Critical game event extraction method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention provides a crisis game event extraction method and device, a storage medium and electronic equipment, and relates to the technical field of event extraction, and the method comprises the steps: carrying out the time marking of a long text through Heidel Time; a non-intrusive text prompt technology is adopted to generate a time prompt on the long text subjected to time marking, and a long text with a non-intrusive time prompt is obtained; and taking the long text with the non-intrusive time prompt as the input of the large language model, and extracting the crisis game event. According to the technical scheme, the long text time association extraction tool Heidel Time is combined with the large language model, non-intrusive prompt enhancement is performed on the long association timestamp in the long text, the recognition accuracy of the model on the event time field is remarkably improved, and the event recognition rate is generally improved by nearly 20%.

Description

Technical Field

[0001] The present application relates to the technical field of event extraction, and in particular to a method, device, storage medium and electronic device for extracting crisis game events. Background Art

[0002] Event extraction aims to extract events from pure natural language text. Existing event extraction technologies have many difficulties and limitations in extracting events with timestamps in long texts, including the following:

[0003] First, there is a lack of training data. Event extraction from long texts requires a large amount of annotated data with timestamps for model training. However, existing event extraction models are usually trained for short texts. The lack of long text datasets and datasets for specific data extraction structures leads to poor performance of the model when processing long texts. Events in long texts are usually more complex, involving multiple temporal relationships and contextual information, and existing datasets and training methods are difficult to cover all possible situations. Even if there are datasets for long texts, these datasets are usually not strictly time-annotated, making it difficult for the model to learn and promote effectively.

[0004] Second, training requires a lot of resources, and it is difficult to transfer learning between different extraction structures / templates. Model training for long text event extraction requires a lot of computing resources and time. This includes not only pre-training of the basic model, but also fine-tuning for specific tasks. When dealing with long texts such as books that have not been processed in any way, the amount of data and computing resources required are even larger. In addition, different event extraction tasks and templates may be significantly different, making it difficult to directly transfer the parameters of the model trained on one task to another. The SFT (Structured from Text) paradigm adopted by most current methods performs well in terms of parameter classification metrics, but performs poorly in cross-task migration and adaptation to new extraction structures. This makes it very difficult for the model to transfer learning between different tasks, and it cannot effectively respond to the diverse needs of long text event extraction.

[0005] Third, there is a lack of a unified and effective prompt framework for zero-shot event extraction that calls the API of large language models. In practical applications, using zero-shot learning or few-shot learning methods to directly call the API of mature large models (such as ChatGPT) is a low-cost option. However, this approach faces the problem of lack of a unified and effective prompt framework. Although existing large language models perform well in some tasks, how to design effective prompts to guide the model to correctly understand and extract timestamp information in long texts remains a huge challenge. Especially for long texts such as unprocessed books, it is more difficult to design reasonable prompts to help the model identify and standardize event times. There is currently no unified and effective prompt framework that can effectively solve this problem, resulting in unstable performance of the model in different contexts and tasks.

[0006] Fourth, the context length of existing language models is not sufficient to support the judgment of relative temporal relationships in long contexts. Existing large language models face limitations in context length when processing long texts. Most models have limited input and output lengths and cannot directly process all contextual information in long texts. This means that in long texts, the model cannot read all content at once, resulting in incomplete information in the event extraction process. If the long text is input in segments, the model lacks global context information when processing each segment, especially the judgment of relative temporal relationships. Segmented input will lead to the loss of contextual temporal relationships, making it impossible for the model to accurately capture the temporal associations between events, thus affecting the accuracy and completeness of event extraction.

[0007] In addition, even if the limitation of context length can be partially overcome, event extraction from long texts still involves complex time standardization processing. The temporal relationship between different events may depend on multiple contextual information in the full text, rather than the information of a single paragraph. Therefore, existing methods perform poorly in temporal inference and standardization processing in long texts, making it difficult to meet the requirements of accurate event time extraction. Summary of the invention

[0008] The embodiments of the present application provide a crisis game event extraction method, device, storage medium and electronic device to solve the problems existing in the prior art.

[0009] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0010] According to a first aspect of an embodiment of the present application, a method for extracting crisis game events is provided, comprising:

[0011] Use HeidelTime to time-mark long texts;

[0012] A non-intrusive text prompt technology is used to generate time prompts on the time-annotated long text, thereby obtaining a long text with non-intrusive time prompts.

[0013] Long texts with non-intrusive time cues are used as input to a large language model to extract crisis game events.

[0014] In some embodiments of the present application, based on the above solution, the use of HeidelTime to time-mark a long text includes:

[0015] Use HeidelTime to standardize time information in long texts based on pattern matching and rules;

[0016] Use TIMEX3 tags to mark the standardized time information.

[0017] In some embodiments of the present application, based on the above-mentioned solution, the non-intrusive text prompt technology is used to generate a time prompt on the time-annotated long text to obtain a long text with a non-intrusive time prompt, including:

[0018] Parse the time-annotated long text and obtain all TIMEX3 tag information in the long text;

[0019] Get the time value in each TIMEX3 tag, use regular expressions to match the time value to the specific year, month, and day, and convert it to the first Python date object;

[0020] Use Python date parser to parse the inner text in TIMEX3 tag and convert the inner text into a second Python date object;

[0021] Compares the first Python date object to the second Python date object and appends the normalized date value to the inner text if the two dates do not match.

[0022] In some embodiments of the present application, based on the above solution, before taking the long text with non-intrusive time prompts as the input of the large language model, it also includes:

[0023] Segment long texts with non-intrusive time cues and define event roles.

[0024] In some embodiments of the present application, based on the above solution, the long text with non-intrusive time prompts is used as the input of the large language model to extract crisis game events, including:

[0025] The segmented long text with non-intrusive time prompts is used as input, and crisis game events are extracted by combining event roles and non-intrusive time prompts.

[0026] According to a second aspect of an embodiment of the present application, a crisis game event extraction device is provided, comprising:

[0027] Time marking unit, used to mark long text with time using HeidelTime;

[0028] A generating unit, used for generating a time prompt on the time-annotated long text by using a non-intrusive text prompt technology, so as to obtain a long text with a non-intrusive time prompt;

[0029] The extraction unit is used to take the long text with non-intrusive time prompts as the input of the large language model to extract crisis game events.

[0030] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the method according to the first aspect.

[0031] According to a fourth aspect of the embodiments of the present application, there is provided an electronic device, including: a memory and a processor;

[0032] The memory is used to store computer instructions;

[0033] The processor is used to call the computer instructions stored in the memory so that the electronic device executes the method as described in the first aspect.

[0034] The technical solution of this application combines the long text time association extraction tool HeidelTime with a large language model to perform non-intrusive prompt enhancement on long associated timestamps in long texts, significantly improving the recognition accuracy of the model on event time fields and generally increasing the event recognition rate by nearly 20%.

[0035] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0037] Figure 1 A schematic diagram of a process of extracting a crisis game event according to an embodiment of the present application is shown;

[0038] Figure 2 A block diagram of a crisis game event extraction device according to an embodiment of the present application is shown;

[0039] Figure 3 A block diagram of an electronic device according to an embodiment of the present application is shown;

[0040] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0041] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0042] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0043] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0044] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0045] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the objects used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those shown or described.

[0046] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Some embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0048] See also Figure 1 , shows a flow chart of a crisis game event extraction method according to an embodiment of the present application.

[0049] like Figure 1 As shown, a method for extracting crisis game events is shown, including steps S100 to S300.

[0050] Step S100: Use HeidelTime to time-mark the long text.

[0051] It should be noted that HeidelTime is a multilingual, domain-sensitive time tagging tool developed by the Database Systems Research Group at Heidelberg University. It is specifically used to extract time expressions from documents and standardize them into a machine-readable format. HeidelTime can recognize various time expressions, including specific dates, time periods, relative time expressions, and fuzzy time expressions. It uses a rule-based approach to extract and parse time information using predefined patterns and vocabularies.

[0052] Since HeidelTime completes the recognition of time expressions based on rules and has no context length limit, we can first use HeidelTime to preprocess the entire document, standardize the time expression of the entire document, and then input the preprocessed text paragraphs into the large language model for event extraction. This provides a clear and consistent time expression for the large language model, thereby greatly improving the performance of the model in the task of behavioral event extraction.

[0053] In some feasible embodiments, based on the above solution, the use of HeidelTime to time-mark a long text includes:

[0054] Use HeidelTime to standardize time information in long texts based on pattern matching and rules;

[0055] Use TIMEX3 tags to mark the standardized time information.

[0056] It should be noted that HeidelTime is a machine learning model based on pattern matching and rule systems, which uses scalable rules to identify and parse common time expressions in various languages ​​and fields. It supports both relative time expression matching rules, such as for matching and parsing relative time expressions such as "3 days later", and absolute time expression matching rules, such as for matching absolute time expressions such as "May 20, 2023".

[0057] HeidelTime can handle both absolute time (such as "January 1, 2023") and relative time (such as "three days ago", "next week"). For absolute time, it can be standardized directly. For relative time, HeidelTime will find the optimal time reference point (Anchor) for standardization. For example, if the text mentions "three days ago" and the time reference point mentioned in the previous text is January 4, 2023, then "three days ago" will be standardized to January 1, 2023.

[0058] It should be noted that TIMEX3 is a time annotation language that is widely used to annotate and standardize time information. The TIMEX3 format contains a wealth of time expression information, including specific dates, times, time periods, and relative times. The main elements of TIMEX3 annotation are as follows:

[0059] DATE: indicates a specific date, such as "2023-07-18".

[0060] TIME: Indicates specific time, such as "14:30:00".

[0061] DURATION: Indicates the time period, such as "P2D" means two days.

[0062] SET: Indicates periodic time expression, such as "EVERY Monday".

[0063] ANCHOR: Indicates a relative time anchor point, such as "before" or "after".

[0064] The TIMEX3 format standardizes time information by adding specific annotation tags to the text. For example, if today is July 18, 2023, the sentence "The meeting will be held tomorrow" can be annotated as "The meeting will be held on<timex3 type="DATE"value="2023-07-19"> It will be held tomorrow".

[0065] Continue to refer Figure 1 , step S200, using non-intrusive text prompt technology to generate time prompts on the long text after time annotation, to obtain a long text with non-intrusive time prompts.

[0066] It should be noted that in this step, time information is prompted in long texts through a non-intrusive method. This processing can not only maintain the integrity of the original text, but also provide more context clues to enhance the accuracy and reliability of subsequent event recognition.

[0067] In some feasible embodiments, based on the above solution, the non-intrusive text prompt technology is used to generate a time prompt on the time-annotated long text to obtain a long text with a non-intrusive time prompt, including:

[0068] Parse the time-annotated long text and obtain all TIMEX3 tag information in the long text;

[0069] Get the time value in each TIMEX3 tag, use regular expressions to match the time value to the specific year, month, and day, and convert it to the first Python date object;

[0070] Use Python date parser to parse the inner text in TIMEX3 tag and convert the inner text into a second Python date object;

[0071] Compares the first Python date object to the second Python date object and appends the normalized date value to the inner text if the two dates do not match.

[0072] It is understandable that this step can provide more time information prompts without changing the original text content.

[0073] Continue to refer Figure 1 ,Step S300, taking the long text with non-intrusive time prompt as the input of the large language model to extract crisis game events.

[0074] In some feasible embodiments, based on the above solution, before the long text with non-intrusive time prompts is used as the input of the large language model, the following is further included:

[0075] Segment long texts with non-intrusive time cues and define event roles.

[0076] It should be noted that the specific process of text segmentation for long text with non-intrusive time prompts is as follows:

[0077] Divide long text into logical paragraphs or segments of a certain length with non-intrusive time annotations.

[0078] This process ensures that each segment contains sufficient context information to facilitate subsequent event extraction.

[0079] It should be noted that the reason for defining event roles is to enhance the accuracy of event extraction and context understanding, so a clear role will be defined in this method and specific tasks and prompt words will be provided for it.

[0080] Example, Event Role Definition: As a distinguished historian of international relations at Harvard University, you have been commissioned to analyze documents related to this case. Please proceed methodically in the specified format, ensuring that all relevant events are fully extracted. Strive to complete as many fields as possible.

[0081] In some feasible embodiments, based on the above solution, the long text with non-intrusive time prompts is used as the input of the large language model to extract crisis game events, including:

[0082] The segmented long text with non-intrusive time prompts is used as input, and crisis game events are extracted by combining event roles and non-intrusive time prompts.

[0083] The following describes an embodiment of the device of the present application, which can be used to execute a method for extracting crisis game events in the above embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the above method of the present application.

[0084] Reference Figure 2 As shown, a crisis game event extraction device according to an embodiment of the present application includes:

[0085] A time marking unit 201 is used to mark the long text with time using HeidelTime;

[0086] A generating unit 202, configured to generate a time prompt on the time-annotated long text by using a non-intrusive text prompt technology, so as to obtain a long text with a non-intrusive time prompt;

[0087] The extraction unit 203 is used to use the long text with non-intrusive time prompts as input to the large language model to extract crisis game events.

[0088] like Figure 3 As shown, an embodiment of the present application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of the above-mentioned crisis game event extraction method are implemented.

[0089] Since the electronic device introduced in this embodiment is a device used to implement a crisis game event extraction device in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation method of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0090] During the specific implementation process, when the computer program 311 is executed by a processor, any implementation method in the embodiments corresponding to the first aspect can be implemented.

[0091] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0092] It should be noted that Figure 4 The computer system 400 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0093] like Figure 4 As shown, the computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. In the RAM 403, various programs and data required for system operation are also stored. The CPU 401, ROM 402 and RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0094] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0095] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 409, and / or installed from a removable medium 411. When the computer program is executed by a central processing unit (CPU) 401, various functions defined in the system of the present application are executed.

[0096] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0097] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0098] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0099] As another aspect, the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes a crisis game event extraction method described in the above embodiment.

[0100] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements a crisis game event extraction method described in the above embodiment.

[0101] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0102] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0103] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary techniques in the art that are not disclosed in the present application. It should be understood that the present application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for extracting crisis game events, characterized in that: include: Use HeidelTime to time-mark long texts; A non-intrusive text prompt technology is used to generate time prompts on the time-annotated long text, thereby obtaining a long text with non-intrusive time prompts. Long texts with non-intrusive time cues are used as input to a large language model to extract crisis game events.

2. The method according to claim 1, characterized in that: The use of HeidelTime to time-mark long texts includes: Use HeidelTime to standardize time information in long texts based on pattern matching and rules; Use TIMEX3 tags to mark the standardized time information.

3. The method according to claim 2, characterized in that The non-intrusive text prompt technology is used to generate a time prompt on the time-annotated long text to obtain a long text with a non-intrusive time prompt, including: Parse the time-annotated long text and obtain all TIMEX3 tag information in the long text; Get the time value in each TIMEX3 tag, use regular expressions to match the time value to the specific year, month, and day, and convert it to the first Python date object; Use Python date parser to parse the inner text in TIMEX3 tag and convert the inner text into a second Python date object; Compares the first Python date object to the second Python date object and appends the normalized date value to the inner text if the two dates do not match.

4. The method according to claim 1, characterized in that Before feeding the long text with non-intrusive temporal cues as input to a large language model, also include: Segment long texts with non-intrusive time cues and define event roles.

5. The method according to claim 1, characterized in that The long text with non-intrusive time prompts is used as the input of the large language model to extract crisis game events, including: The segmented long text with non-intrusive time prompts is used as input, and crisis game events are extracted by combining event roles and non-intrusive time prompts.

6. A crisis game event extraction device, characterized in that: include: Time marking unit, used to mark long text with time using HeidelTime; A generating unit, used for generating a time prompt on the time-annotated long text by using a non-intrusive text prompt technology, so as to obtain a long text with a non-intrusive time prompt; The extraction unit is used to take the long text with non-intrusive time prompts as the input of the large language model to extract crisis game events.

7. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is enabled to execute the method according to any one of claims 1 to 5.

8. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer instructions; The processor is used to call the computer instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-5.

Images