Call forwarding method, model training method, storage medium and electronic equipment

Abstract

The invention discloses a call forwarding method, a model training method, a storage medium and electronic equipment. The method relates to the field of artificial intelligence, and comprises the following steps: in response to a received voice stream of a user incoming call, converting the voice stream to obtain text data; the text data is input into an intention recognition model, the intention recognition model is used for recognizing the intention of the user, intention information of multiple hierarchies is obtained, and the intention information of different hierarchies has different detailed degrees for intention description of the user; determining a service demand category of the user based on the intention information of the multiple levels; the call is forwarded to a server side corresponding to the service demand category, and a customer service staff corresponding to the server side is used for solving the problem of the user on the service demand category. According to the invention, the problem of low call forwarding efficiency in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and communication technology, and more specifically, to a call transfer method, a model training method, a storage medium, and an electronic device. Background Art

[0002] At present, various customer service hotlines provide 7*24 hours service to provide customers with all-round services. However, the traditional customer service center transfer method relies on users to press buttons or wait for manual transfer by human customer service. This process is time-consuming and cannot accurately express the user's intention, thus affecting customer experience and call efficiency, increasing time and labor costs, and thus resulting in low call transfer efficiency in related technologies.

[0003] With regard to the problem of low telephone transfer efficiency in related technologies, no effective solution has been proposed yet. Summary of the invention

[0004] The main purpose of this application is to provide a call transfer method, a model training method, a storage medium and an electronic device to solve the problem of low call transfer efficiency in related technologies.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for transferring a call is provided. The method comprises: in response to receiving a voice stream of an incoming call from a user, converting the voice stream to obtain text data; inputting the text data into an intention recognition model, using the intention recognition model to recognize the user's intention, and obtaining multiple levels of intention information, wherein different levels of intention information describe the user's intention in different degrees of detail; determining the user's service demand category based on the multiple levels of intention information; transferring the call to a service end corresponding to the service demand category, wherein the customer service personnel corresponding to the service end are used to solve the user's problems in the service demand category.

[0006] Furthermore, the multiple levels of intent information include at least one parent intent and at least one child intent, and determining the user's service demand category based on the multiple levels of intent information includes: classifying at least one parent intent to obtain a first service demand category; classifying at least one child intent to obtain a second service demand category, wherein the level of detail of at least one child intent is greater than the level of detail of at least one parent intent; and determining the service demand category based on the first service demand category and the second service demand category.

[0007] Further, determining the service demand category based on the first service demand category and the second service demand category includes: in response to the first service demand category and the second service demand category being the same, determining the second service demand category as the service demand category; in response to the first service demand category and the second service demand category being different, determining the first service demand category as the service demand category.

[0008] Further, after responding that the first service demand category is the same as the second service demand category, the method also includes: in response to the second service demand category containing multiple subcategories, determining a third service demand category among the multiple subcategories based on a preset priority, and determining the third service demand category as the service demand category.

[0009] Furthermore, the method further includes: in response to the second service requirement category including multiple subcategories, outputting the multiple subcategories; in response to receiving a voice confirmation instruction of a target subcategory among the multiple subcategories, determining the target subcategory as the service requirement category.

[0010] Further, transferring the call to the server corresponding to the service demand category includes: determining the server corresponding to the service demand category based on a preset corresponding relationship, wherein the preset corresponding relationship is used to represent the corresponding relationship between different service demand categories and different servers.

[0011] Furthermore, the method also includes: obtaining sample text data of sample users and multiple levels of sample intent information corresponding to the sample text data; inputting the sample text data and the multiple levels of sample intent information into an initial intent recognition model, using the initial intent recognition model to recognize the intent of the sample user to obtain multiple levels of predicted intent information; updating the model parameters of the initial intent recognition model based on the multiple levels of sample intent information and the multiple levels of predicted intent information to obtain an intent recognition model.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a model training method is provided, including: obtaining sample text data of a sample user and multiple levels of sample intent information corresponding to the sample text data; inputting the sample text data and the multiple levels of sample intent information into an initial intent recognition model, using the initial intent recognition model to recognize the intention of the sample user to obtain multiple levels of predicted intent information; training the initial intent recognition model based on the multiple levels of sample intent information and the multiple levels of predicted intent information to obtain an intent recognition model.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a telephone switching device is provided. The device includes: a conversion module, which is used to convert the voice stream in response to receiving the voice stream of the user's incoming call to obtain text data; a recognition module, which is used to input the text data into the intention recognition model, use the intention recognition model to recognize the user's intention, and obtain multiple levels of intention information, wherein different levels of intention information describe the user's intention in different degrees of detail; a determination module, which is used to determine the user's service demand category based on multiple levels of intention information; a switching module, which is used to switch the call to the service end corresponding to the service demand category, wherein the customer service personnel corresponding to the service end are used to solve the user's problems in the service demand category.

[0014] In order to achieve the above purpose, according to another aspect of the present application, a computer-readable storage medium is provided, the computer-readable storage medium includes a stored executable program, wherein when the executable program runs, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned call transfer method.

[0015] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the above-mentioned call transfer method is executed when the program is running.

[0016] In order to achieve the above object, according to another aspect of the present application, a computer program product is provided, including a computer program, and the computer program implements the above call forwarding method when executed by a processor.

[0017] In the embodiment of the present application, first, when receiving the voice stream of the user's incoming call, the voice stream is converted into text data; secondly, the text data is input into the intent recognition model, and the user's intent in the text data is recognized by the intent recognition model to obtain multiple levels of intent information; then the user's service demand category is determined according to the multiple levels of intent information; finally, the call is transferred to the corresponding service end according to the user's service demand category. It is easy to notice that the present application recognizes the text information containing the user's intent by constructing an intent recognition model to obtain different levels of intent information, so that the service demand category to which the user's intent belongs can be accurately determined according to the intent information with different levels of detail, and finally the call is transferred based on the service demand category, achieving the purpose of automatically transferring the call to the most appropriate server, thereby improving the transfer efficiency and accuracy, significantly shortening the user's waiting time, reducing the service delay caused by the transfer error, improving customer satisfaction and overall service efficiency, reducing time cost and labor cost, and thus solving the technical problem of low transfer efficiency in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 A hardware structure block diagram of a computer terminal for implementing a telephone transfer method is shown;

[0020] Figure 2 is a flow chart of a call transfer method according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a process of constructing a vector using an intent recognition model according to an embodiment of the present application;

[0022] Figure 4 is a flow chart of a model training method according to an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of a telephone switching device according to an embodiment of the present application;

[0024] Figure 6 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] 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 data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following explanations:

[0028] Automatic speech recognition technology: Automatic speech recognition technology is an intelligent technology that converts human speech into readable text.

[0029] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0030] Example 1

[0031] According to an embodiment of the present application, an embodiment of a call transfer method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal for implementing a telephone transfer method is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0033] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the telephone transfer method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned telephone transfer method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0035] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0036] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0037] Under the above operating environment, this application provides Figure 2 The call forwarding method shown. Figure 2 It is a flow chart of a call forwarding method according to an embodiment of the present application.

[0038] Step S202: in response to receiving a voice stream of an incoming call from a user, convert the voice stream to obtain text data.

[0039] The above-mentioned voice stream may refer to a continuous audio signal generated when a user calls into the system by phone. The types of voice streams may include but are not limited to customer voice streams, customer service voice streams, automatic voice broadcast streams, etc. The specific voice stream type needs to be determined based on the source and content of the voice stream, which is not limited here. The voice stream contains the user's voice information and the intentions or needs conveyed, and can be used to reflect customer needs and problems.

[0040] The above conversion may refer to converting a voice signal into corresponding text information, that is, converting a voice stream into text data. The conversion method may include but is not limited to automatic speech recognition technology, etc. The conversion can facilitate the subsequent storage, processing and analysis of the text data.

[0041] The above-mentioned text data may refer to text information converted from voice information in the voice stream. The text data may be used for data input in subsequent processing. Through the text data system, the user's specific needs may be understood, and then operations such as seat transfer and information retrieval may be performed.

[0042] In an optional embodiment, after receiving the voice stream of the user's incoming call, the automatic speech recognition technology is used to convert the voice information in the voice stream into text data, which is convenient for subsequent recognition of the text data. The conversion of the voice stream in the above process connects the user's voice input with the system's text understanding and response, and is a key link in achieving efficient and intelligent customer interaction.

[0043] In an optional embodiment, 5000-10000 valid calls, i.e., voice streams, are selected, wherein the number of voice streams is only an example, and the specific number of voice streams can be determined according to actual conditions and is not limited here. Valid means that the voice stream does not contain meaningless words such as "Hey", "Hi, hello", etc., and the voice stream should contain specific intentions, such as {Content: 'I want to check my account information'}, {Content: 'I plan to apply for ETC today, but where is the nearest outlet'}, etc., and the above valid voice streams are converted into text data through automatic speech recognition technology.

[0044] Step S204, inputting the text data into the intention recognition model, using the intention recognition model to recognize the user's intention, and obtaining multiple levels of intention information, wherein different levels of intention information describe the user's intention in different degrees of detail.

[0045] The above-mentioned intent recognition model may refer to a machine learning or deep learning model used to identify and understand a user's specific intentions or needs from the user's natural language text. The specific intent recognition model needs to be determined based on actual needs and is not limited here. The intent recognition model can be used to convert the vague and complex text information expressed by the user into a clear intent category, thereby guiding the subsequent service process of the call center, such as quickly transferring to the appropriate customer service agent.

[0046] The above-mentioned multiple levels of intent information may refer to intent descriptions of different degrees of abstraction obtained by multi-level classification of user text data. In the present application, multiple levels may include but are not limited to coarse-grained (parent), fine-grained (child), etc. The specific multiple levels can be further divided according to actual conditions, which is not limited here. The intent information of multiple levels may include but is not limited to parent intent, child intent, global intent, etc. The specific intent information of different levels needs to be determined according to actual conditions, which is not limited here. The intent information of multiple levels can be used to provide a more comprehensive understanding of user needs. The parent intent can be used to quickly locate service areas, and the child intent can be used to accurately match specific services. This hierarchical structure helps to improve service efficiency and quality.

[0047] In an optional embodiment, when a customer calls in and expresses a need, the system first converts the customer's voice stream into text data through automatic speech recognition technology; then, these text data are input into the intention recognition model to perform multi-level recognition of the customer's intention, thereby obtaining multiple levels of intention information including parent intention and child intention. This multi-level intention recognition strategy can not only quickly locate the area of ​​customer needs, but also accurately understand the customer's specific service needs, thereby greatly improving the efficiency and accuracy of the service.

[0048] In an optional embodiment, the text data and business rules are combined to construct an intent label set LabelSetsAll, and then according to business attributes and rules, the intent label set is divided into more specific label sets, namely the parent intent label set LabelSetsParent, and a correspondence is established between the constructed intent label set LabelSetsAll and the parent intent label set LabelSetsParent.

[0049] Next, the text data is annotated according to the above label combinations. First, all text data are annotated sentence by sentence according to the parent intent label set LabelSetsParent; then, all texts are annotated sentence by sentence according to the intent label set LabelSetsAll; finally, all text data are annotated sentence by sentence according to the global intent label set GlobalSets{'parent category-child category'}, and a total of 3 sets of annotated data are established, which are used together as further model data.

[0050] In an optional embodiment, Figure 3 is a schematic diagram of a process of constructing a vector using an intent recognition model according to an embodiment of the present application, such as Figure 3 As shown, first, the text data is input into the intent recognition model including multiple conversion layers; word embedding vectors, paragraph embedding vectors, and position embedding vectors are obtained through multiple conversion layers; finally, the word embedding vectors, paragraph embedding vectors, and position embedding vectors are combined to obtain a comprehensive vector.

[0051] In the above process, the input text data is first divided into a series of vocabulary units Token, and then each unit is mapped to a vector. This process is called word embedding Token Embedding, and the word embedding vector is obtained. At the same time, when processing input text containing multiple sentences or paragraphs, the BERT model will use paragraph embedding Segment Embedding to distinguish the different components of the text, thereby obtaining a paragraph embedding vector. In addition, in the BERT model, even if the input sentence is divided into Tokens, the model needs to understand the position relationship of these Tokens in the sentence, so Position Embedding is used to obtain the position embedding vector, and the above vectors are combined to obtain the required comprehensive vector.

[0052] Step S206, determining the user's service demand category based on multiple levels of intention information.

[0053] The above-mentioned service demand categories may refer to the results of classifying user needs according to different levels and specific business scenarios after multi-level intent identification. The service demand categories may include but are not limited to the first service demand category, the second service demand category, and the third service demand category. The specific service demand category can be determined based on the service type and business scope of the service center, and is not limited here. By determining the service demand category, it will not only help reduce customer waiting time and improve service efficiency, but also improve the accuracy of problem solving and customer satisfaction.

[0054] In an optional embodiment, through multi-level classification, the telephone service center can establish a comprehensive and detailed service demand catalog, so that no matter how specific or complex the user's needs are, the system can quickly and accurately classify them through the intent recognition model, that is, find the user's service demand category, and transfer them to the most appropriate seat, thereby significantly improving service quality and efficiency.

[0055] Step S208: transfer the call to the server corresponding to the service demand category, wherein the customer service personnel corresponding to the server are used to solve the user's problem in the service demand category.

[0056] The above-mentioned server may refer to a customer service staff or agent group in a telephone service center who is specifically responsible for handling different types of service demands. The types of server may include but are not limited to parent server, child server, integrated server, etc. The specific server type may be determined according to the different levels of service demand categories and is not limited here. The server may be used to ensure that user problems are solved in a timely, professional and efficient manner, thereby reducing customer waiting time, improving customer satisfaction, and optimizing the work efficiency of customer service staff.

[0057] In an optional embodiment, the call is transferred to the corresponding service end according to the service demand category to complete the call transfer. The above-mentioned hierarchical division of the service end ensures that the call center can flexibly and efficiently respond to various user needs. From the most general service to the most specific service scenario, there are corresponding customer service personnel or seat groups ready to provide services, thereby reducing user waiting time and improving the operating efficiency and service quality of the call service center.

[0058] In the embodiment of the present application, first, when receiving the voice stream of the user's incoming call, the voice stream is converted into text data; secondly, the text data is input into the intent recognition model, and the user's intent in the text data is recognized by the intent recognition model to obtain multiple levels of intent information; then the user's service demand category is determined according to the multiple levels of intent information; finally, the call is transferred to the corresponding service end according to the user's service demand category. It is easy to notice that the present application recognizes the text information containing the user's intent by constructing an intent recognition model to obtain different levels of intent information, so that the service demand category to which the user's intent belongs can be accurately determined according to the intent information with different levels of detail, and finally the call is transferred based on the service demand category, achieving the purpose of automatically transferring the call to the most appropriate server, thereby improving the transfer efficiency and accuracy, significantly shortening the user's waiting time, reducing the service delay caused by the transfer error, improving customer satisfaction and overall service efficiency, reducing time cost and labor cost, and thus solving the technical problem of low transfer efficiency in the related technology.

[0059] Optionally, in the call transfer method provided in an embodiment of the present application, multiple levels of intent information include at least one parent intent and at least one child intent, and determining the user's service demand category based on the multiple levels of intent information includes: classifying at least one parent intent to obtain a first service demand category; classifying at least one child intent to obtain a second service demand category, wherein the level of detail of at least one child intent is greater than the level of detail of at least one parent intent; and determining the service demand category based on the first service demand category and the second service demand category.

[0060] The above-mentioned parent intent may refer to a broader, higher-level abstract description of user needs identified in the intent recognition model. The parent intent may include but is not limited to inquiries, transfers, investment and financial management, etc. The specific parent intent needs to be determined based on the service scope and actual conditions. No limitation is made here. The parent intent can be used to quickly locate the approximate scope of user needs, provide preliminary direction guidance for subsequent child intent identification, speed up service response, etc.

[0061] The above-mentioned sub-intentions may refer to the subdivisions under the parent-level intentions, which are more specific and detailed descriptions of service requirements, and go deep into specific operations or inquiries that users may have. Sub-intentions may include but are not limited to checking balances, reporting lost credit cards, and corporate transfers. Specific sub-intentions need to be determined based on the service scope and actual conditions, and are not limited here. Sub-intentions can be used to accurately understand the specific needs of users, ensure that calls are transferred to the most appropriate seats, and improve the accuracy and efficiency of problem solving.

[0062] The above-mentioned first service demand category may refer to a service demand category determined based on the parent intent classification. The first service demand category represents a broad field of user needs. The types of the first service demand category may include but are not limited to user needs such as inquiry and transfer. The specific first service demand category needs to be determined based on the parent intent and service scope, and is not limited here. The first service demand category can be used to provide the system with preliminary user service demand positioning to facilitate rapid response and preliminary resource allocation.

[0063] The above-mentioned second service demand category may refer to a service demand category determined based on the sub-level intent classification. The second service demand category provides detailed types of user needs. The types of the second service demand category may include but are not limited to balance inquiry, public transfer, etc. The specific second service demand category needs to be determined based on the sub-level intent and service scope. No limitation is made here. The second service demand category can be used to further refine the user's specific needs and ensure that the call is transferred to the agent who can solve the problem most effectively and directly.

[0064] In an optional embodiment, the first service demand category is first obtained based on the parent intent identification, and then the second service demand category is obtained based on the child intent identification. Then, by combining the information of these two categories, the specific service demand category is finally determined, such as "transfer-public transfer". This process not only covers a wide range of user needs, but also goes deep into specific service types, ensuring that the call center can provide fast and accurate service responses, improving overall service efficiency and customer experience.

[0065] In an optional embodiment, in order to ensure that the parent recognition result corresponds to the child recognition result, a hierarchy-based penalty term pu is introduced to constrain the model prediction, thereby reducing the error propagation of the hierarchical recognition results. The calculation formula is as follows:

[0066] pu=λmax{0,loss i -loss0} 2 , (i=1,2)loss i (i≠0);

[0067] In the formula, pu represents the penalty term, loss i (i≠0) and loss0 represent the loss functions of the child node and the parent node respectively. max represents the maximum value. λ is an adjustable parameter used to control the influence of the penalty term pu. Through continuous iteration, the penalty term pu is minimized to achieve the combination of local step-by-step recognition and global recognition capabilities.

[0068] Optionally, in the call forwarding method provided in an embodiment of the present application, the service demand category is determined based on the first service demand category and the second service demand category, including: in response to the first service demand category and the second service demand category being the same, determining the second service demand category as the service demand category; in response to the first service demand category and the second service demand category being different, determining the first service demand category as the service demand category.

[0069] In an optional embodiment, when the first service demand category and the second service demand category are the same, it means that the user's needs have been accurately described by the child intent recognition, and no further parent classification confirmation is required. At this time, the system directly determines the second service demand category as the service demand category, quickly and accurately transfers the call, avoids unnecessary hierarchical judgments, significantly shortens the call processing time, and improves the customer experience. On the contrary, if the first service demand category is different from the second service demand category, it usually means that the child intent recognition fails to clearly capture the details of the user's needs, or there are recognition errors. At this time, the system will adopt a more robust strategy, that is, based on the parent intent classification results, the first service demand category is determined as the service demand category. This method ensures that even in the case of deviations in child identification, the call can be transferred to the seat that handles the corresponding broad field needs, avoiding service delays or incorrect transfers due to intent recognition errors, and ensuring service continuity and timely resolution of customer problems.

[0070] Optionally, in the call forwarding method provided in an embodiment of the present application, after responding that the first service demand category is the same as the second service demand category, the method also includes: in response to the second service demand category containing multiple subcategories, determining a third service demand category among the multiple subcategories based on a preset priority, and determining the third service demand category as the service demand category.

[0071] The above-mentioned preset priority may refer to a pre-set sorting mechanism in order to quickly determine the service demand with the highest priority among multiple subcategories. The preset priority may include but is not limited to setting emergency service requests such as loss report and fault report as the highest priority, and setting consulting services such as account inquiries as a lower priority. The specific preset priority can be determined based on the business characteristics of the call service center and customer demand analysis, and is not limited here. The preset priority can be used to make quick decisions when there are multiple possible service needs, ensuring that the call is transferred to the seat that can handle more urgent and more important service needs, thereby improving the overall service efficiency and the speed of resolving customer problems.

[0072] The above-mentioned third service demand category may refer to a specific category selected from these subcategories according to preset priority when the second service demand category contains multiple subcategories. The third service demand category may include but is not limited to balance inquiry, public transfer, etc. The specific third service demand category needs to be determined based on the second service demand category and the preset priority. No limitation is made here. The third service demand category can be used to refine service requirements and ensure the accuracy of the call transfer process.

[0073] In an optional embodiment, when the first service demand category is the same as the second service demand category, and there are multiple subcategories in the second service demand category, the system will select the third service demand category with the highest priority from these subcategories according to the preset priority sorting mechanism. This process ensures that even if there are multiple possible service demands, the call can be quickly transferred to the seat that can best respond to the user's needs, ensuring the timeliness and pertinence of the service.

[0074] Optionally, the call forwarding method provided in the embodiment of the present application also includes: in response to the second service requirement category containing multiple subcategories, outputting multiple subcategories; in response to receiving a voice confirmation instruction of a target subcategory among the multiple subcategories, determining that the target subcategory is the service requirement category.

[0075] The above-mentioned multiple subcategories may mean that in the second service demand category, there may be multiple specific service demand sub-classifications. The multiple subcategories may include but are not limited to balance inquiry, transaction detail inquiry, account opening bank inquiry, etc. The specific subcategories need to be determined based on the second service demand category and business scenario, and are not limited here. The second service demand category can be used to provide a more fine-grained list of service demand options, so that users can express their needs more accurately and avoid transfer errors caused by inaccurate or vague demand descriptions.

[0076] The above-mentioned target subcategory may refer to a specific subcategory that is finally determined to require service among multiple subcategories through further confirmation by the user. The target subcategory may be used to indicate the specific category of service requirements after confirmation by the user, which directly determines to which agent or service end the call will be transferred.

[0077] The above-mentioned voice confirmation instruction may refer to an instruction for the user to confirm his or her specific service needs through voice. The voice confirmation instruction may include but is not limited to directly speaking the target subcategory name, keywords related to the target subcategory, or voice instructions for selecting options according to system prompts, etc. The specific voice confirmation instruction needs to be determined based on the system design and voice recognition technology, and is not limited here. The voice confirmation instruction can be used as an interactive medium between the user and the system, allowing the user to confirm their exact needs through natural language voice in multiple subcategories, thereby ensuring accurate identification and satisfaction of service needs.

[0078] In an optional embodiment, when the user's intention is to identify the second service demand category, and the category contains multiple subcategories, the system will announce these subcategory options to the user and request the user to clarify the target subcategory through voice confirmation instructions; once the user's confirmation instruction is received, the system will be able to determine the user's specific service needs, and accordingly quickly transfer the call to the seat or service end that can provide the target subcategory service, thereby achieving accurate and efficient service response. This process not only improves the user interaction experience, but also ensures the accurate matching of service needs, which helps to improve customer satisfaction and the operational efficiency of the call service center.

[0079] Optionally, in the call forwarding method provided in an embodiment of the present application, the call is forwarded to a server corresponding to a service demand category, including: determining the server corresponding to the service demand category based on a preset corresponding relationship, wherein the preset corresponding relationship is used to represent the corresponding relationship between different service demand categories and different servers.

[0080] The above-mentioned preset correspondence relationship may refer to a mapping mechanism pre-set within the telephone service center, which defines the association between different service demand categories and specific service ends. The preset correspondence relationship may be based on the service demand category and the server's schedule. The types of preset correspondence relationships may include but are not limited to one-to-one relationships, one-to-many relationships, many-to-one relationships, and many-to-many relationships. The type of preset correspondence relationship needs to be determined based on the actual business structure and service requirements, and is not limited here. The preset correspondence relationship can be used to realize intelligent call forwarding, improve service efficiency and customer problem solving speed.

[0081] In an optional embodiment, by establishing a preset correspondence between the service demand category and the service end, the call can be quickly transferred to the service end according to the preset correspondence after the service demand category is determined. The above process can provide more personalized, efficient and professional customer service by carefully dividing and reasonably matching the service demand category and the service end, and at the same time effectively manage and utilize customer service resources to achieve the goal of improving overall service quality and operational efficiency.

[0082] In an optional embodiment, establishing an agent schedule is to determine the preset correspondence, and the process of establishing an agent schedule is as follows: 1. Determine the demand: First, analyze historical data and business trends to determine the number of customer service personnel required in each time period. This can be predicted based on the workload and customer demand in different time periods; 2. Determine the shift length: Determine the length of each shift based on business needs and employee working time restrictions. The common shift length is 8 hours, but it can also be adjusted according to actual conditions; 3. Assign employees to shifts: Assign available customer service personnel to appropriate shifts based on their available working time periods and availability. Ensure that each shift is covered by enough customer service personnel; 4. Consider vacation and rest time: Consider employees' vacation needs and rest time, and ensure that these times are reasonably allocated in the scheduling plan. This can be achieved by collecting employees' vacation requests in advance or using shift rules; 5. Create a schedule: Create a schedule based on the above allocations and considerations to clarify each employee's work shift in each time period. The shift schedule should include the start time, end time and corresponding customer service personnel for each shift; 6. Shift rules: If the shift model is used, determine the shift cycle and arrange the shift order of employees into the shift schedule according to the rules. This ensures that employees work in shifts at different time periods to balance workloads and distribute working time fairly; 7. Adjustment and optimization: Adjust and optimize the shift schedule based on actual conditions and feedback. The shift schedule can be fine-tuned based on customer feedback, business needs and employee feedback to improve work efficiency and employee satisfaction.

[0083] Optionally, the call transfer method provided in the embodiment of the present application also includes: obtaining sample text data of the sample user and multiple levels of sample intent information corresponding to the sample text data; inputting the sample text data and the multiple levels of sample intent information into an initial intent recognition model, using the initial intent recognition model to recognize the intention of the sample user, and obtaining multiple levels of predicted intent information; updating the model parameters of the initial intent recognition model based on the multiple levels of sample intent information and the multiple levels of predicted intent information to obtain an intent recognition model.

[0084] The above-mentioned sample text data may refer to real or simulated user conversation texts used to train and test intent recognition models. The sample text data may come from the interaction history between customers and telephone service centers. The sample text data may include but is not limited to conversation texts for various service needs such as user inquiries, account operations, product consultations, complaints and suggestions. The specific sample text data needs to be determined based on actual conditions and model requirements, and is not limited here.

[0085] The above-mentioned sample intent information may refer to the real intent label corresponding to the sample text data, which is usually manually annotated by professionals based on the content of the sample text data. The types of sample intent information may include but are not limited to query, operation, consultation, etc. The specific sample intent information needs to be determined based on specific business needs and the service scope of the telephone service center. No limitation is made here. The sample text data and the sample intent data are used together to enable the model to learn the expression patterns and intent classification standards of different user service needs, thereby improving the model's intent recognition capabilities.

[0086] The above-mentioned initial intent recognition model may refer to the initial model that has not yet been trained for a specific task at the beginning of the model training process. The specific initial intent recognition model needs to be determined based on actual needs and model functions, and is not limited here. The initial intent recognition model can be used to build a preliminary framework for intent recognition, and through parameter adjustment during the model training process, it can more accurately understand and classify users' service needs.

[0087] The above-mentioned predicted intent information may refer to the intent classification result obtained by the initial intent recognition model on the sample text data. The predicted intent information may be used to evaluate the performance of the model. By comparing the predicted results output by the model with the sample intent information, the recognition accuracy of the model may be quantified, thereby guiding the updating and optimization of the model parameters.

[0088] In an optional embodiment, firstly, sample text data of a large number of sample users are collected, and multiple levels of sample intent information related to the sample text data are annotated; then, these sample text data and sample intent information are input into the initial intent recognition model for training. The training process enables the model to gradually master the recognition skills of user intent. For each sample text data, the model will output multiple levels of predicted intent information; finally, the predicted intent information is compared with the sample intent information, and then the model parameters are adjusted based on the comparison results to optimize the learning process of the model. Through repeated iterations and optimization, a high-precision intent recognition model is finally obtained. This multi-level intent recognition method based on deep learning overcomes the limitations of traditional key transfer by making full use of the hierarchical structure of sample data and intent, realizes instant understanding and reasonable transfer of calls, greatly shortens customer waiting time, and improves service efficiency and quality.

[0089] The present application also provides a model training method. Figure 4 is a flow chart of a model training method according to an embodiment of the present application, such as Figure 4 As shown, the method includes:

[0090] Step S402: Obtain sample text data of a sample user and multiple levels of sample intent information corresponding to the sample text data.

[0091] Step S404: input the sample text data and multiple levels of sample intent information into an initial intent recognition model, use the initial intent recognition model to recognize the intent of the sample user, and obtain multiple levels of predicted intent information.

[0092] Step S406, training the initial intent recognition model based on multiple levels of sample intent information and multiple levels of predicted intent information to obtain an intent recognition model.

[0093] In an optional embodiment, first obtain sample text data in historical data and sample intent information corresponding to the sample text data; then input these sample text data and sample intent information into the initial intent recognition model for training. The training process enables the model to gradually master the recognition skills of user intent. For each sample text data, the model will output multiple levels of predicted intent information; finally, compare the predicted intent information with the sample intent information, and then adjust the model parameters based on the comparison results to optimize the learning process of the model. Through repeated iterations and optimization, a high-precision intent recognition model is finally obtained. This multi-level intent recognition method based on deep learning overcomes the limitations of traditional key transfer by making full use of the hierarchical structure of sample data and intent, realizes instant understanding and reasonable transfer of calls, greatly shortens customer waiting time, and improves service efficiency and quality.

[0094] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0095] Example 2

[0096] The embodiment of the present application also provides a telephone switching device. It should be noted that the telephone switching device of the embodiment of the present application can be used to execute the telephone switching method provided in the embodiment of the present application. The telephone switching device provided in the embodiment of the present application is introduced below.

[0097] According to an embodiment of the present application, a device for implementing the above-mentioned call transfer method is also provided. Figure 5 is a schematic diagram of a telephone switching device according to an embodiment of the present application, such as Figure 5As shown, the device includes: a conversion module 502, which is used to convert the voice stream in response to receiving the voice stream of the user's incoming call to obtain text data; an identification module 504, which is used to input the text data into the intention recognition model, and use the intention recognition model to identify the user's intention to obtain multiple levels of intention information, wherein different levels of intention information have different levels of detail in describing the user's intention; a first determination module 506, which is used to determine the user's service demand category based on multiple levels of intention information; a transfer module 508, which is used to transfer the call to the server corresponding to the service demand category, wherein the customer service personnel corresponding to the server are used to solve the user's problems in the service demand category.

[0098] The telephone transfer device provided in the embodiment of the present application identifies text information containing user intentions by constructing an intent recognition model to obtain intent information at different levels, so that the service demand category to which the user intention belongs can be accurately determined based on intent information of different levels of detail. Finally, the call is transferred based on the service demand category, thereby achieving the purpose of automatically transferring the call to the most appropriate service end, thereby improving the transfer efficiency and accuracy, significantly shortening the user waiting time, reducing service delays caused by transfer errors, and improving customer satisfaction and overall service efficiency, thereby solving the technical problem of low transfer efficiency in related technologies.

[0099] Optionally, in the telephone switching device provided in the embodiment of the present application, multiple levels of intent information include at least one parent intent and at least one child intent, and the first determination module includes: a first classification unit, used to classify at least one parent intent to obtain a first service demand category; a second classification unit, used to classify at least one child intent to obtain a second service demand category, wherein the level of detail of at least one child intent is greater than the level of detail of at least one parent intent; a first determination unit, used to determine the service demand category based on the first service demand category and the second service demand category.

[0100] Optionally, in the telephone switching device provided in the embodiment of the present application, the first determination unit includes: a first determination sub-unit, used to determine that the second service demand category is a service demand category in response to the first service demand category being the same as the second service demand category; and a second determination sub-unit, used to determine that the first service demand category is a service demand category in response to the first service demand category being different from the second service demand category.

[0101] Optionally, in the telephone switching device provided in the embodiment of the present application, the first determination subunit further includes: in response to the second service demand category containing multiple subcategories, determining a third service demand category among the multiple subcategories based on a preset priority, and determining the third service demand category as the service demand category.

[0102] Optionally, in the telephone switching device provided in the embodiment of the present application, the device also includes: an output module, used to output multiple subcategories in response to the second service demand category containing multiple subcategories; a second determination module, used to determine that the target subcategory is a service demand category in response to receiving a voice confirmation instruction of a target subcategory among the multiple subcategories.

[0103] Optionally, in the telephone switching device provided in the embodiment of the present application, the switching module includes: a second determination unit, used to determine the server corresponding to the service demand category based on a preset corresponding relationship, wherein the preset corresponding relationship is used to represent the correspondence between different service demand categories and different server ends.

[0104] Optionally, in the telephone switching device provided in the embodiment of the present application, the device also includes: an acquisition module, used to obtain sample text data of a sample user and multiple levels of sample intent information corresponding to the sample text data; an identification module, used to input the sample text data and multiple levels of sample intent information into an initial intent recognition model, and use the initial intent recognition model to identify the intention of the sample user to obtain multiple levels of predicted intent information; an update module, used to update the model parameters of the initial intent recognition model based on multiple levels of sample intent information and multiple levels of predicted intent information to obtain an intent recognition model.

[0105] It should be noted here that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules can also be run as part of the device in the computer terminal 10 provided in Example 1.

[0106] Example 3

[0107] An embodiment of the present application may provide an electronic device, Figure 6 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 6 As shown, the electronic device may include: one or more ( Figure 6 (only one is shown) processor 602, memory 604, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0108] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0109] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: in response to receiving a voice stream of an incoming call from a user, convert the voice stream to obtain text data; input the text data into an intent recognition model, and use the intent recognition model to recognize the user's intent to obtain multiple levels of intent information, wherein different levels of intent information describe the user's intent in different degrees of detail; determine the user's service demand category based on the multiple levels of intent information; and transfer the call to a server corresponding to the service demand category, wherein the customer service personnel corresponding to the server are used to solve the user's problems in the service demand category.

[0110] The processor can also call the information and applications stored in the memory through the transmission device to perform the following steps: classify at least one parent intent to obtain a first service requirement category; classify at least one child intent to obtain a second service requirement category, wherein the level of detail of at least one child intent is greater than the level of detail of at least one parent intent; determine the service requirement category based on the first service requirement category and the second service requirement category.

[0111] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: in response to the first service demand category being the same as the second service demand category, determining the second service demand category as the service demand category; in response to the first service demand category being different from the second service demand category, determining the first service demand category as the service demand category.

[0112] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: in response to the second service demand category containing multiple subcategories, determine the third service demand category among the multiple subcategories based on a preset priority, and determine the third service demand category as the service demand category.

[0113] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: in response to the second service demand category containing multiple subcategories, output multiple subcategories; in response to receiving a voice confirmation instruction of a target subcategory among the multiple subcategories, determine that the target subcategory is a service demand category.

[0114] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: determine the server corresponding to the service demand category based on a preset correspondence, wherein the preset correspondence is used to represent the correspondence between different service demand categories and different server ends.

[0115] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain sample text data of the sample user and multiple levels of sample intent information corresponding to the sample text data; input the sample text data and multiple levels of sample intent information into the initial intent recognition model, use the initial intent recognition model to recognize the intention of the sample user, and obtain multiple levels of predicted intent information; update the model parameters of the initial intent recognition model based on multiple levels of sample intent information and multiple levels of predicted intent information to obtain an intent recognition model.

[0116] By adopting the embodiment of the present application, a solution for call forwarding is provided. The present application identifies text information containing user intentions by constructing an intent recognition model, and obtains intent information of different levels, so that the service demand category to which the user intention belongs can be accurately determined according to the intent information of different levels of detail, and finally the call is forwarded based on the service demand category, so as to achieve the purpose of automatically forwarding the call to the most appropriate service end, thereby improving the transfer efficiency and accuracy, significantly shortening the user waiting time, reducing the service delay caused by the transfer error, improving customer satisfaction and overall service efficiency, and thus solving the technical problem of low transfer efficiency in the related technology.

[0117] It can be understood by those skilled in the art that Figure 6 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 6 The structure of the electronic device is not limited. Figure 6 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 6 Different configurations shown.

[0118] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0119] Example 4

[0120] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the call transfer method provided in the first embodiment.

[0121] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0122] The present application also provides a computer program product, which is suitable for executing the steps of the call forwarding method when executed on a data processing device.

[0123] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0124] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0125] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0129] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A telephone transfer method, characterized in that: include: In response to receiving a voice stream of an incoming call from a user, converting the voice stream to obtain text data; Inputting the text data into an intention recognition model, using the intention recognition model to recognize the user's intention, and obtaining multiple levels of intention information, wherein different levels of intention information describe the user's intention in different degrees of detail; Determining a service demand category of the user based on the multiple levels of intent information; The call is transferred to a service end corresponding to the service demand category, wherein the customer service personnel corresponding to the service end are used to solve the user's problem in the service demand category.

2. The telephone transfer method according to claim 1, characterized in that: The multiple levels of intent information include at least one parent intent and at least one child intent, and determining the service demand category of the user based on the multiple levels of intent information includes: Classifying the at least one parent intent to obtain a first service demand category; Classifying the at least one child intent to obtain a second service demand category, wherein the detail level of the at least one child intent is greater than the detail level of the at least one parent intent; The service requirement category is determined based on the first service requirement category and the second service requirement category.

3. The telephone transfer method according to claim 2, characterized in that: Determining the service requirement category based on the first service requirement category and the second service requirement category includes: In response to the first service demand category being the same as the second service demand category, determining the second service demand category to be the service demand category; In response to the first service demand category being different from the second service demand category, the first service demand category is determined to be the service demand category.

4. The telephone transfer method according to claim 2, characterized in that: After responding that the first service requirement category is the same as the second service requirement category, the method further includes: In response to the second service demand category including a plurality of subcategories, a third service demand category among the plurality of subcategories is determined based on a preset priority, and the third service demand category is determined as the service demand category.

5. The telephone transfer method according to claim 2, characterized in that: After responding that the first service requirement category is the same as the second service requirement category, the method further includes: In response to the second service demand category including a plurality of subcategories, outputting the plurality of subcategories; In response to receiving a voice confirmation instruction of a target subcategory among the plurality of subcategories, the target subcategory is determined to be the service demand category.

6. The telephone transfer method according to claim 1, characterized in that: Transferring the call to a service end corresponding to the service demand category includes: The server corresponding to the service requirement category is determined based on a preset corresponding relationship, wherein the preset corresponding relationship is used to represent the corresponding relationship between different service requirement categories and different server ends.

7. The telephone transfer method according to claim 1, characterized in that: The method further comprises: Acquire sample text data of a sample user and multiple levels of sample intent information corresponding to the sample text data; Inputting the sample text data and the sample intent information of the multiple levels into an initial intent recognition model, using the initial intent recognition model to recognize the intent of the sample user, and obtaining multiple levels of predicted intent information; Based on the multiple levels of sample intent information and the multiple levels of predicted intent information, the model parameters of the initial intent recognition model are updated to obtain an intent recognition model.

8. A model training method, characterized in that: include: Acquire sample text data of a sample user and multiple levels of sample intent information corresponding to the sample text data; Inputting the sample text data and the sample intent information of the multiple levels into an initial intent recognition model, using the initial intent recognition model to recognize the intent of the sample user, and obtaining multiple levels of predicted intent information; The initial intent recognition model is trained based on the multiple levels of sample intent information and the multiple levels of predicted intent information to obtain an intent recognition model.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 8.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 8 when running.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images