RPA and ai combined model fusion result acquisition method and device, and electronic equipment

Abstract

The present disclosure provides a model fusion result obtaining method and device combining RPA and AI, electronic equipment and storage medium, and relates to the field of artificial intelligence. The scheme is as follows: performed by an RPA system, the RPA system obtains to-be-processed information, and inputs the to-be-processed information into n models respectively, to obtain n processing results of the to-be-processed information based on natural language processing (NLP), wherein n is an integer greater than 1; the RPA system obtains the distance between any processing result and the remaining n-1 processing results; the RPA system obtains a target processing result of the to-be-processed information according to the distance, and displays the target processing result. The present disclosure uses RPA technology and AI technology, no longer depends on the probability of model output result, improves the utilization rate of model output result and ensures the accuracy of model fusion result, and at the same time, improves the robustness of the model fusion result.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence, and in particular to a method, apparatus, and electronic device for obtaining model fusion results combining RPA and AI. Background Technology

[0002] Robotic Process Automation (RPA) uses specific "robot software" to simulate human operations on a computer and automatically execute process tasks according to rules.

[0003] Artificial intelligence (AI) is a technical science that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence.

[0004] In related technologies, a common approach in model fusion methods is to calculate the arithmetic mean of all answers and use it as the fusion result. This method relies on the probability of the model output, limiting its utilization and resulting in low accuracy. Therefore, how to reduce reliance on the probability of the model output while improving its utilization and ensuring the accuracy of the fusion result is an urgent issue that needs to be addressed. Summary of the Invention

[0005] This disclosure provides a method, apparatus, and electronic device for obtaining model fusion results combining RPA and AI.

[0006] According to one aspect of this disclosure, a method for obtaining model fusion results combining RPA and AI is provided, including:

[0007] The RPA system acquires the information to be processed and inputs it into n models respectively to obtain n processing results of the information to be processed based on natural language processing (NLP), where n is an integer greater than 1.

[0008] The RPA system obtains the distance between any processing result and the remaining n-1 processing results;

[0009] The RPA system obtains the target processing results of the information to be processed based on the distance and then displays them.

[0010] This disclosure utilizes RPA and AI technologies to automatically perform model fusion and display the fusion results, thereby improving the utilization rate of the model output and enhancing the robustness of the fusion results.

[0011] According to another aspect of this disclosure, an apparatus for obtaining model fusion results combining RPA and AI is provided, comprising:

[0012] The first acquisition module is used to acquire the information to be processed and input the information to be processed into n models respectively, so as to obtain n processing results of the information to be processed based on natural language processing (NLP), where n is an integer greater than 1;

[0013] The second acquisition module is used to acquire the distance between any processing result and the remaining n-1 processing results;

[0014] The display module is used to obtain the target processing result of the information to be processed based on the distance, and then display it.

[0015] According to another aspect of this disclosure, an electronic device is provided, including a memory and a processor; wherein the processor runs a program corresponding to the executable program code by reading executable program code stored in the memory, so as to implement the RPA combined with AI model fusion result acquisition method of the first aspect embodiment of this disclosure.

[0016] According to another aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the RPA-AI combined model fusion result acquisition method of the first aspect of this disclosure.

[0017] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the RPA-AI combined model fusion result acquisition method of the first aspect of this disclosure.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0019] Figure 1 This is a flowchart of a method for obtaining model fusion results of RPA combined with AI according to an embodiment of the present disclosure;

[0020] Figure 2 This is a flowchart of a method for obtaining model fusion results of RPA combined with AI according to an embodiment of the present disclosure;

[0021] Figure 3 This is a flowchart of a method for obtaining model fusion results of RPA combined with AI according to an embodiment of the present disclosure;

[0022] Figure 4 This is a flowchart of a method for obtaining model fusion results of RPA combined with AI according to an embodiment of the present disclosure;

[0023] Figure 5This is a structural diagram of an RPA-AI combined model fusion result acquisition device according to an embodiment of the present disclosure;

[0024] Figure 6 This is a block diagram of an electronic device used to implement the RPA combined with AI model fusion result acquisition method of the embodiments of this disclosure. Detailed Implementation

[0025] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0026] The following describes, with reference to the accompanying drawings, a method, apparatus, and electronic device for obtaining model fusion results combining RPA and AI of this disclosure.

[0027] Figure 1 This is a flowchart of a method for obtaining model fusion results of RPA combined with AI according to an embodiment of this disclosure, such as... Figure 1 As shown, the method includes the following steps:

[0028] S101, the RPA system obtains the information to be processed and inputs the information to be processed into n models respectively, so as to obtain n processing results of the information to be processed based on natural language processing (NLP), where n is an integer greater than 1.

[0029] RPA (Repetitive Processing) is a relatively new and popular software technology that simulates human operation on a PC. It is increasingly being applied to enterprise production and office work. The core of RPA is to use automation and intelligent technologies to "replace" humans in repetitive, low-value, and fixed process-oriented operations that do not require human decision-making, thereby effectively improving work efficiency and reducing errors.

[0030] Natural Language Processing (NLP) is an important field within computer science and AI. It studies the theories and methods for enabling effective communication between humans and computers using natural language. NLP is a science that integrates linguistics, computer science, and mathematics. Therefore, research in this field involves natural language—the language people use in daily life—and thus it has a close relationship with linguistics, but also important differences.

[0031] The information to be processed can be any information represented as a string. For example, the information to be processed can be a problem that the user is trying to solve, such as "What is the title of this report?" or "Which team produced this report?"

[0032] Here, "model" refers to any model that participates in the model fusion process.

[0033] Model fusion refers to the process of combining the answers from multiple individual models and then outputting a better fused answer.

[0034] For example, the information to be processed is input into n models, and then the processing results corresponding to the information are obtained. For model 1, the processing result is a1, and for model n, the processing result is a... n In this case, the model fusion result is obtained by processing the results a1~a n The result after processing.

[0035] S102, the RPA system obtains the distance between any processing result and the remaining n-1 processing results.

[0036] Distance can be obtained in various ways, and this disclosure does not limit the methods used.

[0037] As one possible implementation, the edit distance or word shift distance can be obtained and used as the distance between any processing result and the remaining n-1 processing results.

[0038] Edit distance, also known as Levenshtein distance, refers to the minimum number of edits required to transform one string into another; word mover's distance (WMD) is a measure of text similarity.

[0039] As another possible implementation, the distance between any processing result and the remaining n-1 processing results can be obtained by encoding and acquiring similarity. In this embodiment of the disclosure, after obtaining n processing results of the information to be processed, all processing results can be encoded to obtain n processing result vectors.

[0040] Optionally, the RPA system inputs all processing results into a trained encoding model, such as a Transformer-based Bidirectional Encoder Representations from Transformers (BERT) or Bidirectional Long Short-Term Memory (Bi-LSTM) network model, and uses the n encoded results of preset length as the processing result vector.

[0041] Furthermore, the RPA system can calculate the distance between any processing result and the remaining n-1 processing results based on n processing result vectors and in conjunction with the distance calculation formula.

[0042] S103, the RPA system obtains the target processing result of the information to be processed based on the distance and displays it.

[0043] In this embodiment of the disclosure, after determining the distance between any processing result obtained by the RPA system and the remaining n-1 processing results, the target processing result of the information to be processed can be selected from all the processing results based on the distance and then displayed.

[0044] In this embodiment, the RPA system acquires the information to be processed and inputs it into n models to obtain n processing results. Next, the RPA system obtains the distance between any processing result and the remaining n-1 processing results. Finally, based on the distances, the RPA system obtains the target processing result for the information to be processed and displays it. This embodiment utilizes RPA and AI technologies, eliminating reliance on the probability of model output results, improving the utilization rate of model output results, ensuring the accuracy of model fusion results, and simultaneously enhancing the robustness of model fusion results.

[0045] The following sections explain the specific process by which the RPA system obtains the distance between any processing result and the other n-1 processing results, specifically by using edit distance or word shift distance as the distance between any processing result and the other n-1 processing results, and by using encoding and similarity to obtain the distance between any processing result and the other n-1 processing results.

[0046] Regarding obtaining the edit distance or word shift distance as the distance between any processing result and the remaining n-1 processing results, optionally, the RPA system can directly obtain the edit distance or word shift distance between any processing result and the remaining n-1 processing results, and use the obtained edit distance or word shift distance as the distance between any processing result and the remaining n-1 processing results. Regarding obtaining the distance between any processing result and the remaining n-1 processing results through encoding and similarity acquisition, optionally, the following distance calculation formula can be used to obtain the distance between any processing result and the remaining n-1 processing results:

[0047]

[0048] Where E is the sentence vector encoding function and d is the distance.

[0049] It should be noted that, in this disclosure, before obtaining the distance between any processing result and the remaining n-1 processing results, the RPA system can encode all processing results to obtain n processing result vectors.

[0050] It should be noted that this disclosure does not limit the specific method for encoding all processing results to obtain n processing result vectors, and can be set according to the actual situation. Optionally, the RPA system can input all processing results into the trained encoding model and use the n encoded results of preset length as processing result vectors.

[0051] Furthermore, after obtaining any processing result vector, the distance between any processing result and the remaining n-1 processing results can be obtained based on the similarity.

[0052] As one possible implementation, based on the above embodiments, further combining Figure 2 This paper explains the specific process by which the RPA system obtains the distance between any processing result and the other n-1 processing results through encoding and similarity acquisition. The process includes the following steps:

[0053] S201, the RPA system obtains the similarity information between any processing result and the remaining n-1 processing results based on the processing result vector.

[0054] The similarity information refers to the degree of similarity between individuals (processing result vectors).

[0055] S202, the RPA system obtains the distance based on similarity information.

[0056] Specifically, the lower the similarity between the processed result vectors, the greater the distance between them; conversely, the greater the similarity between the processed result vectors, the smaller the distance between them.

[0057] For example, for the processed result vectors X1, X2, and X3, the similarity information between X1 and X2 and between X1 and X3 is 95% and 15%, respectively. In this case, the distance between X1 and X2 is smaller than the distance between X1 and X3.

[0058] Figure 3 This is a flowchart of a method for obtaining model fusion results combining RPA and AI according to an embodiment of this disclosure. Based on the above embodiment, it further combines... Figure 3 The process by which an RPA system obtains the target processing result of the information to be processed based on distance is explained, including the following steps:

[0059] S301, the RPA system obtains the sum of distances between any processing result and the remaining n-1 processing results based on the distance.

[0060] For example, for three processing results a1, a2, and a3, the distances between a1 and a2 and a3 are d1 and d2, respectively; the distances between a2 and a1 and a3 are d3 and d4, respectively; and the distances between a3 and a1 and a2 are d5 and d6, respectively. In this case, the sum of the distances between a1 and a2 and a3, D1, is d1 + d2; the sum of the distances between a2 and a1 and a3, D2, is d3 + d4; and the sum of the distances between a3 and a1 and a2, D3, is d5 + d6.

[0061] S302, the RPA system determines the processing result with the smallest sum of distances to the remaining n-1 processing results based on the sum of distances, and takes the processing result with the smallest sum of distances as the target processing result.

[0062] In this embodiment of the disclosure, after the RPA system obtains the sum of distances, it can determine the processing result with the smallest sum of distances among the remaining n-1 processing results, and take the processing result with the smallest sum of distances as the target processing result.

[0063] For example, for three processing results a1, a2, and a3, the sum of the distances between a1 and a2 and a3 is D1, the sum of the distances between a2 and a1 and a3 is D2, and the sum of the distances between a3 and a1 and a2 is D3, and D3 < D1 < D2. In this case, the sum of the distances between a3 and a1 and a2 is the smallest, so processing result a3 can be taken as the target processing result.

[0064] In this embodiment of the disclosure, the processing result with the smallest sum of distances can be used as the target processing result through the RPA system. By obtaining the processing result with the highest similarity, the goal of obtaining a more accurate target processing result is achieved, which further improves the reliability and accuracy of the model fusion result.

[0065] Figure 4 This is a flowchart of a method for obtaining model fusion results of RPA combined with AI according to an embodiment of this disclosure, such as... Figure 4 As shown, based on the RPA-AI combined model fusion result acquisition method provided in this disclosure, the process of acquiring the RPA-AI combined model fusion result in a practical application scenario includes the following steps:

[0066] S401, the RPA system obtains the information to be processed and inputs the information to be processed into n models respectively to obtain n processing results of the information to be processed, where n is an integer greater than 1.

[0067] In this embodiment of the disclosure, after obtaining the processing result, optionally, step S405 can be executed to obtain the distance by obtaining the edit distance or word shift distance; optionally, steps S402 to S404 can be executed to obtain the distance by obtaining the encoding and similarity.

[0068] S402, the RPA system inputs all processing results into the trained encoding model and uses the n encoded results of the output, each with a preset length, as the processing result vector.

[0069] S403, the RPA system obtains similarity information between any processing result and the remaining n-1 processing results based on the processing result vector.

[0070] S404, the RPA system obtains the distance based on similarity information.

[0071] S405, the RPA system obtains the edit distance or word shift distance between any processing result and the remaining n-1 processing results based on the processing result vector.

[0072] It should be noted that after completing step S405 or step S404, step S406 is executed to obtain the sum of distances.

[0073] S406, the RPA system obtains the sum of distances between any processing result and the remaining n-1 processing results based on the distance.

[0074] S407, the RPA system determines the processing result with the smallest sum of distances to the remaining n-1 processing results based on the sum of distances, and takes the processing result with the smallest sum of distances as the target processing result.

[0075] S408, the RPA system obtains the target processing result of the information to be processed and displays it.

[0076] The following section uses distance as the edit distance as an example to explain the method for obtaining model fusion results of RPA combined with AI proposed in this disclosure.

[0077] Optionally, the RPA system obtains the information to be processed and inputs it into M models to obtain M processing results for the information to be processed. In this case, for model i, the corresponding processing result can be labeled as a_i.

[0078] Furthermore, the sum of edit distances s_i between the processing results a_i output by each model and the processing results output by other models can be obtained using the following formula:

[0079]

[0080] Among them, ai a j Let M be the processing result of model i and j, and M be the number of models used in the model fusion process.

[0081] Furthermore, the processing result with the smallest sum of distances to the remaining n-1 processing results can be obtained and displayed as the target processing result.

[0082] It should be noted that the method for obtaining model fusion results by combining RPA and AI proposed in this disclosure is highly effective in various application scenarios where the information to be processed is represented in string form.

[0083] For reading comprehension applications, six models were pre-trained. Each model can extract a paragraph (span) from the document based on the question content (information to be processed) as the answer to the question (processing result).

[0084] In this case, for example, if the information to be processed is: "What is the title of this report?", and the six processing results are: Morning Meeting Minutes, Morning Meeting Minutes, Morning Meeting Minutes, Tianfeng Securities, Morning Meeting Minutes, Morning Meeting Minutes, and the processing result with the smallest sum of distances to the other five processing results is: "Morning Meeting Minutes", then the model fusion result (target processing result) is: "Morning Meeting Minutes".

[0085] For example, if the information to be processed is: "Which team produced this report?", and the six processing results are: Dai Shuang, Dai Shuang, Product Center Research Team, Financial Engineering Research Team, Tang, Financial Engineering Research Team, and the processing result with the smallest sum of distances to the other five processing results is: "Financial Engineering Research Team", then the model fusion result (target processing result) is: "Financial Engineering Research Team".

[0086] For example, if the information to be processed is: "What is the product's slogan?", and the six processing results are: LED lighting color is clear at a glance, LED lighting color is clear at a glance, color is clear at a glance, LED lighting color is clear at a glance, humanized design is more than just a little bit comfortable, humanized design is more than just a little bit comfortable, beautiful and corrosion resistant LED lighting color is clear at a glance, and the processing result with the smallest sum of distances to the other five processing results is: "LED lighting color is clear at a glance", then the model fusion result (target processing result) is: "LED lighting color is clear at a glance".

[0087] It should be noted that model fusion methods in related technologies often calculate the average of all model outputs and then use this average as the fusion result. This not only relies on the probability of each model output as the basis for obtaining the fusion result but also limits the utilization of the model outputs. Therefore, this disclosure introduces the concept of the median to fully utilize the processing result of each model output, improving the utilization rate of the model outputs and thus enhancing the reliability and accuracy of the model fusion result acquisition process. Furthermore, by using an RPA system to select the processing result with the smallest sum of distances as the target processing result, the goal of obtaining a more accurate target processing result is achieved by obtaining the processing result with the highest similarity, further improving the reliability and accuracy of the model fusion result.

[0088] Figure 5 This is a structural diagram of an apparatus for obtaining model fusion results of RPA combined with AI according to an embodiment of the present disclosure, as shown below. Figure 5 As shown, the RPA-AI combined model fusion result acquisition device 500 includes:

[0089] The first acquisition module 510 is used to acquire information to be processed and input the information to be processed into n models respectively, so as to obtain n processing results of the information to be processed based on natural language processing (NLP), where n is an integer greater than 1;

[0090] The second acquisition module 520 is used to acquire the distance between any of the processing results and the remaining n-1 processing results;

[0091] The display module 530 is used to obtain the target processing result of the information to be processed based on the distance, and to display it.

[0092] The embodiments disclosed herein utilize RPA and AI technologies to make the model output results no longer dependent on the probability of the model output results, thereby improving the utilization rate of the model output results and ensuring the accuracy of the model fusion results. At the same time, the robustness of the model fusion results is improved.

[0093] It should be noted that the explanation of the above-described method for obtaining the model fusion result of RPA combined with AI also applies to the device for obtaining the model fusion result of RPA combined with AI in this embodiment, and will not be repeated here.

[0094] Furthermore, in one possible implementation of this embodiment, the display module 630 is further configured to: obtain the sum of distances between any processing result and the remaining n-1 processing results based on the distance; determine the processing result with the smallest sum of distances to the remaining n-1 processing results based on the sum of distances, and use the processing result with the smallest sum of distances as the target processing result.

[0095] Furthermore, in one possible implementation of this embodiment, the second acquisition module 620 is further configured to: encode all processing results to obtain n processing result vectors.

[0096] Furthermore, in one possible implementation of this embodiment, the second acquisition module 620 is further configured to: input all processing results into the trained encoding model, and use the n output encoding results, each with a preset length, as the processing result vector.

[0097] Furthermore, in one possible implementation of this disclosure embodiment, the second acquisition module 620 is further configured to: acquire similarity information between any processing result and the remaining n-1 processing results based on the processing result vector; and acquire distance based on the similarity information.

[0098] Furthermore, in one possible implementation of this disclosure, the second acquisition module 620 is further configured to: the RPA system acquire the edit distance or word shift distance between any processing result and the remaining n-1 processing results based on the processing results.

[0099] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0100] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0101] like Figure 6 As shown, it includes a memory 61, a processor 62, and a computer program stored on the memory 61 and capable of running on the processor 62. When the processor 62 executes the program, it implements the aforementioned method for obtaining model fusion results by combining RPA and AI.

[0102] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0103] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0104] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for obtaining model fusion results combining RPA and AI, characterized in that, The model fusion is a process of combining the answers from multiple individual models and then outputting a fused answer. The model fusion result is executed by an RPA system, and the method includes: The RPA system automatically acquires the information to be processed and inputs the information to be processed into n models respectively, so as to obtain n processing results of the information to be processed based on natural language processing (NLP), wherein the information to be processed is the problem that the user is trying to solve, and n is an integer greater than 1; The RPA system automatically obtains the distance between any one of the processing results and the remaining n-1 processing results; The RPA system automatically obtains the sum of the distances between any processing result and the remaining n-1 processing results based on the distances, and takes the processing result with the smallest sum of distances between it and the remaining n-1 processing results as the target processing result of the information to be processed, and displays it. The RPA system automatically obtains the distance between any one of the processing results and the remaining n-1 processing results, including: The RPA system automatically obtains the edit distance or word shift distance between any processing result and the remaining n-1 processing results based on the processing results; The edit distance or the word shift distance is used as the distance between any processing result and the remaining n-1 processing results.

2. The method according to claim 1, characterized in that, Before the RPA system automatically obtains the distance between any of the processing results and the remaining n-1 processing results, it also includes: The RPA system encodes all the processing results to obtain n processing result vectors.

3. The method according to claim 2, characterized in that, The RPA system encodes all the processing results to obtain n processing result vectors, including: The RPA system inputs all the processing results into the trained encoding model and uses the n encoded results of the output, each of which has a preset length, as the processing result vector.

4. The method according to claim 2 or 3, characterized in that, The RPA system automatically obtains the distance between any one of the processing results and the remaining n-1 processing results, and also includes: The RPA system obtains similarity information between any one of the processing results and the remaining n-1 processing results based on the processing result vector; The RPA system obtains the distance based on the similarity information.

5. A device for obtaining model fusion results combining RPA and AI, characterized in that, The model fusion is a process of fusing the answers from multiple individual models and then outputting a fused answer. The model fusion result is executed by an RPA system, and the device includes: The first acquisition module is used to automatically acquire information to be processed and input the information to be processed into n models respectively, so as to obtain n processing results of the information to be processed based on natural language processing (NLP), wherein the information to be processed is the problem that the user inputs and attempts to solve, and n is an integer greater than 1; The second acquisition module is used to automatically acquire the distance between any of the processing results and the remaining n-1 processing results; The display module is used to automatically obtain the sum of the distances between any processing result and the remaining n-1 processing results based on the distance, and to display the processing result that corresponds to the smallest sum of distances between the processing result and the remaining n-1 processing results as the target processing result of the information to be processed. The RPA system obtains the distance between any one of the processing results and the remaining n-1 processing results, including: The RPA system automatically obtains the edit distance or word shift distance between any processing result and the remaining n-1 processing results based on the processing results; The edit distance or the word shift distance is used as the distance between any processing result and the remaining n-1 processing results.

6. The apparatus according to claim 5, characterized in that, The second acquisition module is further configured to: All the processing results are encoded to obtain n processing result vectors.

7. The apparatus according to claim 6, characterized in that, The second acquisition module is further configured to: All the processing results are input into the trained encoding model, and the n output encoding results, each with a preset length, are used as the processing result vector.

8. The apparatus according to claim 6 or 7, characterized in that, The second acquisition module is further configured to: Based on the processing result vector, obtain the similarity information between any one of the processing results and the remaining n-1 processing results; The distance is obtained based on the similarity information.

9. An electronic device, characterized in that, Including memory and processor; The processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the method as described in any one of claims 1-4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-4.

11. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-4.

Images