when the natural language editing instruction is to perform an operation of adding or deleting elements on the array type JSON data, the modified part of the JSON data is the entire array, which may still cause the amount of data output by the GPT model to be too large, thereby causing the interface response time to be too long. In actual applications, users can design different query templates according to actual needs. The query instructions generated based on different query models can control the GPT model to output operation instructions that conform to the JSON patch format, or output the modified full JSON data, or output the modified part of the JSON data.

[0112] Step S92, calling the generative pre-trained transformer GPT model based on the query instruction to obtain the operation instruction output by the GPT model.

[0113] Among them, calling the GPT model based on the query instruction to obtain the operation instruction output by the GPT model can be understood as calling the interface provided by the GPT model service based on the query instruction, or it can be understood as inputting the query instruction into the GPT model, and the GPT model processes the query instruction and then outputs and returns the operation instruction.

[0114] Considering that in some cases, if the natural language editing instructions input by the user are not accurate enough, that is, the description of the natural language editing instructions is vague, this may make the GPT model unable to accurately know the object to be edited and / or the editing method of the object, or the natural language editing instructions issued by the user exceed the scope of the platform data available for editing in the target platform, etc. In these cases, the GPT model usually outputs user-oriented content including inquiries, prompts, guidance, etc., such as reconfirming the edited object and / or the editing method of the object to the user, guiding the user to enter the natural language editing instructions that meet the specifications, etc. For example, assuming that the natural language editing instruction input by the user is "change the color of the title to red", but there are main titles and subtitles in the platform data, at this time the GPT model does not know which type of title to modify specifically, it can return the query content "Please confirm whether to modify the main title or subtitle or all titles" to confirm the modified object to the user. In these cases, the content (operation instructions) output by the GPT model usually does not conform to the specified editing format of the platform data, that is, these contents (operation instructions) need to be displayed to the user to guide the user to issue instructions again.

[0115] Based on this, in a possible implementation, after calling the GPT model based on the query instruction and obtaining the operation instruction output by the GPT model, the method may also include: determining whether the operation instruction output by the GPT model conforms to the specified editing format of the platform data, and if the operation instruction output by the GPT model conforms to the specified editing format of the platform data, executing step S93, that is, executing the operation instruction to edit the platform data.

[0116] As described above, the specified editing format may include the JSON patch format. In one possible implementation, determining whether the operation instructions output by the GPT model conform to the specified editing format of the platform data may specifically include: detecting whether the operation instructions output by the GPT model conform to the JSON patch format; if the operation instructions output by the GPT model conform to the JSON patch format, determining that the operation instructions output by the GPT model conform to the specified editing format of the platform data; or, if the operation instructions output by the GPT model do not conform to the JSON patch format, the operation instructions output by the GPT model do not conform to the specified editing format of the platform data.

[0117] As shown above, the query instruction can also be used to instruct the GPT model to output the modified full JSON data or partial JSON data. The specified editing format can also include the JSON format. Based on this, judging whether the operation instructions output by the GPT model conform to the specified editing format of the platform data can also include: detecting whether the operation instructions output by the GPT model conform to the JSON format. If they conform to the JSON format, it is determined that the operation instructions conform to the specified editing format; if they do not conform to the JSON format, it is determined that the operation instructions do not conform to the specified editing format.

[0118] Step S93, when the operation instruction output by the GPT model conforms to the specified editing format of the platform data, execute the operation instruction to edit the platform data.

[0119] Among them, the operation instructions that comply with the specified editing format of the platform data can realize the editing of the platform data, so the platform data can be edited by executing the operation instructions.

[0120] For example, by Figure 2 The platform data shown executes the following operation instructions:

[0121] [{

[0122] "op":"replace",

[0123] "path":" / titleColor",

[0124] "value":"orange"

[0125] }],

[0126] You can Figure 2 Change the color of all titles in to orange;

[0127] For example, through Figure 2 The platform data shown executes the following operation instructions:

[0128] [{

[0129] "op":"move",

[0130] "from":" / list / 0",

[0131] "path":" / list / 1"

[0132] }],

[0133] You can Figure 2 Move from the first pit to the second pit.

[0134] According to an embodiment of the present disclosure, by calling the GPT model based on the natural language editing instructions issued by the user and the query instructions generated by the current platform data of the target platform, the GPT model converts the natural language editing instructions into operation instructions that conform to the specified editing format, and executes the operation instructions to edit the platform data. This enables the GPT model to assist the target platform in automatically and intelligently editing the platform data. Compared with manually editing the platform data, the editing efficiency of the platform data can be improved and the labor cost can be reduced.

[0135] As shown above, in actual situations, there may be situations where the operation instructions output by the GPT model do not conform to the specified editing format of the platform data. Such operation instructions that do not conform to the specified editing format usually need to be displayed to the user to guide the user to issue the instruction again. In a possible implementation, the method further includes:

[0136] When the operation instructions output by the GPT model do not conform to the specified editing format of the platform data, the operation instructions output by the GPT model are displayed, and the displayed operation instructions are used to guide the user to issue natural language auxiliary instructions, and the natural language auxiliary instructions are used to assist the GPT model to output operation instructions that conform to the specified editing format;

[0137] In response to receiving a natural language assisted instruction issued in response to the displayed operation instruction, calling the GPT model based on the natural language assisted instruction to obtain the operation instruction re-output by the GPT model;

[0138] When the operation instructions re-output by the GPT model conform to the specified editing format, the operation instructions re-output by the GPT model are executed to edit the platform data.

[0139] Among them, the method of obtaining natural language auxiliary instructions can be the same as the above-mentioned natural language editing instructions. The natural language auxiliary instructions can be understood as replies based on the displayed operation instructions, which can assist the GPT model to accurately know the objects and / or the editing methods of the objects that the user wants to edit. For example, if the GPT model outputs "Please confirm whether to modify the main title, subtitle or all titles", the user can enter "Modify the main title" in the input box of the platform interface again, then the "Modify the main title" is a natural language auxiliary instruction issued by the user. The natural language auxiliary instruction can assist the GPT model to output an operation instruction to modify the main title in the platform data to red, that is, to assist the GPT model to output an operation instruction that conforms to the specified editing format.

[0140] Among them, calling the GPT model based on the natural language auxiliary instruction means inputting the natural language auxiliary instruction into the GPT model, or calling the interface of the GPT model service based on the natural language auxiliary instruction, so as to obtain the operation instruction re-output by the GPT model. Then, it can be judged again whether the operation instruction re-output by the GPT model conforms to the specified editing format. If the operation instruction re-output by the GPT model conforms to the specified editing format, the operation instruction re-output by the GPT model is executed; if the operation instruction re-output by the GPT model still does not conform to the specified editing format, the operation instruction re-output by the GPT model can be displayed again until the GPT model outputs the operation instruction conforming to the specified editing format.

[0141] It should be understood that the above-mentioned judgment of whether the operation instructions output by the GPT model conform to the specified editing format of the platform data can be used to determine whether the operation instructions re-output by the GPT model conform to the specified editing format, which will not be elaborated here.

[0142] According to the embodiments of the present disclosure, the GPT model can be effectively assisted to output operation instructions that conform to the specified editing format, so as to accurately realize the intelligent editing of platform data.

[0143] Fig.10 A schematic diagram showing an intelligent editing process of platform data according to an embodiment of the present disclosure is shown, and the process can be applied to a target platform, such as Fig.10 As shown, the intelligent editing process includes:

[0144] The user inputs natural language editing instructions into the target platform;

[0145] Convert the current platform data of the target platform into JSON data and generate the corresponding JSON Schema data;

[0146] A preset query template is used to instruct the GPT model to output natural language editing instructions in JSON Patch format;

[0147] Fill the query template with JSON data, JSON Schema data, and natural language editing instructions to obtain a complete query instruction for the GPT model;

[0148] Call the GPT model based on the query instruction and obtain the operation instruction returned by the GPT model;

[0149] Determine whether the operation instructions returned by the GPT model conform to the JSON Patch format;

[0150] If the operation instruction conforms to the JSON Patch format, execute the operation instruction to modify the JSON data;

[0151] If the operation instruction does not conform to the JSON Patch format, display the operation instruction returned by the GPT model to guide the user to issue natural language assisted instructions;

[0152] The user inputs natural language-assisted instructions to the target platform;

[0153] Call the GPT model based on natural language auxiliary instructions to obtain the operation instructions returned by the GPT model again;

[0154] Determine whether the operation instruction returned by the GPT model conforms to the JSON Patch format;

[0155] If the operation instruction returned again conforms to the JSON Patch format, execute the operation instruction to modify the JSON data;

[0156] If the operation instruction returned again does not conform to the JSON Patch format, the operation instruction returned by the GPT model is displayed again until the GPT model returns an operation instruction that conforms to the JSON Patch format.

[0157] According to the embodiments of the present disclosure, it is possible to use the GPT model to assist the target platform in automatically and intelligently editing platform data. By converting the platform data into JSON data and JSON Schema data, the GPT model can understand the structure and meaning of the platform data, so that the GPT model does not need to pay attention to the business logic of the platform itself, but only needs to process the editing of the JSON data; by allowing the GPT model to convert natural language editing instructions into operation instructions that conform to the JSON Patch format, the response time of the GPT model can be shortened and the calling cost of the GPT model can be reduced.

[0158] Fig.11 A block diagram of an intelligent editing device for platform data according to an embodiment of the present disclosure is shown. Fig.11 As shown, the intelligent editing device comprises:

[0159] An instruction generation module 111 is used for generating a query instruction according to the natural language editing instruction and the platform data in response to receiving a natural language editing instruction for the current platform data of the target platform;

[0160] A model calling module 112, configured to call a generative pre-trained transformer GPT model based on the query instruction to obtain an operation instruction output by the GPT model;

[0161] The instruction execution module 113 is used to execute the operation instruction to edit the platform data when the operation instruction output by the GPT model conforms to the specified editing format of the platform data.

[0162] In a possible implementation, the query instruction is generated based on the natural language editing instruction and the platform data, including: converting the platform data into JSON data in JSON format and generating corresponding JSON description data, wherein the JSON description data is used to describe the format and specifications of the JSON data; filling the natural language editing instruction, the JSON data and the JSON description data into a preset query template to obtain a query instruction.

[0163] In one possible implementation, the query instruction is used to instruct the GPT model to convert natural language editing instructions into operation instructions that conform to the JSON patch format, wherein the specified editing format includes the JSON patch format, and the JSON patch format is a format for describing changes made to JSON data.

[0164] In a possible implementation, the JSON description data includes JSON Schema data, and the JSON patch format includes JSON Patch format.

[0165] In one possible implementation, after calling the generative pre-trained transformer GPT model based on the query instruction and obtaining the operation instructions output by the GPT model, the device also includes: a format detection module, used to detect whether the operation instructions output by the GPT model conform to the JSON patch format; when the operation instructions output by the GPT model conform to the JSON patch format, determining that the operation instructions output by the GPT model conform to the specified editing format of the platform data; or, when the operation instructions output by the GPT model do not conform to the JSON patch format, the operation instructions output by the GPT model do not conform to the specified editing format of the platform data.

[0166] In one possible implementation, the device also includes: a display module, which is used to display the operation instructions output by the GPT model when the operation instructions output by the GPT model do not conform to the specified editing format of the platform data, and the displayed operation instructions are used to guide the user to issue natural language auxiliary instructions, and the natural language auxiliary instructions are used to assist the GPT model to output operation instructions that conform to the specified editing format; the model calling module 112 is also used to respond to receiving natural language auxiliary instructions issued for the displayed operation instructions, call the GPT model based on the natural language auxiliary instructions, and obtain the operation instructions re-output by the GPT model; the instruction execution module 113 is also used to execute the operation instructions re-output by the GPT model when the operation instructions re-output by the GPT model conform to the specified editing format to edit the platform data.

[0167] In one possible implementation, the natural language editing instruction includes an object to be edited in the platform data and an editing method of the object, wherein the object includes at least one of the following: layout of page components, page component configuration, general page configuration, and functional controls; the editing method includes at least one of the following: adding, deleting, modifying, moving, and copying.

[0168] It should be understood that the functions or modules included in the device provided in the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation thereof can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0169] According to an embodiment of the present disclosure, a query instruction is generated based on the natural language editing instruction issued by the user and the current platform data of the target platform, and the GPT model is called based on the query instruction to convert the natural language editing instruction input by the user into an operation instruction that conforms to a specified editing format, that is, to convert it into an operation instruction that can edit the platform data, or to convert it into an operation instruction that can be executed by the target platform, and the operation instruction is executed to complete the editing of the platform data, thereby utilizing the GPT model to assist the target platform in automatically and intelligently editing the platform data. Compared with manually editing the platform data, the editing efficiency of the platform data can be improved and the labor cost can be reduced.

[0170] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0171] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0172] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0173] Fig.12 1 is a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server or a terminal device. Fig.12 , the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0174] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0175] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0176] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0177] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0178] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0179] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0180] Various aspects of the present disclosure are described herein 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 disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0181] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0182] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0183] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0184] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many edits and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for intelligently editing platform data, characterized in that: include: In response to receiving a natural language editing instruction for current platform data of a target platform, generating a query instruction according to the natural language editing instruction and the platform data; Calling a generative pre-trained transformer GPT model based on the query instruction to obtain an operation instruction output by the GPT model; When the operation instruction output by the GPT model conforms to the specified editing format of the platform data, executing the operation instruction to edit the platform data; The step of generating a query instruction according to the natural language editing instruction and the platform data includes: Convert the platform data into JSON data in JSON format and generate corresponding JSON description data, wherein the JSON description data is used to describe the format and specification of the JSON data; Filling the natural language editing instruction, the JSON data, and the JSON description data into a preset query template to obtain a query instruction; The query instruction is used to instruct the GPT model to convert natural language editing instructions into operation instructions that conform to the JSON patch format, wherein the specified editing format includes the JSON patch format, and the JSON patch format is a format for describing changes made to JSON data.

2. The method according to claim 1, characterized in that The JSON description data includes JSON Schema data, and the JSON patch format includes JSON Patch format.

3. The method according to claim 1, characterized in that After calling the generative pre-trained transformer GPT model based on the query instruction and obtaining the operation instruction output by the GPT model, the method further includes: Detecting whether the operation instructions output by the GPT model conform to the JSON patch format; In the case where the operation instruction output by the GPT model conforms to the JSON patch format, determining that the operation instruction output by the GPT model conforms to the specified editing format of the platform data; or, In the case where the operation instruction output by the GPT model does not conform to the JSON patch format, the operation instruction output by the GPT model does not conform to the specified editing format of the platform data.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: In the case where the operation instruction output by the GPT model does not conform to the specified editing format of the platform data, displaying the operation instruction output by the GPT model, wherein the displayed operation instruction is used to guide the user to issue a natural language auxiliary instruction, wherein the natural language auxiliary instruction is used to assist the GPT model to output the operation instruction conforming to the specified editing format; In response to receiving a natural language assisted instruction issued in response to the displayed operation instruction, calling the GPT model based on the natural language assisted instruction to obtain the operation instruction re-output by the GPT model; In a case where the operation instructions re-output by the GPT model conform to the specified editing format, the operation instructions re-output by the GPT model are executed to edit the platform data.

5. The method according to claim 1, characterized in that The natural language editing instructions include the objects to be edited in the platform data and the editing methods of the objects, wherein the objects include at least one of the following: layout of page components, page component configuration, general page configuration, and functional controls; the editing methods include at least one of the following: adding, deleting, modifying, moving, and copying.

6. An intelligent editing device for platform data, characterized in that: include: An instruction generation module, configured to generate a query instruction according to the natural language editing instruction and the platform data in response to receiving a natural language editing instruction for the current platform data of the target platform; A model calling module, used to call a generative pre-trained transformer GPT model based on the query instruction to obtain an operation instruction output by the GPT model; An instruction execution module, configured to execute the operation instruction output by the GPT model to edit the platform data when the operation instruction conforms to a specified editing format of the platform data; The step of generating a query instruction according to the natural language editing instruction and the platform data includes: Convert the platform data into JSON data in JSON format and generate corresponding JSON description data, wherein the JSON description data is used to describe the format and specification of the JSON data; Filling the natural language editing instruction, the JSON data, and the JSON description data into a preset query template to obtain a query instruction; The query instruction is used to instruct the GPT model to convert natural language editing instructions into operation instructions that conform to the JSON patch format, wherein the specified editing format includes the JSON patch format, and the JSON patch format is a format for describing changes made to JSON data.

7. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the method described in any one of claims 1 to 5 when executing the instructions stored in the memory.

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

Images