Service providing method and device and service request processing method

Abstract

The embodiment of the invention provides a service providing method and device and a service request processing method, and relates to the technical field of artificial intelligence, and the service providing method comprises the steps: obtaining an initial text which is a description text of a request target service; field association information and an initial domain model corresponding to the initial text are determined, the initial domain model comprises multiple to-be-filled fields, and the field association information comprises association relationships among the to-be-filled fields; determining a filling sequence according to the field associated information, and filling the to-be-filled fields in the initial domain model according to the filling sequence and the initial text to obtain a target domain model; and providing the target business based on the target domain model. The to-be-filled field is prevented from being omitted, the completeness of field filling is improved, and the accuracy of field filling is improved. In practical application, a user does not need to input a complete text containing the field values of all the to-be-filled fields, and only needs to input a simple required text, so that the knowledge threshold of the user is reduced, and the user experience is improved.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of artificial intelligence technology, and in particular to a service provision method and device, and a service request processing method. Background Art

[0002] A domain model is an abstract representation of the business rules and logic within a specific business domain. It uses objects to describe entities within the business domain and the relationships between them. Fields are one of the basic building blocks of an object and are used to describe the specific characteristics of objects within the domain model. For example, in a transaction business, the objects in the domain model might include entities such as orders and accounts. The fields corresponding to order objects might include the order number and order creation time, while the fields corresponding to account objects might include the account ID, account credit rating, and account type.

[0003] Generally, when a user has a business need, the fields in the domain model corresponding to the business need to be populated first. This means that the field values ​​of the fields in the domain model need to be determined. Only after the fields are populated can the domain model be called and processed by subsequent business logic to provide services to users. Therefore, accurately populating the fields in the domain model is an important prerequisite for ensuring the correct execution of business processes. Summary of the Invention

[0004] In view of this, embodiments of this specification provide a service provision method. One or more embodiments of this specification also relate to a service request processing method, a service provision apparatus, a computing device, a computer-readable storage medium, and a computer program product to address technical deficiencies in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a service provision method is provided, including: Obtaining an initial text, wherein the initial text is a description text of the requested target service; Determining field association information and an initial domain model corresponding to the initial text, wherein the initial domain model includes a plurality of fields to be filled, and the field association information includes association relationships between the fields to be filled; Determining a filling order according to the field association information, and filling the to-be-filled fields in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one to-be-filled field; The target service is provided based on the target domain model.

[0006] According to a second aspect of an embodiment of this specification, a service request processing method is provided, which is applied to a cloud-side device and includes: A service request sent by a receiving terminal device, wherein the service request carries an initial text; Determining field association information and an initial domain model corresponding to the business request, wherein the initial domain model includes a plurality of fields to be filled, and the field association information includes association relationships between the fields to be filled; Determining a filling order according to the field association information, and filling the to-be-filled fields in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one to-be-filled field; The business request is processed based on the target domain model, a request processing result corresponding to the business request is obtained, and the request processing result is sent to the end-side device.

[0007] According to a third aspect of the embodiments of this specification, a service providing device is provided, including: An acquisition module is configured to acquire an initial text, wherein the initial text is a description text of the requested target service; A first determining module is configured to determine field association information and an initial domain model corresponding to the initial text, wherein the initial domain model includes a plurality of fields to be filled, and the field association information includes association relationships between the fields to be filled; A first filling module is configured to determine a filling order according to the field association information, and fill the to-be-filled fields in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one to-be-filled field; A providing module is configured to provide the target business based on the target domain model.

[0008] According to a fourth aspect of the embodiments of this specification, a computing device is provided, including: memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the above method are implemented.

[0009] According to a fifth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores a computer program / instruction, and the computer program / instruction implements the steps of the above method when executed by a processor.

[0010] According to a sixth aspect of the embodiments of this specification, a computer program product is provided, comprising a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0011] One embodiment of the present specification can obtain an initial text, which is a description text of the target business requested; determine the field association information and the initial domain model corresponding to the initial text, wherein the initial domain model includes multiple fields to be filled, and the field association information includes the association relationship between the fields to be filled; determine the filling order based on the field association information, and fill the fields to be filled in the initial domain model according to the initial text in accordance with the filling order to obtain the target domain model, wherein the filling order includes at least one field to be filled; and provide the target business based on the target domain model.

[0012] An embodiment of the present specification fills the fields in the domain model corresponding to the initial text according to the filling order determined by the field association information corresponding to the initial text, which can avoid missing the fields to be filled and improve the accuracy of field filling. In addition, since the field association information is the association information between the fields to be filled, when the initial text does not include the field values ​​of all the fields to be filled, the field values ​​of the fields to be filled that are not included in the initial text can be determined based on the field association information, and the integrity of the field filling can still be guaranteed. That is, the aforementioned method supports receiving the initial text that does not contain the field values ​​of all the fields to be filled, that is, the incomplete initial text. In actual application, the user does not need to enter the complete text containing the field values ​​of all the fields to be filled, but can enter a simple requirement text, which reduces the user's knowledge threshold and improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 This is a flow chart of a service provision method provided by an embodiment of this specification; Figure 2 This is a schematic diagram of an association relationship provided by an embodiment of this specification; Figure 3 This is a flow chart of a method for providing a financial resource borrowing service provided by an embodiment of this specification; Figure 4 This is a flowchart of a method for processing a service request provided by an embodiment of this specification; Figure 5 This is a schematic diagram of the structure of a service providing device provided in one embodiment of this specification; Figure 6 This is a schematic diagram of the structure of a service request processing device provided by an embodiment of this specification; Figure 7 This is an architecture diagram of a service request processing system provided by one embodiment of this specification; Figure 8 This is a structural block diagram of a computing device provided by one embodiment of this specification. DETAILED DESCRIPTION

[0013] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0014] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0015] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0016] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this manual are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant regions, and corresponding operation entrances must be provided for users to choose to authorize or refuse.

[0017] In one or more embodiments of this specification, a large model refers to a deep learning model with large-scale model parameters, typically containing hundreds of millions, tens of billions, hundreds of billions, trillions, or even more than ten trillion model parameters. A large model can also be called a foundation model. It is pre-trained on a large amount of unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks and has good generalization capabilities, such as large language models (LLMs) and multi-modal pre-training models.

[0018] When large models are used in practice, only a small number of samples are needed to fine-tune the pre-trained model and it can be applied to different tasks. Large models can be widely used in natural language processing (NLP), computer vision and other fields. Specifically, they can be applied to computer vision tasks such as visual question answering (VQA), image caption (IC), and image generation, as well as natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. The main application scenarios of large models include digital assistants, intelligent robots, search, online education, office software, e-commerce, and intelligent design.

[0019] As described in the background, a domain model is an abstract representation of the core concepts, rules, entities, and their relationships within a specific business domain. It describes the key objects involved in the business domain and expresses the interactions between these objects and the business rules. The domain model is the core of business logic, serving as a bridge between business requirements and technical implementation. In practical applications, to ensure the correct execution of business processes, the fields in the domain model must be populated with valid data.

[0020] In this specification, a service provision method is provided. This specification also involves a service request processing method, a service provision device, a computing device, a computer-readable storage medium and a computer program product, which are described in detail one by one in the following embodiments.

[0021] See also Figure 1 , Figure 1 A flowchart of a service provision method according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0022] Step 102: Acquire an initial text, wherein the initial text is a description text of the requested target service.

[0023] The executing entity of the technical solution of this application specification can be any computing device with computing capabilities, such as a terminal, server, etc., and this specification does not impose any specific restrictions.

[0024] In actual applications, a computing device may provide at least one business service to a user. This specification does not limit the specific types and number of business services that a computing device can provide. For example, the business services provided include but are not limited to transactions, resource lending, tutoring, and travel services.

[0025] In one or more embodiments of this specification, the initial text may be input by a user into a computing device, and the computing device may receive the initial text input by the user. Specifically, when a user has a service requirement, the user may input a description text of the target service requested, i.e., the initial text, into the computing device. The computing device may perform subsequent processing based on the initial text input by the user to provide the target service to the user.

[0026] It should be noted that this specification does not limit the method by which the computing device obtains the initial text, nor does it limit the method by which the user requests the target service. To improve the convenience and speed of user service requests, in this specification, users can request the target service from the computing device through text input, voice input, etc.

[0027] In one or more embodiments of the present specification, a computing device may display a business page, which may include an input control for entering text. A user may enter a description text of the requested target business, i.e., an initial text, in the input control, and the computing device may obtain the initial text.

[0028] In one or more embodiments of the present specification, the computing device may further include a speech recognition module, and the user may issue a speech instruction through semantic input, and the speech instruction is used to instruct the computing device to provide the target service for the user. The computing device may then parse the speech instruction through the speech recognition module and generate corresponding text content, thereby obtaining an initial text corresponding to the speech instruction.

[0029] Step 104: Determine the field association information and the initial domain model corresponding to the initial text, wherein the initial domain model includes a plurality of fields to be filled, and the field association information is association information between the fields to be filled.

[0030] As previously mentioned, a computing device can provide users with at least one business service, such as a transaction service, a resource lending service, a tutoring service, or a travel service. In actual applications, relevant technical personnel can pre-build domain models corresponding to each business, such as a domain model corresponding to a transaction service, a domain model corresponding to a resource lending service, a domain model corresponding to a tutoring service, and a domain model corresponding to a travel service.

[0031] Furthermore, in order to meet the diverse needs of users, for each business, it can be divided into several sub-businesses based on different division rules, and a corresponding domain model can be constructed for each sub-business. For example, for transaction business, the transaction business can be divided into cross-border transaction sub-businesses and domestic transaction sub-businesses based on regions, and corresponding domain models can be constructed for each of them. The transaction business can also be divided into risky transaction sub-businesses and non-risky transaction sub-businesses based on transaction amounts, and corresponding domain models can be constructed for each of them. Similarly, for resource borrowing business, the resource borrowing business can be divided into financial resource borrowing business, storage resource borrowing business, etc. based on resource type, and corresponding domain models can be constructed for each of them. In actual applications, each business can be divided and each domain model can be constructed based on actual needs, and this manual does not impose specific restrictions.

[0032] It should be noted that how to build a domain model corresponding to the business is a relatively mature technology at present, and this manual will not go into details.

[0033] In actual applications, domain models include multiple fields to be populated. When providing services to users, the computing device must first determine the domain model corresponding to the user's requested service, then populate the fields in the domain model corresponding to the user's requested service. Only after the populated fields are completed can the user's requested service be provided based on the populated domain model.

[0034] It should be noted that the fields to be filled in the domain model are predetermined. The fields to be filled can be at least part of the fields in the domain model, or all the fields in the domain model. The fields to be filled in the domain model can be predetermined based on actual needs.

[0035] With the rapid development of Large Language Models (LLMs), using LLMs to assign values ​​to fields in domain models has become a key approach. However, with the continuous optimization and upgrade of business systems and the evolving needs of users, the number of entities in the business has increased, and with it, the number of fields in the domain model has increased. This makes accurately assigning values ​​to each field in LLMs a challenge.

[0036] In this specification, in order to improve the accuracy of field filling, the association information between the to-be-filled fields corresponding to each domain model can be pre-built. For example, for transaction business, the fields may include order number, order creation time, etc. Generally, the order number can be assigned after the order is created, so the association information between the order number and the order creation time can be: generate the order number after generating the order creation time. For another example, for financial resource borrowing business, the fields may include financial resource borrowing target, financial resource borrowing amount, etc. Generally, the financial resource borrowing target is different, and the financial resource borrowing target is the service provider corresponding to the financial resource borrowing business, and the financial resource borrowing amount is different, so the association information between the financial resource borrowing target and the financial resource borrowing amount can be: determine the financial resource borrowing amount according to the financial resource borrowing target.

[0037] In one or more embodiments of this specification, each to-be-populated field in a domain model has field association information. This field association information is association information between the to-be-populated fields in the domain model. For example, if there are two domain models, Domain Model A and Domain Model B, association information between the to-be-populated fields in Domain Model A and between the to-be-populated fields in Domain Model B can be pre-established.

[0038] It should be noted that the field association information may be association information between some of the fields to be filled in the domain model, or association information between all the fields to be filled, and can be determined according to actual needs.

[0039] In addition, this specification does not limit the specific representation of the associated information. In practical applications, the representation of associated information includes but is not limited to a graph structure, a linked list structure, and a text description. For example, with respect to the aforementioned transaction business and financial resource borrowing business, this specification takes the directed graph in the graph structure as an example and provides a schematic diagram of the association relationship. For details, please refer to Figure 2 See also Figure 2 , Figure 2 A schematic diagram of an association relationship provided for one embodiment of this specification.

[0040] In this specification, after the domain model and the field association information corresponding to the domain model are pre-built, the computing device can determine the field association information and the initial domain model corresponding to the initial text after obtaining it.

[0041] In practical applications, when determining the field association information and initial domain model corresponding to the initial text, one can first determine the target business corresponding to the initial text and then determine the initial domain model and field association information based on the target business. For example, a computing device can input the initial text into a machine learning model, such as a keyword extraction model or an intent recognition model, to obtain the target business corresponding to the initial text output by the machine learning model. The computing device can then match the initial domain model to the target business and obtain the field association information corresponding to the initial domain model.

[0042] Step 106: Determine a filling order based on the field association information, and fill the fields to be filled in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one field to be filled.

[0043] In practical applications, the computing device can use a pre-trained large language model to fill in the to-be-filled fields in the initial domain model based on the association information between the to-be-filled fields provided by the field association information, and based on the initial text, thereby obtaining the target domain model. Specifically, the computing device can determine the current to-be-filled field based on the association information between the to-be-filled fields provided by the field association information, and extract the field value of the current to-be-filled field from the initial text using the large language model.

[0044] Since there are dependencies between different fields, the dependencies between fields, that is, field association information, can provide guidance information for the large language model, thereby improving the accuracy of the filled field values.

[0045] In one or more embodiments of this specification, a filling order may be determined based on field association information. This filling order refers to the filling order of the fields to be filled, and the filling order includes at least one field to be filled. For example, if the field association information is that A includes B, and B and C have an association relationship, then the filling order may be A, B, C. This specification does not specifically limit how to determine the filling order based on the field association information. For example, the order of fields with fewer associations may be arranged before the order of fields with more associations. The filling order may also be determined based on the field association information and actual business needs.

[0046] Filling the to-be-filled fields in the initial domain model according to the initial text in the filling order includes: Determine the current field to be filled according to the filling order; According to the initial text, the field value of the current field to be filled is determined, and according to the field value, the current field to be filled in the initial domain model is filled.

[0047] In one or more embodiments of the present specification, in order to improve the accuracy of the field value determined by the LLM and to improve the accuracy of field filling, the current field to be filled may be one, that is, the filling order is the filling order of each field to be filled.

[0048] In one or more embodiments of this specification, the filling sequence can be constructed as a linked list, where each element in the linked list is a field to be filled. Each field to be filled can then be filled in sequence according to the linked list. Of course, the filling sequence can also be constructed as a graph structure or text description, etc., and this specification does not impose any specific limitations.

[0049] In this specification, determining the field value of the current field to be filled according to the initial text includes: Determine whether the initial text includes the field value corresponding to the current field to be filled; If yes, extract the field value corresponding to the current field to be filled from the initial text; If not, then according to the preset condition corresponding to the current field to be filled, obtain the field value corresponding to the current field to be filled.

[0050] As can be seen, when the field value corresponding to the current field to be filled can be determined from the initial text, that is, the initial text includes the field value corresponding to the current field to be filled, the field value corresponding to the current field to be filled can be extracted from the initial text. When the field value corresponding to the current field to be filled cannot be determined from the initial text, that is, the initial text does not include the field value corresponding to the current field to be filled, the field value corresponding to the current field to be filled can be obtained based on the preset conditions corresponding to the current field to be filled.

[0051] It should be noted that, the field value corresponding to the current field to be filled in can be extracted from the initial text by using a key field extraction model, a large language model, etc., and this specification does not impose any specific restrictions.

[0052] Obtaining a field value corresponding to the current field to be filled according to a preset condition corresponding to the current field to be filled includes: When the initial text satisfies the preset condition, obtaining a field value corresponding to the current field to be filled from the preset condition; In the case that the initial text does not meet the preset condition, question information is generated according to the current field to be filled, and the field value corresponding to the current field to be filled is obtained based on the reply information corresponding to the question information.

[0053] In one or more embodiments of the present specification, the preset condition may be whether there is a mapping relationship between the field value corresponding to the current field to be filled and the field value corresponding to the field to be filled contained in the initial text. If there is a mapping relationship, the preset condition is met; if there is no mapping relationship, the preset condition is not met.

[0054] The mapping relationship is pre-set, specifically, a pre-set mapping relationship between the field value corresponding to the current field to be filled and the field value corresponding to the field to be filled contained in the initial text. It should be understood that the mapping relationship can also reflect the mapping relationship between the current field to be filled and the field to be filled contained in the initial text, the mapping relationship between the field value corresponding to the current field to be filled and the field to be filled contained in the initial text, and the mapping relationship between the current field to be filled and the field value corresponding to the field to be filled contained in the initial text.

[0055] Therefore, when the initial text does not include the field value corresponding to the current field to be filled, the field value corresponding to the field to be filled contained in the initial text can be determined first, and then the target mapping relationship between the field value corresponding to the field to be filled contained in the initial text and the current field to be filled can be determined from the pre-set mapping relationship, so that the field value corresponding to the current field to be filled in the target mapping relationship can be obtained. Of course, if the target mapping relationship can be determined, that is, the target mapping relationship exists, then the preset condition is met; if the target mapping relationship cannot be determined, that is, the target mapping relationship does not exist, then the preset condition is not met. The target mapping relationship is a mapping relationship between the current field to be filled and the field value corresponding to the field to be filled contained in the initial text, and the target mapping relationship includes the field value corresponding to the current field to be filled.

[0056] For example, in the field of storage resource borrowing, the fields to be filled include the storage resource borrowing service provider and the storage resource borrowing period. Assuming that the current field to be filled is the storage resource borrowing period, and the initial text entered by the user is: Borrow storage resources from service provider A, then based on the initial text, it can be determined that the field to be filled contained in the initial text is: storage resource borrowing service provider, and the field value corresponding to the field to be filled contained in the initial text is: storage resource service provider A. In practice, since different storage resource borrowing service providers set different storage resource borrowing periods, the mapping relationship between different service providers and storage resource borrowing periods can be pre-set. It is further assumed that the set mapping relationship includes: the storage resource borrowing period corresponding to storage resource service provider A is one week, and the storage resource borrowing period corresponding to storage resource service provider B is one month. Although the initial text entered by the user does not include the field value corresponding to the storage resource borrowing period, the target mapping relationship between the field value corresponding to the field to be filled contained in the initial text and the current field to be filled can be determined, that is, the target mapping relationship is: the storage resource borrowing period corresponding to storage resource service provider A is one week, then the storage resource borrowing period of the current field to be filled can be obtained as one week.

[0057] Based on the above method, the user does not need to provide the field value corresponding to each field to be filled. The field values ​​of some fields to be filled can be deduced according to the field association information and preset conditions, thereby lowering the user's knowledge threshold and improving the user experience.

[0058] In actual applications, when the initial text does not meet the preset conditions, it is necessary to generate question information corresponding to the current field to be filled. The user can reply based on the question information, so that the computing device can respond to the reply to the question information and obtain the reply information corresponding to the question information, so that the field value corresponding to the current field to be filled can be extracted from the reply information.

[0059] It should be noted that if the reply to the question still fails to obtain the corresponding field value for the currently unfilled field, the field association information and initial domain model can be redefined based on the initial text and reply information. In other words, if the user intends to update the service, it is necessary to re-determine the target service requested by the user based on the initial text and reply text, and then re-determine the field association information and initial domain model. The re-defined target service can then be provided to the user according to the aforementioned service provision method.

[0060] Furthermore, obtaining a field value corresponding to the current field to be filled according to a preset condition corresponding to the current field to be filled includes: Obtaining a field value corresponding to the field to be filled according to a preset condition corresponding to the field to be filled; The initial text is updated according to the obtained field value corresponding to the current field to be filled.

[0061] In one or more embodiments of the present specification, since it is necessary to determine the field values ​​of the fields to be filled that are not included in the initial text based on the field values ​​of the fields to be filled contained in the initial text, and since the fields to be filled in this specification are filled individually according to the filling order determined based on the field association information, the initial text can be updated after obtaining the field values ​​of the fields to be filled that are not included in the initial text. The updating of the initial text can specifically be adding the field values ​​of the fields to be filled that are not included in the determined initial text to the initial text.

[0062] When filling each field value in sequence according to the filling order, the initial text can be dynamically updated, thereby providing more contextual information for determining the field value corresponding to the next field to be filled, that is, providing more field value information, thereby improving the accuracy of the determined field value corresponding to the next field to be filled.

[0063] Step 108: Providing the target business based on the target domain model.

[0064] In actual applications, after obtaining the target domain model with the fields filled in, the target business can be provided based on the target domain model.

[0065] It should be noted that providing users with services corresponding to domain models based on domain models is a relatively mature technology and is not specifically limited in this specification. For example, after obtaining the target domain model, the computing device can invoke the service execution engine corresponding to the target service, then pass the target domain model as a parameter to the service execution engine, execute the service logic, and provide the target service to the user.

[0066] Based on the above-mentioned service provision method, the fields in the domain model corresponding to the initial text are filled in accordance with the filling order determined by the field association information corresponding to the initial text, which can avoid missing the fields to be filled and improve the accuracy of field filling. In addition, since the field association information is the association information between the fields to be filled, when the initial text does not include the field values ​​of all the fields to be filled, the field values ​​of the fields to be filled that are not included in the initial text can be determined based on the field association information, and the integrity of the field filling can still be guaranteed. That is, the above-mentioned method supports receiving the initial text that does not contain the field values ​​of all the fields to be filled, that is, the incomplete initial text. In actual application, the user does not need to enter the complete text containing the field values ​​of all the fields to be filled, but can enter a simple requirement text, which reduces the user's knowledge threshold and improves the user experience.

[0067] In addition, in this specification, extracting the field value corresponding to the current to-be-filled field from the initial text includes: Get the prompt text corresponding to the current field to be filled; According to the prompt text, the field value corresponding to the current field to be filled is extracted from the initial text.

[0068] For each field currently to be filled, a prompt text corresponding to the field currently to be filled is dynamically set to prompt the large language model to extract the field value corresponding to the field currently to be filled, thereby improving the accuracy of the extracted field value. Specifically, when dynamically setting the prompt text corresponding to the field currently to be filled, the prompt text corresponding to the field currently to be filled can be generated based on a preset prompt framework.

[0069] In one or more embodiments of the present specification, the large language model used to extract the field values ​​of the fields to be filled from the initial text may be a model based on the Transformer architecture. In practical applications, the model based on the Transformer architecture has limited modeling capabilities for long-distance contextual dependencies when processing longer input sequences. Therefore, in the present specification, the field values ​​are extracted field by field in the order of filling, which can reduce the interference of irrelevant information in the initial text and enhance the large language model's ability to capture and extract key contextual information in the initial text, thereby overcoming the limitations of the Transformer architecture in long-distance dependency modeling and alleviating the drawbacks of inaccurate long-distance knowledge acquisition under the Transformer architecture.

[0070] In one or more embodiments of the present specification, the domain model may be a domain model based on a JAVA project. In practical applications, the set operation of the java domain may be enhanced so as to receive the user's natural language requirements as parameter input.

[0071] The following combined Figure 3 , taking the application of the business provision method provided in this specification in the field of financial resource borrowing business as an example, the business provision method is further explained. Figure 3 A flowchart of a method for providing a financial resource borrowing service according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0072] Step 302: Acquire an initial text, wherein the initial text is a description text of a request for a financial resource borrowing service.

[0073] Step 304: Determine the field association information and the initial domain model corresponding to the initial text, wherein the initial domain model includes multiple fields to be filled, and the field association information is the association information between the fields to be filled.

[0074] Step 306: Determine a filling order based on the field association information, and fill the fields to be filled in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one field to be filled.

[0075] Step 308: providing the financial resource borrowing service based on the target domain model.

[0076] Financial resource borrowing refers to business activities in the financial sector where users borrow financial resources from service providers to meet their needs. In this type of business, service providers can provide users with financial resource borrowing services, and users can request financial resource borrowing services from service providers. Service providers can be financial service platforms, banks, financial institutions, etc. Financial resources include but are not limited to currency, bonds, stocks, etc.

[0077] In actual applications, when requesting financial resource borrowing, a user may enter initial text into a device or terminal application provided by the service provider that can be used to handle financial resource borrowing services. This initial text describes the user's request for the financial resource borrowing service. The service provider's corresponding server or device then retrieves the initial text. Field association information corresponding to the initial text and an initial domain model are then determined. The initial domain model includes multiple fields to be filled, and the field association information represents the associations between the fields to be filled. Finally, based on the initial text and the field association information, the fields to be filled in the initial domain model are filled to obtain a target domain model. The financial resource borrowing service is then provided based on the target domain model.

[0078] Of course, the initial domain model is the domain model corresponding to the financial resource borrowing business, which can be pre-set as mentioned above, and the to-be-filled fields of the domain model corresponding to the financial resource borrowing business can also be pre-set, which will not be repeated here.

[0079] In addition, as mentioned above, the financial resource borrowing business can also be divided into multiple sub-businesses based on more specific business needs, such as currency borrowing sub-business, equity pledge sub-business, bond purchase sub-business, etc., and then a corresponding domain model can be set for each sub-business, and the fields to be filled in the domain model corresponding to each sub-business can be determined. They can be pre-set according to actual needs, and no further details will be given here.

[0080] It should be noted that, in this embodiment, the specific method of providing the user with the financial resource borrowing service based on the initial text is consistent with the above service providing method. Please refer to the above service providing method and will not be described in detail here.

[0081] Based on the above-mentioned method for providing financial resource borrowing services, the fields in the domain model corresponding to the initial text are filled in accordance with the filling order determined by the field association information corresponding to the initial text, which can avoid missing fields to be filled and improve the accuracy of field filling. In addition, since the field association information is the association information between the fields to be filled, when the initial text does not include the field values ​​of all the fields to be filled, the field values ​​of the fields to be filled that are not included in the initial text can be determined based on the field association information, and the integrity of the field filling can still be guaranteed. That is, the above-mentioned method supports receiving initial text that does not contain the field values ​​of all the fields to be filled, that is, incomplete initial text. In actual applications, users do not need to enter the complete text containing the field values ​​of all the fields to be filled, but can enter a simple requirement text, which reduces the user's knowledge threshold and improves the user experience.

[0082] This specification also provides an embodiment of a method for processing a service request. Figure 4 FIG1 shows a flow chart of a method for processing a service request provided by an embodiment of this specification. Figure 4 As shown, the method for processing the service request includes: Step 402: Receive a service request sent by a terminal-side device, wherein the service request carries an initial text.

[0083] Step 404: Determine the field association information and the initial domain model corresponding to the business request, wherein the initial domain model includes multiple fields to be filled, and the field association information is the association information between the fields to be filled.

[0084] Step 406: Determine a filling order based on the field association information, and fill the fields to be filled in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one field to be filled.

[0085] Step 408: Process the business request based on the target domain model, obtain a request processing result corresponding to the business request, and send the request processing result to the end-side device.

[0086] In actual applications, when a user has a need, the user can enter an initial text on the terminal device. After the terminal device receives the initial text entered by the user, it can send a service request carrying the initial text to the cloud device.

[0087] The cloud-side device can receive a business request sent by the end-side device, and the business request carries an initial text. And determine the field association information and the initial domain model corresponding to the business request, wherein the initial domain model includes multiple fields to be filled, and the field association information is the association information between the fields to be filled. According to the field association information, determine the filling order, and according to the filling order, fill the fields to be filled in the initial domain model according to the initial text to obtain the target domain model, wherein the filling order includes at least one field to be filled. Process the business request based on the target domain model, obtain the request processing result corresponding to the business request, and send the request processing result to the end-side device. Thus, the end-side device can provide the target business to the user based on the request processing result.

[0088] It should be noted that the process of obtaining the target domain model according to the initial text in the business request is consistent with that in the above-mentioned business provision method, and will not be described in detail here.

[0089] Based on the above-mentioned business request processing method, the fields in the domain model corresponding to the initial text can be filled in accordance with the filling order determined by the field association information corresponding to the initial text, which can avoid missing fields to be filled and improve the accuracy of field filling. In addition, since the field association information is the association information between the fields to be filled, when the initial text does not include the field values ​​of all the fields to be filled, the field values ​​of the fields to be filled that are not included in the initial text can be determined based on the field association information, and the integrity of the field filling can still be guaranteed. That is, the above-mentioned method supports receiving initial text that does not contain the field values ​​of all the fields to be filled, that is, incomplete initial text. In actual applications, users do not need to enter the complete text containing the field values ​​of all the fields to be filled, but can enter a simple requirement text, which reduces the user's knowledge threshold and improves the user experience.

[0090] Corresponding to the above-mentioned service providing method embodiment, this specification also provides a service providing device embodiment, Figure 5 FIG1 shows a schematic diagram of the structure of a service providing device provided by an embodiment of this specification. Figure 5 As shown, the device includes: The acquisition module 502 is configured to acquire an initial text, wherein the initial text is a description text of the target service requested; A first determining module 504 is configured to determine field association information corresponding to the initial text and an initial domain model, wherein the initial domain model includes a plurality of fields to be filled, and the field association information is association information between the fields to be filled; A first filling module 506 is configured to determine a filling order according to the field association information, and fill the to-be-filled fields in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one to-be-filled field; The providing module 508 is configured to provide the target business based on the target domain model.

[0091] Optionally, the first determining module 504 is further configured to determine a target business corresponding to the initial text; and determine field association information and an initial domain model according to the target business.

[0092] Optionally, the first filling module 506 is further configured to determine the current field to be filled according to the filling order; determine the field value of the current field to be filled according to the initial text, and fill the current field to be filled in the initial domain model according to the field value.

[0093] Optionally, the first filling module 506 is further configured to determine whether the initial text includes the field value corresponding to the current field to be filled; if so, extract the field value corresponding to the current field to be filled from the initial text; if not, obtain the field value corresponding to the current field to be filled according to the preset conditions corresponding to the current field to be filled.

[0094] Optionally, the first filling module 506 is further configured to, when the initial text meets the preset conditions, obtain the field value corresponding to the current field to be filled from the preset conditions; when the initial text does not meet the preset conditions, generate question information according to the current field to be filled, and obtain the field value corresponding to the current field to be filled based on the reply information corresponding to the question information.

[0095] Optionally, the first filling module 506 is further configured to obtain a field value corresponding to the current field to be filled according to a preset condition corresponding to the current field to be filled; and update the initial text according to the obtained field value corresponding to the current field to be filled.

[0096] Optionally, the first filling module 506 is further configured to obtain a prompt text corresponding to the current field to be filled; and extract a field value corresponding to the current field to be filled from the initial text according to the prompt text.

[0097] Optionally, the first filling module 506 is further configured to, when the field value corresponding to the current field to be filled cannot be obtained based on the reply information corresponding to the question information, redetermine the field association information and the initial domain model based on the initial text and the reply information.

[0098] The above is a schematic scheme of a service provision device of this embodiment. It should be noted that the technical scheme of the service provision device and the technical scheme of the service provision method described above are based on the same concept. For details not described in detail in the technical scheme of the service provision device, please refer to the description of the technical scheme of the service provision method described above.

[0099] Based on the above-mentioned service providing device, the fields in the domain model corresponding to the initial text can be filled in accordance with the filling order determined by the field association information corresponding to the initial text, which can avoid missing the fields to be filled and improve the accuracy of field filling. In addition, since the field association information is the association information between the fields to be filled, when the initial text does not include the field values ​​of all the fields to be filled, the field values ​​of the fields to be filled that are not included in the initial text can be determined based on the field association information, and the integrity of the field filling can still be guaranteed. That is, the above-mentioned method supports receiving the initial text that does not contain the field values ​​of all the fields to be filled, that is, the incomplete initial text. In actual application, the user does not need to enter the complete text containing the field values ​​of all the fields to be filled, but can enter a simple requirement text, which reduces the user's knowledge threshold and improves the user experience.

[0100] Corresponding to the above-mentioned service request processing method embodiment, this specification also provides a service request processing device embodiment, Figure 6 FIG. 1 shows a schematic diagram of a structure of a service request processing device provided by an embodiment of this specification. Figure 6 As shown, the device includes: The receiving module 602 is configured to receive a service request sent by a terminal device, wherein the service request carries an initial text; The second determining module 604 is configured to determine field association information corresponding to the business request and an initial domain model, wherein the initial domain model includes a plurality of fields to be filled, and the field association information is association information between the fields to be filled; A second filling module 606 is configured to determine a filling order based on the field association information, and fill the to-be-filled fields in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one to-be-filled field; The processing module 608 is configured to process the business request based on the target domain model, obtain a request processing result corresponding to the business request, and send the request processing result to the end-side device.

[0101] The above is a schematic diagram of a service request processing device according to this embodiment. It should be noted that the technical solution of the service request processing device and the technical solution of the service request processing method described above are based on the same concept. For details not described in detail in the technical solution of the service request processing device, please refer to the description of the technical solution of the service request processing method described above.

[0102] Based on the above-mentioned business request processing device, the fields in the domain model corresponding to the initial text can be filled in accordance with the filling order determined by the field association information corresponding to the initial text, which can avoid missing the fields to be filled and improve the accuracy of field filling. In addition, since the field association information is the association information between the fields to be filled, when the initial text does not include the field values ​​of all the fields to be filled, the field values ​​of the fields to be filled that are not included in the initial text can be determined based on the field association information, and the integrity of the field filling can still be guaranteed. That is, the above-mentioned method supports receiving the initial text that does not contain the field values ​​of all the fields to be filled, that is, the incomplete initial text. In actual application, the user does not need to enter the complete text containing the field values ​​of all the fields to be filled, but can enter a simple requirement text, which reduces the user's knowledge threshold and improves the user experience.

[0103] See also Figure 7 , Figure 7 The following is an architecture diagram of a service request processing system provided by an embodiment of the present specification. The service request system may include a client 100 and a server 200; The client 100 is configured to send a service request to the server 200, wherein the service request carries an initial text; The server 200 is configured to receive a business request sent by a client, determine field association information and an initial domain model corresponding to the business request, wherein the initial domain model includes multiple fields to be filled, and the field association information is association information between the fields to be filled; determine a filling order based on the field association information, and fill the fields to be filled in the initial domain model according to the filling order based on the initial text to obtain a target domain model, wherein the filling order includes at least one field to be filled; process the business request based on the target domain model to obtain a request processing result corresponding to the business request; and send the request processing result to the client 100; The client 100 is further configured to receive the request processing result sent by the server 200 .

[0104] By applying the solution of the embodiment of this specification, the fields in the domain model corresponding to the initial text can be filled based on the field association information corresponding to the initial text, which can avoid missing fields to be filled and improve the accuracy of field filling. In addition, since the field association information is the association information between the fields to be filled, when the initial text does not include the field values ​​of all the fields to be filled, the field values ​​of the fields to be filled that are not included in the initial text can be determined based on the field association information, and the integrity of the field filling can still be guaranteed. That is, the aforementioned method supports receiving the initial text that does not contain the field values ​​of all the fields to be filled, that is, the incomplete initial text. In actual applications, the user does not need to enter the complete text containing the field values ​​of all the fields to be filled, but can enter a simple requirement text, which reduces the user's knowledge threshold and improves the user experience.

[0105] The service request processing system may include multiple clients 100 and a server 200. The clients 100 may be referred to as end-side devices, and the server 200 may be referred to as cloud-side devices. Multiple clients 100 may establish communication connections through the server 200. In a service request processing scenario, the server 200 is used to provide service request processing services between the multiple clients 100. The multiple clients 100 may act as either senders or receivers, communicating through the server 200.

[0106] Users can interact with the server 200 through the client 100 to receive data sent by other clients 100, or send data to other clients 100. In the service request processing scenario, the user can publish a data stream to the server 200 through the client 100. The server 200 generates a request processing result based on the data stream and pushes the request processing result to other clients with which communication has been established.

[0107] The client 100 and the server 200 are connected via a network. The network provides a medium for the communication link between the client 100 and the server 200. The network can include various connection types, such as wired or wireless communication links or fiber optic cables. The data transmitted by the client 100 may need to be encoded, transcoded, compressed, or other processing before being released to the server 200.

[0108] The client 100 can be a browser, an application (APP), a web application such as an H5 (HyperText Markup Language 5) application, a lightweight application (also known as a mini-program, a type of lightweight application), or a cloud application. The client 100 can be developed based on the software development kit (SDK) of the corresponding service provided by the server 200, such as a real-time communication (RTC) SDK. The client 100 can be deployed on a computing device and rely on the device or certain applications on the device to run. For example, the computing device can have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, tablet computer, or personal computer. Various other types of applications can also be configured on the computing device, such as human-computer interaction applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0109] The server 200 may include servers that provide various services, such as servers that provide communication services to multiple clients, servers that support backend training for models used on clients, and servers that process data sent by clients. It should be noted that the server 200 can be implemented as a distributed server cluster consisting of multiple servers or as a single server. The server can also be a server in a distributed system or a server integrated with blockchain. The server can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), big data and artificial intelligence platforms, or intelligent cloud computing servers or intelligent cloud hosts equipped with artificial intelligence technology.

[0110] It is worth noting that the service provision methods and service request processing methods provided in the embodiments of this specification are generally executed by the server. However, in other embodiments of this specification, the client may also have similar functions to the server, thereby executing the service provision methods and service request processing methods provided in the embodiments of this specification. In other embodiments, the service provision methods and service request processing methods provided in the embodiments of this specification may also be executed jointly by the client and the server.

[0111] Figure 88 shows a block diagram of a computing device 800 according to an embodiment of the present application. Components of the computing device 800 include, but are not limited to, a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and a database 850 is used to store data.

[0112] The computing device 800 also includes an access device 840 that enables the computing device 800 to communicate via one or more networks 860. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 840 may include one or more of any type of network interface (e.g., a network interface card (NIC)) whether wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0113] In one embodiment of the present application, the above components of the computing device 800 and Figure 8 Other components not shown in the figure may also be connected to each other, for example, via a bus. Figure 8 The computing device structure block diagram shown is for illustrative purposes only and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.

[0114] Computing device 800 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, personal digital assistant, laptop computer, notebook computer, netbook computer, etc.), a mobile phone (e.g., a smartphone), a wearable computing device (e.g., a smartwatch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or personal computer (PC). Computing device 800 can also be a mobile or stationary server.

[0115] The processor 820 is configured to execute the following computer program / instruction, which, when executed by the processor, implements the steps of the above-mentioned service provision method and service request processing method.

[0116] The above is a schematic diagram of a computing device according to this embodiment. It should be noted that the technical solution of this computing device is based on the same concept as the technical solutions of the aforementioned service provision method and service request processing method. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solutions of the aforementioned service provision method and service request processing method.

[0117] An embodiment of the present specification further provides a computer-readable storage medium storing a computer program / instruction. When the computer program / instruction is executed by a processor, the steps of the above-mentioned service providing method and service request processing method are implemented.

[0118] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from the other embodiments. In particular, the computer-readable storage medium embodiment is generally similar to the service provision method and service request processing method embodiments, so its description is relatively simple. For relevant portions, refer to the description of the service provision method and service request processing method embodiments.

[0119] An embodiment of the present specification further provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned service provision method and service request processing method when executed by a processor.

[0120] The above is an illustrative solution of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product is based on the same concept as the technical solutions of the aforementioned service provision method and service request processing method. For details not described in detail in the technical solution of the computer program product, please refer to the description of the technical solutions of the aforementioned service provision method and service request processing method.

[0121] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content of the computer-readable medium may be appropriately increased or decreased based on the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0123] It should be noted that the above description is of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0124] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0125] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made based on the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A service providing method, characterized in that: include: Obtaining an initial text, wherein the initial text is a description text of the requested target service; Determining field association information and an initial domain model corresponding to the initial text, wherein the initial domain model includes a plurality of fields to be filled, and the field association information includes association relationships between the fields to be filled; Determining a filling order according to the field association information, and filling the to-be-filled fields in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one to-be-filled field; The target service is provided based on the target domain model.

2. The method according to claim 1, wherein Determining the field association information and the initial domain model corresponding to the initial text includes: Determining a target business corresponding to the initial text; According to the target business, field association information and an initial domain model are determined.

3. The method according to claim 2, wherein Filling the to-be-filled fields in the initial domain model according to the initial text in the filling order includes: Determine the current field to be filled according to the filling order; According to the initial text, the field value of the current field to be filled is determined, and according to the field value, the current field to be filled in the initial domain model is filled.

4. The method according to claim 3, wherein Determining the field value of the current field to be filled according to the initial text includes: Determine whether the initial text includes the field value corresponding to the current field to be filled; If yes, extract the field value corresponding to the current field to be filled from the initial text; If not, then according to the preset condition corresponding to the current field to be filled, obtain the field value corresponding to the current field to be filled.

5. The method according to claim 4, wherein Obtaining a field value corresponding to the current field to be filled according to a preset condition corresponding to the current field to be filled includes: When the initial text satisfies the preset condition, obtaining a field value corresponding to the current field to be filled from the preset condition; In the case that the initial text does not meet the preset condition, question information is generated according to the current field to be filled, and the field value corresponding to the current field to be filled is obtained based on the reply information corresponding to the question information.

6. The method according to claim 4, wherein Obtaining a field value corresponding to the current field to be filled according to a preset condition corresponding to the current field to be filled includes: Obtaining a field value corresponding to the field to be filled according to a preset condition corresponding to the field to be filled; The initial text is updated according to the obtained field value corresponding to the current field to be filled.

7. The method according to claim 4, wherein Extracting a field value corresponding to the current to-be-filled field from the initial text includes: Get the prompt text corresponding to the current field to be filled; According to the prompt text, the field value corresponding to the current field to be filled is extracted from the initial text.

8. The method according to claim 4, wherein: The method further comprises: In the case that the field value corresponding to the current to-be-filled field cannot be obtained based on the reply information corresponding to the question information, the field association information and the initial domain model are re-determined according to the initial text and the reply information.

9. A method for processing a business request, characterized in that: The method is applied to a cloud-side device and includes: A service request sent by a receiving terminal device, wherein the service request carries an initial text; Determining field association information and an initial domain model corresponding to the business request, wherein the initial domain model includes a plurality of fields to be filled, and the field association information includes association relationships between the fields to be filled; Determining a filling order according to the field association information, and filling the to-be-filled fields in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one to-be-filled field; The business request is processed based on the target domain model, a request processing result corresponding to the business request is obtained, and the request processing result is sent to the end-side device.

10. A service providing device, characterized in that: include: An acquisition module is configured to acquire an initial text, wherein the initial text is a description text of the requested target service; A first determining module is configured to determine field association information and an initial domain model corresponding to the initial text, wherein the initial domain model includes a plurality of fields to be filled, and the field association information includes association relationships between the fields to be filled; A first filling module is configured to determine a filling order according to the field association information, and fill the to-be-filled fields in the initial domain model according to the initial text according to the filling order to obtain a target domain model, wherein the filling order includes at least one to-be-filled field; A providing module is configured to provide the target business based on the target domain model.

11. A computing device, characterized in that include: memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer program / instructions are executed by the processor, the steps of the method according to any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium, characterized in that It stores a computer program / instruction, which implements the steps of the method according to any one of claims 1 to 9 when executed by a processor.

13. A computer program product, characterized in that The method comprises a computer program / instruction, which implements the steps of the method according to any one of claims 1 to 9 when executed by a processor.

Images