Process arrangement method, storage medium, program product and electronic equipment

Abstract

The embodiment of the invention discloses a process arrangement method and related equipment, and relates to the technical field of computers. In the embodiment of the specification, according to an initial text, a plurality of processes for processing a product in the initial text and texts corresponding to the plurality of processes are extracted; and further determining hardware interface information and service protocol information required for realizing the flow according to the text corresponding to each flow, wherein the hardware interface information and the service protocol information are used for indicating the system to complete product processing corresponding to the flow node based on at least one hardware interface and at least one service protocol. Further, visualization processing is performed on the plurality of processes and the hardware interface information and the service protocol information corresponding to the plurality of processes to obtain process arrangement information used for indicating complete processing of the product.

Description

Technical Field

[0001] The present specification relates to the field of computer technology, and in particular to a process scheduling method, storage medium, program product and electronic device. Background Art

[0002] Institutions such as consumer finance institutions, e-commerce institutions, and logistics institutions are facing increasing demands from the transaction side, and there are constantly new things and new products waiting for the institutions to process. From the system side, the systems of each institution need to use a set of highly versatile process orchestration systems to orchestrate the entire process of product processing, especially new products, so as to reduce the cost of understanding product processing for users.

[0003] For example, a credit processing process suitable for processing credit products is compiled, which includes common pre-loan process, loan process and post-loan process. Even if credit products have different characteristics and requirements at different times, such as consumer loans, corporate loans, car loans, mortgages, etc., each product may have different approval standards, risk control requirements, repayment methods, etc., the credit process orchestration system can compile a set of processes that are as close to the processing process of different products as possible according to the needs of different products, so that users can understand and use them.

[0004] However, existing process orchestration methods are often accompanied by a large amount of manual intervention. For example, process nodes such as product entry processes and risk control processes require manual orchestration, which is time-consuming and labor-intensive, and has low accuracy. Summary of the invention

[0005] The embodiments of this specification provide a process scheduling method, storage medium, program product and electronic device, which can realize efficient and automatic process scheduling. The technical solution is as follows:

[0006] In a first aspect, an embodiment of the present specification provides a process orchestration method, the method comprising:

[0007] Get the initial text with content related to product processing;

[0008] Extracting multiple processes for processing the product from the initial text, and texts corresponding to the multiple processes;

[0009] According to the text corresponding to the process, determine the hardware interface information and service protocol information required to implement the process, and obtain the implementation information of the process;

[0010] Visualize the multiple processes and the implementation information corresponding to the multiple processes to obtain process arrangement information for indicating the processing of the product

[0011] In a second aspect, an embodiment of the present specification provides a process orchestration device, the device comprising:

[0012] A text acquisition module, used to acquire initial text with content related to product processing;

[0013] A process extraction module, used to extract multiple processes for processing the product from the initial text, and texts corresponding to the multiple processes;

[0014] An information determination module, used to determine the hardware interface information and service protocol information required to implement the process according to the text corresponding to the process, and obtain the implementation information of the process;

[0015] The process arrangement module is used to visualize the multiple processes and the implementation information respectively corresponding to the multiple processes to obtain process arrangement information for indicating the processing of the product.

[0016] In a third aspect, an embodiment of the present specification provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0017] In a fourth aspect, an embodiment of the present specification provides a computer program product, wherein the computer program product stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0018] In a fifth aspect, an embodiment of the present specification provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0019] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least:

[0020] In an embodiment of the present specification, based on the initial text, multiple processes for processing a product in the initial text, and the texts corresponding to the multiple processes are extracted. Further, based on the text corresponding to each process, the hardware interface information and service protocol information required to implement the process are determined, and the hardware interface information and service protocol information are used to indicate that the system completes the processing for the product corresponding to the process node based on at least one hardware interface and at least one service protocol. Further, the hardware interface information and service protocol information corresponding to the multiple processes and the multiple processes are visualized to obtain process orchestration information for indicating the complete processing of the product. Therefore, the embodiment of the present specification can realize efficient and automatic process orchestration based on the process orchestration method, and the obtained process orchestration information can be a visual report in the form of a chart. Through the visual report, the user can quickly understand the multiple processes for complete processing of the product, as well as the hardware interface information and service protocol information required for each process. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 It is a schematic diagram of the architecture of a process orchestration method provided in an embodiment of this specification;

[0023] Figure 2 It is a flowchart of a process arrangement method provided in an embodiment of this specification;

[0024] Figure 3 It is a structural diagram of a process arrangement information provided by an embodiment of this specification;

[0025] Figure 4 It is a flowchart of implementing information of a determination process provided by an embodiment of this specification;

[0026] Figure 5 It is a flowchart of a process arrangement method provided in an embodiment of this specification;

[0027] Figure 6 It is a flowchart of a process arrangement method provided in an embodiment of this specification;

[0028] Figure 7 It is a flowchart of a process arrangement method provided in an embodiment of this specification;

[0029] Figure 8It is a structural diagram of a process arrangement device provided in an embodiment of this specification;

[0030] Fig. 9 It is a structural schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0032] In the description of this specification, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In the description of this specification, it should be noted that, unless otherwise clearly specified and limited, "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. For those of ordinary skill in the art, the specific meanings of the above terms in this specification can be understood in specific circumstances. In addition, in the description of this specification, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are an "or" relationship.

[0033] The present specification is described in detail below with reference to specific embodiments.

[0034] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of this specification are all 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 relevant countries and regions. For example, the features, information and data involved in this specification are all obtained with full authorization.

[0035] Institutions such as consumer finance institutions, e-commerce institutions, and logistics institutions are facing increasing demands from the transaction side, and there are constantly new things and new products waiting for the institutions to process. From the system side, the systems of each institution need to use a set of highly versatile process orchestration systems to orchestrate the entire process of product processing, especially new products, so as to reduce the cost of understanding product processing for users.

[0036] For example, a credit processing process suitable for processing credit products is compiled, which includes common pre-loan process, loan process and post-loan process. Even if credit products have different characteristics and requirements at different times, such as consumer loans, corporate loans, car loans, mortgages, etc., each product may have different approval standards, risk control requirements, repayment methods, etc., the credit process orchestration system can compile a set of processes that are as close to the processing process of different products as possible according to the needs of different products, so that users can understand and use them.

[0037] However, existing process orchestration methods are often accompanied by a large amount of manual intervention. For example, process nodes such as product entry processes and risk control processes require manual orchestration, which is time-consuming and labor-intensive, and has low accuracy.

[0038] like Figure 1 As shown, Figure 1 It is a schematic diagram of the architecture of a process orchestration method provided in an embodiment of this specification. Figure 1 The system shown includes at least a plurality of electronic devices and a server 101, and the plurality of electronic devices includes at least an electronic device 1011, an electronic device 1012, and an electronic device 1013. It can be understood that Figure 1 The number of servers and electronic devices shown in the figure is for illustration only, and this specification does not impose any limitation on this.

[0039] In the embodiments of this specification, the electronic device refers to a device that sends an initial text or a request to view process orchestration information to the server 101, and the server 101 refers to a server device that executes the process orchestration method.

[0040] Server 101 is a plurality of physical servers, and the plurality of physical servers are independent in hardware. Alternatively, server 101 is a plurality of virtual servers, and the plurality of virtual servers are deployed in the same hardware resource pool, and the deployment methods of the virtual servers include but are not limited to: VMware, Virtual Box and Virtual PC. It is understandable that server 101 also has other service capabilities and functions to complete the tasks in the following embodiments. For example, server 101 also provides portal services, resource management services, and CI / CD services.

[0041] Electronic devices such as electronic device 1021, electronic device 1022 and electronic device 1023 include but are not limited to physical or virtual processors, mobile stations (Mobile Station, MS), mobile terminal equipment (Mobile Terminal), mobile phones (Mobile Telephone), handsets and portable equipment (portable equipment), Bluetooth headsets, smart watches and other types. The electronic devices can communicate with one or more core networks via a radio access network (Radio Access Network, RAN).

[0042] Electronic devices 1021, 1022, 1023, etc. may be equipped with display devices, and the display devices may be various devices capable of realizing display functions, for example, the display devices may be cathode ray tube display (CR), light-emitting diode display (LED), electronic ink screen, liquid crystal display (LCD), plasma display panel (PDP), etc. For example, a user may use the display device on the electronic device 1021 to view the process arrangement information sent by the server 101.

[0043] Multiple electronic devices and the server 101 can communicate through a communication link established by a communication protocol, such as the gRPC protocol, which is a high-performance, general-purpose open source remote processor call (RPC) framework, which is mainly designed for mobile application development and based on the HTTP / 2 protocol standard, based on the protocol buffer (PB) serialization protocol development, and supports many development languages. In addition, the communication link can also be a wireless communication link or a wired communication link, for example: a wired communication link includes an optical fiber, a twisted pair or a coaxial cable, and a wireless communication link includes a Bluetooth communication link, a wireless fidelity (WIreless-FIdelity, Wi-Fi) communication link or a microwave communication link, etc.

[0044] based on Figure 1 The architecture shown, such as Figure 2 As shown, it is a flowchart of a process scheduling method provided by an embodiment of this specification. The method can be implemented by a computer program and can be run on a process scheduling device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application.

[0045] Specifically, the process orchestration method includes:

[0046] S102: Acquire initial text whose content is related to product processing.

[0047] The specific content of the initial text is related to the processing of a certain product. For example, if the product is a credit product, the source of the initial text may be from a financial institution, bank, loan company, etc. The name of the initial text may be "Product Review Document" or "Product Manual". The specific content of the initial text may be an introduction to the characteristics of the credit product, application method, application steps, interest rate, fees, applicable conditions, repayment method and plan, risks and other information.

[0048] The method for obtaining the initial text may be to receive the initial text sent from other electronic devices, for example, Figure 1 The initial text is shown as sent by the electronic device 1021. Another method for obtaining the initial text is to obtain it from the log data of the server 101, or any other acquisition method.

[0049] In one embodiment, after obtaining the initial text whose content is related to product processing, the initial text is preprocessed, so that subsequent process arrangement processing is performed based on the preprocessed initial text. The step of preprocessing the initial text includes at least one or more of the following steps: cleaning data, removing noise, such as HTML tags, special characters, repeated content, etc.; standardization: including lowercase, removing stop words, processing spelling errors, etc.; removing stop words, deleting high-frequency words that do not contribute to the analysis; processing outliers: such as removing text that is too long or too short, filtering out garbled characters, etc. The method of preprocessing the initial text may also include a method, and the embodiments of this specification do not impose any restrictions on this.

[0050] S104, multiple processes for processing the product in the initial text, and texts corresponding to the multiple processes.

[0051] Understand the specific content of the initial text, perform information extraction (IE) on the initial text, extract multiple processes for processing the product in the initial text, and each process corresponds to a certain part of the processing steps in the complete processing of the product. Further, determine the text related to each process in the initial text based on the multiple processes, and the text corresponding to each process includes multiple text information from the initial text.

[0052] For example, understand the specific content of the initial text and extract multiple processes for processing the product in the initial text. The product is a credit product. The multiple processes for processing the product include at least: product analysis process, agreement analysis process, pre-loan process, mid-loan process and post-loan process. The product analysis process corresponds to the product analysis text, the agreement analysis process corresponds to the agreement analysis text, the pre-loan process corresponds to the pre-loan process text, the mid-loan process corresponds to the mid-loan process text, and the post-loan process corresponds to the post-loan process text.

[0053] like Figure 3 As shown, Figure 3 It is a structural diagram of a process arrangement information provided in an embodiment of this specification. According to the specific content of the initial text 201, three processes including at least the pre-loan process 2021, the loan process 2022, and the post-loan process 2023 are extracted, and the texts corresponding to the pre-loan process 2021, the loan process 2022, and the post-loan process 2023 are determined from the initial text 201.

[0054] In this embodiment, multiple processes for processing products in the initial text can be processed by rule-based text processing (Rule-based Extraction), and the rules can be set according to regular expressions, keywords, grammatical structures, etc. Specifically, different keywords or phrases are set according to multiple processes. For example, the keywords corresponding to the process of applying for the use of the product are "application conditions", "loan amount", "application process", etc., and specific texts are further matched in the initial text by regular expressions to determine the process corresponding to the keyword and the text corresponding to the process. After the process of applying for the use of the product is extracted, the values ​​related to "minimum amount" and "maximum amount" are matched according to the regular expression as the text corresponding to the process.

[0055] S106. According to the text corresponding to the process, determine the hardware interface information and service protocol information required to implement the process, and obtain the implementation information of the process.

[0056] Hardware interface information and service protocol information are key technical components used to achieve interaction and integration between the system and hardware and external services, and define the communication interface between the hardware layer and the software, as well as the contract between the product provider and the product consumer. Specifically, hardware interface information may include a set of standardized interfaces that define how to programmatically access the functions of the hardware device of the server that serves as a product provider or service provider, obtain the status information of the server, or control the server to perform specific tasks, in order to achieve interaction between product consumers and product providers. Service protocol information is an agreement between a service provider and a service consumer, used to complete the provision of services or products, and the consumption of services or products based on different protocols.

[0057] In one embodiment, the hardware interface information includes at least one application program interface and interface information of the application program interface, and the service protocol information includes at least one service provider interface related to the application program interface and interface information of the service provider interface.

[0058] Specifically, the hardware interface information includes at least one application program interface (API), which is used to control or access hardware functions through programming language calls. The application program interface (API) may include an application program interface of a system that is a product provider, such as a product management system or a process orchestration system set up on a server. The application program interface (API) may also include an application program interface of a system that is a product consumer, such as a product consumption system set up on an electronic device. The interface information of the application program interface, which describes the specific details of the application program interface (API), such as parameter types, return values, etc.

[0059] The service agreement information includes at least one service provider interface SPI, and one application program interface API corresponds to at least one service provider interface SPI, which can be understood as how to implement the functions defined by the above application program interface API through the service provider interface SPI. In other words, the service provider interface SPI is a specific way to implement the application program interface API function, which defines a series of rules and standards that service providers must follow.

[0060] The API defines what can be done, while at least one SPI specifies how to implement the API's functions. For example, in a smart home system, the API defines how to set the room temperature, while the specific implementation (such as which communication protocol to use, how to parse data, etc.) is completed through at least one SPI.

[0061] For example, a weather forecast product is introduced into the smart home system, and the application programming interface API used by the smart home system to call weather queries is used. The interface information of the service provider interface SPI corresponding to the application programming interface API will specifically describe what types of parameters (such as geographic location strings) are received based on the application programming interface API method, what data structure is returned (possibly a weather report in JSON format), and how to handle request failures (such as network errors).

[0062] like Figure 3 As shown, Figure 3 The pre-loan process 2021, the mid-loan process 2022, and the post-loan process 2023 correspond to the hardware interface information including the application program interface API and the service protocol information including the service provider interface SPI.

[0063] Specifically, the implementation information corresponding to the pre-loan process 2021 includes the application programming interface API and the service agreement information of activation SPI and credit SPI; the implementation information corresponding to the mid-loan process 2022 includes the application programming interface API and the service agreement information of expenditure SPI and loan release SPI; the implementation information corresponding to the pre-loan process 2023 includes the application programming interface API and the service agreement information of account entry SPI and repayment SPI.

[0064] In this embodiment, the hardware interface information and service protocol information required to implement the process are determined according to the text corresponding to the process. Figure 4 As shown, Figure 4 It is a flow chart of a process implementation information for determining a process provided by an embodiment of this specification. Taking the loan process 2022 as an example, in a system for providing products and product-related services such as a product processing system or a process scheduling system or a service provision system, according to the text corresponding to the loan process 2022, the hardware interface information required for implementing the product processing corresponding to the loan process 2022 is determined, including the expenditure approval API set in the above system. The expenditure approval API generally refers to a programming interface for processing fund expenditure applications and approval processes.

[0065] Furthermore, based on the expenditure approval API, according to the text information related to the expenditure approval in the text of the loan process 2022, the required expenditure trial SPI is determined in the system including multiple expenditure trial SPIs for implementing the expenditure approval API. The specific descriptions of the multiple expenditure approval SPIs are different, that is, the versions of the multiple expenditure approval SPIs are different.

[0066] For example, the description of the expenditure approval SPI-version 1 includes: this version will not create a loan contract, and when the quota is occupied, it will only decide whether to occupy the fixed quota or the temporary quota; if the approval fails, it will be rejected immediately and will not be retried. The description of the expenditure approval SPI-version 2 includes: this version will create a loan contract, and when the quota is occupied, it will decide whether to occupy the fixed quota, temporary quota, special quota, and medium and large temporary quota; if the approval fails, it will not be rejected immediately and will be retried. Based on the text information related to expenditure approval in the text of the loan process 2022, the expenditure approval SPI of the version required to implement the loan process 2022 is determined in multiple expenditure approval SPIs.

[0067] Based on the above steps, the implementation information corresponding to the loan process 2022 is determined to include: Figure 4 The hardware interface information and service protocol information are shown.

[0068] S108. Visualize the multiple processes and the implementation information corresponding to the multiple processes to obtain process arrangement information for indicating processing of the product.

[0069] Visual processing is performed based on multiple processes and the implementation information corresponding to the multiple processes, so as to obtain process arrangement information including data in the form of graphics and / or tables and / or text. The process arrangement information facilitates users to understand how to completely process the product, understand the multiple processes included in the process of processing the product and the hardware interface information and service protocol information required to implement each process.

[0070] In an embodiment of the present specification, based on the initial text, multiple processes for processing a product in the initial text, and the texts corresponding to the multiple processes are extracted. Further, based on the text corresponding to each process, the hardware interface information and service protocol information required to implement the process are determined, and the hardware interface information and service protocol information are used to indicate that the system completes the processing for the product corresponding to the process node based on at least one hardware interface and at least one service protocol. Further, the hardware interface information and service protocol information corresponding to the multiple processes and the multiple processes are visualized to obtain process orchestration information for indicating the complete processing of the product. Therefore, the embodiment of the present specification can realize efficient and automatic process orchestration based on the process orchestration method, and the obtained process orchestration information can be a visual report in the form of a chart. Through the visual report, the user can quickly understand the multiple processes for complete processing of the product, as well as the hardware interface information and service protocol information required for each process.

[0071] like Figure 5 As shown, it is a flowchart of a process scheduling method provided by an embodiment of this specification. The method can be implemented by a computer program and can be run on a process scheduling device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application.

[0072] Specifically, the process orchestration method includes:

[0073] S202: Acquire initial text whose content is related to product processing.

[0074] See the above S102, which will not be described again here.

[0075] S204: extracting multiple processes for processing the product from the initial text, and the texts corresponding to the multiple processes.

[0076] See the above S104, which will not be repeated here.

[0077] S206. According to the field to which the process belongs, match a processing model corresponding to the process from a plurality of preset natural language processing models belonging to different fields.

[0078] Natural language processing (NLP) models are computer models that can understand, generate, analyze, and process human language. The main task of natural language processing (NLP) models is to convert text into a machine-understandable form and perform various language tasks, such as text classification, entity recognition, sentiment analysis, machine translation, etc.

[0079] In this embodiment, the natural language processing model can be one of the following models: statistical models, such as hidden Markov models, support vector machines, etc., which model language based on statistical laws and are widely used in early NLP tasks; models based on deep learning, such as RNN, LSTM, Transformer, etc. The rapid development of deep learning in recent years has made neural network-based NLP models mainstream, which can better capture long-term dependencies and semantic information in language; pre-trained models, such as BERT, GPT, T5, etc., are models pre-trained through large-scale corpora, which can understand various language phenomena and have strong migration capabilities, and are widely used in different NLP tasks.

[0080] In this embodiment, multiple natural language processing models belonging to different fields are trained, and the natural language processing modules in each field are used to process text in that field. Figure 6 As shown, Figure 6 It is a flowchart of a process arrangement method provided in the embodiment of this specification. In this embodiment, the product analysis model 3031, the risk assessment model 3022, the contract signing and issuance model 3033, the credit management model 3034, the post-loan monitoring model 3035 and the settlement model 3026 are obtained through pre-training. It can be understood that Figure 6 The number of process models shown is merely an example, and the types of process models may not be exactly the same.

[0081] According to the field to which the process belongs, for example, the process belongs to the pre-loan process field, or the process belongs to the mid-loan process field, a processing model corresponding to the process is matched in a plurality of preset natural language processing models belonging to different fields. For example, the processing model matched by process 3021 is risk assessment module 3032, the processing model matched by process 3022 is credit management model 3034, and the processing model matched by process 3023 is post-loan monitoring model 3035.

[0082] S208. Process the text corresponding to the process through the processing model corresponding to the process, determine the hardware interface information and service protocol information required to implement the process, and obtain the implementation information of the process.

[0083] In one embodiment, descriptive information representing the specific processing process of the process is extracted from the text corresponding to the process through the processing model corresponding to the process; matching is performed among multiple preset hardware interfaces and multiple service protocol information based on the descriptive information to determine at least one target hardware interface and at least one target service protocol whose matching degree meets the matching conditions; hardware interface information corresponding to at least one target hardware interface and service protocol information corresponding to at least one target service protocol are obtained to obtain implementation information of the process.

[0084] The descriptive information representing the specific processing process of the flow may include the sequence of steps, operation objects, processing conditions, etc. According to the descriptive information, matching is performed among the preset multiple hardware interface information and multiple service protocols. The descriptive information may be vectorized through a processing model to obtain vector data corresponding to the descriptive information, and then matched among the vector data corresponding to the preset multiple hardware interfaces and the vector data corresponding to the multiple service protocols to obtain at least one target hardware interface and at least one target service protocol whose cosine similarity between the vectors meets the preset conditions. The vector data corresponding to the hardware interface can be understood as the vector data corresponding to the description information of the hardware interface API, and the vector data corresponding to the service protocol can be understood as the vector data corresponding to the description information of the service provider interface SPI.

[0085] In this embodiment, by respectively processing the texts corresponding to multiple processes through multiple processing models, the efficiency of matching the corresponding implementation information for each process can be improved, and each processing model can be fine-tuned based on the text in this field to improve the accuracy of matching the corresponding implementation information for each process.

[0086] In one embodiment, the preset multiple natural language processing models are created by a process management system for processing products. The initial description information representing the specific processing process of the process is extracted from the text corresponding to the process through the processing model corresponding to the process, and the version of the initial description information is converted into a version that conforms to the process management system to obtain the description information.

[0087] In this embodiment, the process management system for handling products works in collaboration with multi-agent agents (Multi-Agent Collaboration), which is a collaborative concept involving multiple agents. These agents can be people or computer programs, and they achieve common goals through communication and information sharing.

[0088] Each intelligent agent is provided with a processing model, and the processing model is fine-tuned based on at least 7B parameters, so that the processing model can accurately understand the text information in the process field, and can be connected with the process management system to create multiple versions of processing models corresponding to the process management system.

[0089] Multiple versions of processing models can extract initial description information that characterizes the specific processing process of the process from the text corresponding to the process, and convert the version of the initial description information into a version that conforms to the process management system to obtain description information, and then further match the description information among multiple preset hardware interfaces and multiple service protocols to obtain the implementation information corresponding to the process.

[0090] For example, the text corresponding to the product analysis process is sent to an intelligent agent equipped with a product analysis model. The intelligent agent receives the text and extracts the initial descriptive information characterizing the product in the text through the product analysis model, including: a first-level product code or a second-level product code or a third-level product code, CSSU or FSSU or a credit product code or a loan product code. Based on the requirements of the process management system, the above different versions of the initial description information are converted into a version that complies with the process management system to obtain the description information, that is, convert it into a standard request to the process management system to create a product code, and call the process management system to create it.

[0091] S210: Visualize the multiple processes and the implementation information corresponding to the multiple processes to obtain process arrangement information for indicating processing of the product.

[0092] See the above S106, which will not be described again here.

[0093] In an embodiment of the present specification, based on the initial text, multiple processes for processing a product in the initial text, and the texts corresponding to the multiple processes are extracted. Further, based on the text corresponding to each process, the hardware interface information and service protocol information required to implement the process are determined, and the hardware interface information and service protocol information are used to indicate that the system completes the processing for the product corresponding to the process node based on at least one hardware interface and at least one service protocol. Further, the hardware interface information and service protocol information corresponding to the multiple processes and the multiple processes are visualized to obtain process orchestration information for indicating the complete processing of the product. Therefore, the embodiment of the present specification can realize efficient and automatic process orchestration based on the process orchestration method, and the obtained process orchestration information can be a visual report in the form of a chart. Through the visual report, the user can quickly understand the multiple processes for complete processing of the product, as well as the hardware interface information and service protocol information required for each process.

[0094] like Figure 7 As shown, it is a flowchart of a process scheduling method provided by an embodiment of this specification. The method can be implemented by a computer program and can be run on a process scheduling device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application.

[0095] Specifically, the process orchestration method includes:

[0096] S302: Acquire initial text whose content is related to product processing.

[0097] See the above S102, which will not be described again here.

[0098] S304: extract multiple processes for processing the product from the initial text through a large-scale pre-trained model, and segment the initial text to obtain texts corresponding to the multiple processes.

[0099] Large Pre-trained Models refer to deep learning models that have been trained with large-scale data sets and can play a powerful role in multiple natural language processing (NLP) tasks. These models usually use a large amount of text data and are trained through self-supervised learning methods, so that they can generate meaningful text representations and then be applied to various NLP tasks, such as text classification, sentiment analysis, named entity recognition, machine translation, etc.

[0100] In this embodiment, COT, self-consistency and other prompt engineering methods are used to understand the semantics of the initial text through a large-scale pre-trained model, extract multiple processes for processing the product in the initial text, and segment the initial text to obtain the text corresponding to each process.

[0101] The COT method emphasizes helping the model reason step by step by refining the steps. This method is suitable for extracting information from multiple and complex processes included in product processing, and can help large-scale pre-trained models break down abstract product processing into small, easy-to-understand processes, thereby building multiple structured processes.

[0102] The self-consistency method can improve the accuracy of the results by reasoning about the same question multiple times and comparing multiple answers. It can compensate for the possible deviations of large-scale pre-trained models and ensure that the multiple processes extracted from the initial text and the text corresponding to each process are more consistent and reliable.

[0103] Taking the pre-loan process as an example, the pre-loan process involves application, approval, risk control assessment and other links. According to the prompt work, the prompt text is constructed, and the prompt text includes sample text information related to the pre-loan process. The constructed prompt text and the initial text are input into the large-scale pre-training model, and the COT method is used to gradually derive the detailed steps of the pre-loan process, such as user application, submission of materials, and material approval. Finally, the pre-loan process included in the initial text and the text corresponding to the pre-loan process are extracted.

[0104] In one embodiment, a large-scale pre-trained model is fine-tuned with prompt words based on a prompt word template to obtain a target prompt word, which is used to prompt the large-scale pre-trained model to extract multiple processes included in the sample text; the target prompt word is used to instruct the large-scale pre-trained model to extract multiple processes for processing the product in the initial text, and to segment the initial text to obtain texts corresponding to the multiple processes.

[0105] The goal of cue word fine-tuning is to instruct the large-scale pre-trained model to extract multiple processes from the sample text. The cue word template refers to the input format used to guide the large-scale pre-trained model to perform reasoning. These templates need to be clear and unambiguous to help the large-scale pre-trained model understand and extract multiple processes and the text corresponding to each process from the initial text.

[0106] Specifically, using the prompt word template and sample texts with multiple processes annotated, the sample texts and the expected output process data are organized into a data format suitable for fine-tuning. The format of [input text] + [target process] is usually used as training data. The large-scale pre-trained model is fine-tuned with the training data to obtain the target prompt word.

[0107] Prompt tuning is the process of optimizing the input prompt words for the large-scale pre-trained model, aiming to improve the performance and output quality of the large-scale pre-trained model. This embodiment can make the large-scale pre-trained model better understand the initial text to generate multiple processes and segment the initial text to obtain the text corresponding to each process by refining and adjusting the prompt words.

[0108] S306. According to the field to which the process belongs, a processing model corresponding to the process is matched among a plurality of preset natural language processing models belonging to different fields.

[0109] See the above S206, which will not be described again here.

[0110] S308. Process the text corresponding to the process through the processing model corresponding to the process, determine the hardware interface information and service protocol information required to implement the process, and obtain the implementation information of the process.

[0111] See the above S208, which will not be repeated here.

[0112] S310: Visualize multiple processes and implementation information corresponding to the multiple processes to obtain process arrangement information for indicating processing of the product.

[0113] See the above S310, which will not be described again here.

[0114] In one embodiment, multiple processes are sorted based on the processing order for processing products, and visual description data is added at the location of the process according to the implementation information of the process, so as to obtain a process arrangement report for indicating the processing of the product.

[0115] The processing order of the product is determined according to the product processing logic and transaction requirements to sort multiple processes, and there is a dependency relationship between multiple processes, so as to obtain the execution order of each process. The execution order of multiple processes is further characterized by identification such as directionality.

[0116] Furthermore, visual description data is added at the location of the process according to the implementation information of the process. For example, a short label is added to each process node to explain at least one hardware interface and at least one service provider interface required for the process. For another example, comments and descriptions are added to the process nodes to explain key steps or complex logic. In this embodiment, different types of processes can also be distinguished by using different icons and colors.

[0117] The process arrangement report is used to indicate the process of processing the product. The process arrangement report includes a table, a list or a combination of text and graphics to ensure that the report format is clear and easy to read.

[0118] In one embodiment, a plurality of processes and implementation information corresponding to the plurality of processes are visualized to obtain initial process orchestration information for indicating processing of a product; at least one correction instruction from a user is received, and at least one target process and / or implementation information of the target process in the initial process orchestration information is corrected in response to the at least one correction instruction to obtain process orchestration information.

[0119] In this embodiment, a user-friendly interface can be provided to allow the user to submit a correction instruction, which can be a web form, email, a dedicated application or any other suitable communication channel. Further, the corresponding part of the initial process arrangement information is modified according to the user's correction instruction, including at least one target process and / or the implementation information of the target process, specifically including: adding / deleting a target process, adding a new target process or removing a target process that is no longer needed; adjusting the connection line, changing the direction or order of the target process; updating the implementation information of the target process, modifying the implementation information related to the target process, including hardware interface information and service protocol information, etc.

[0120] In this embodiment, receiving the user's correction instruction and making corresponding adjustments to the initial process orchestration information are key steps to ensure the accuracy and effectiveness of the process orchestration.

[0121] In an embodiment of the present specification, based on the initial text, multiple processes for processing a product in the initial text, and the texts corresponding to the multiple processes are extracted. Further, based on the text corresponding to each process, the hardware interface information and service protocol information required to implement the process are determined, and the hardware interface information and service protocol information are used to indicate that the system completes the processing for the product corresponding to the process node based on at least one hardware interface and at least one service protocol. Further, the hardware interface information and service protocol information corresponding to the multiple processes and the multiple processes are visualized to obtain process orchestration information for indicating the complete processing of the product. Therefore, the embodiment of the present specification can realize efficient and automatic process orchestration based on the process orchestration method, and the obtained process orchestration information can be a visual report in the form of a chart. Through the visual report, the user can quickly understand the multiple processes for complete processing of the product, as well as the hardware interface information and service protocol information required for each process.

[0122] The following are device embodiments of this specification, which can be used to implement the method embodiments of this specification. For details not disclosed in the device embodiments of this specification, please refer to the method embodiments of this specification.

[0123] See also Fig. 9 , which shows a schematic diagram of the structure of a process orchestration device provided by an exemplary embodiment of this specification. The system at least includes a sending end device and a receiving end device, and the device is suitable for being set on a sending end device in which a sending end proxy service is deployed in the system. The process orchestration device can be implemented as all or part of the device through software, hardware or a combination of both. The process orchestration device includes a text acquisition module 401, a process extraction module 402, an information determination module 403 and a process orchestration module 404.

[0124] A text acquisition module 401 is used to acquire an initial text whose content is related to product processing;

[0125] A process extraction module 402 is used to extract multiple processes for processing the product from the initial text, and texts corresponding to the multiple processes;

[0126] An information determination module 403 is used to determine the hardware interface information and service protocol information required to implement the process according to the text corresponding to the process, and obtain the implementation information of the process;

[0127] The process arrangement module 404 is used to visualize the multiple processes and the implementation information corresponding to the multiple processes, and obtain process arrangement information for indicating the processing of the product.

[0128] In one embodiment, the information determination module 403 includes:

[0129] A model matching unit, configured to match a processing model corresponding to the process from a plurality of preset natural language processing models belonging to different fields, according to the field to which the process belongs;

[0130] The information matching unit is used to process the text corresponding to the process through the processing model corresponding to the process, determine the hardware interface information and service protocol information required to implement the process, and obtain the implementation information of the process.

[0131] In one embodiment, the information matching unit includes:

[0132] A first matching subunit is used to extract descriptive information representing a specific processing process of the process from the text corresponding to the process through a processing model corresponding to the process;

[0133] A second matching subunit is used to match among a plurality of preset hardware interfaces and a plurality of service protocols according to the description information, and determine at least one target hardware interface and at least one target service protocol whose matching degree meets the matching condition;

[0134] The third matching subunit is used to obtain hardware interface information corresponding to the at least one target hardware interface and service protocol information corresponding to the at least one target service protocol, so as to obtain implementation information of the process.

[0135] In one embodiment, the plurality of preset natural language processing models are created by a process management system for processing the product;

[0136] The first matching subunit is specifically used to extract initial description information representing the specific processing process of the process from the text corresponding to the process through the processing model corresponding to the process, and convert the version of the initial description information into a version that conforms to the process management system to obtain description information.

[0137] In one embodiment, the hardware interface information includes at least one application program interface and interface information of the application program interface, and the service protocol information includes at least one service provider interface related to the application program interface and interface information of the service provider interface.

[0138] In one embodiment, the process extraction module 402 includes:

[0139] An extraction and segmentation unit is used to extract multiple processes for processing the product from the initial text through a large-scale pre-trained model, and segment the initial text to obtain texts corresponding to the multiple processes.

[0140] In one embodiment, the process prompt module 402 further includes:

[0141] A prompt word fine-tuning unit, used for fine-tuning the prompt word on the large-scale pre-trained model based on the prompt word template to obtain a target prompt word, wherein the target prompt word is used to prompt the large-scale pre-trained model to extract a plurality of processes including the sample text;

[0142] Extract the segmentation unit, including:

[0143] The extraction and segmentation subunit is used to instruct the large-scale pre-trained model to extract multiple processes for processing the product in the initial text through the target prompt word, and to segment the initial text to obtain texts corresponding to the multiple processes respectively.

[0144] In one embodiment, the process orchestration module 404 includes:

[0145] A visualization processing unit is used to sort the multiple processes based on the processing order for processing the product, and to add visualization description data at the location of the process according to the implementation information of the process, so as to obtain a process arrangement report for indicating the processing of the product.

[0146] In one embodiment, the process orchestration module 404 includes:

[0147] A first correction unit is used to perform visualization processing on the multiple processes and the implementation information respectively corresponding to the multiple processes to obtain initial process arrangement information for indicating processing of the product;

[0148] The second correction unit is used to receive at least one correction instruction from the user, and correct at least one target process in the initial process scheduling information and / or the implementation information of the target process in response to the at least one correction instruction to obtain the process scheduling information.

[0149] In an embodiment of the present specification, based on the initial text, multiple processes for processing a product in the initial text, and the texts corresponding to the multiple processes are extracted. Further, based on the text corresponding to each process, the hardware interface information and service protocol information required to implement the process are determined, and the hardware interface information and service protocol information are used to indicate that the system completes the processing for the product corresponding to the process node based on at least one hardware interface and at least one service protocol. Further, the hardware interface information and service protocol information corresponding to the multiple processes and the multiple processes are visualized to obtain process orchestration information for indicating the complete processing of the product. Therefore, the embodiment of the present specification can realize efficient and automatic process orchestration based on the process orchestration method, and the obtained process orchestration information can be a visual report in the form of a chart. Through the visual report, the user can quickly understand the multiple processes for complete processing of the product, as well as the hardware interface information and service protocol information required for each process.

[0150] It should be noted that the process orchestration device provided in the above embodiment only uses the division of the above functional modules as an example when executing the process orchestration method. In actual applications, the above functional distribution can be completed by different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the process orchestration device provided in the above embodiment and the process orchestration method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0151] The serial numbers of the embodiments of this specification are for description only and do not represent the advantages or disadvantages of the embodiments.

[0152] The present specification also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor as described above. Figure 1 - Figure 7 The process arrangement method of the embodiment shown in the figure can be found in the specific execution process. Figure 1 - Figure 8 The specific description of the illustrated embodiment will not be repeated here.

[0153] The present specification also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor as described above. Figure 1 - Figure 7 The process arrangement method of the embodiment shown in the figure can be found in the specific execution process. Figure 1 - Figure 7 The specific description of the illustrated embodiment will not be repeated here.

[0154] See also Fig. 9 , is a schematic diagram of the structure of an electronic device provided in the embodiment of this specification. Fig. 9 As shown, the electronic device 500 may include: at least one processor 501 , at least one network interface 504 , a user interface 503 , a memory 505 , and at least one communication bus 502 .

[0155] The communication bus 502 is used to realize the connection and communication between these components.

[0156] The user interface 503 may include a display screen (Display) and a camera (Camera), and the optional user interface 503 may also include a standard wired interface and a wireless interface.

[0157] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0158] Among them, the processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts within the entire server 500, and executes various functions and processes data of the server 500 by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 501 can integrate one or more combinations of processors (Central Processing Unit, CPU), image processors (Graphics Processing Unit, GPU) and modems. Among them, the CPU mainly processes operating systems, user interfaces, and applications; the GPU is responsible for rendering and drawing the content that needs to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 501, and it can be implemented separately through a chip.

[0159] Among them, the memory 505 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 505 may also be optionally at least one storage device located away from the aforementioned processor 501. As Fig. 9 As shown, the memory 505 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a process orchestration application.

[0160] exist Fig. 9In the electronic device 500 shown, the user interface 503 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 501 can be used to call the process scheduling application stored in the memory 505 and specifically perform the following operations:

[0161] Get the initial text with content related to product processing;

[0162] Extracting multiple processes for processing the product from the initial text, and texts corresponding to the multiple processes;

[0163] According to the text corresponding to the process, determine the hardware interface information and service protocol information required to implement the process, and obtain the implementation information of the process;

[0164] Visual processing is performed on the multiple processes and the implementation information respectively corresponding to the multiple processes to obtain process arrangement information for indicating processing of the product.

[0165] In one embodiment, the processor 501 executes the text corresponding to each of the processes, determines the hardware interface information and service protocol information required to implement the process, obtains the implementation information of the process, and specifically performs:

[0166] According to the field to which the process belongs, matching a processing model corresponding to the process from a plurality of preset natural language processing models belonging to different fields;

[0167] The text corresponding to the process is processed by the processing model corresponding to the process, the hardware interface information and service protocol information required to implement the process are determined, and the implementation information of the process is obtained.

[0168] In one embodiment, the processor 501 processes the text corresponding to the process through the processing model corresponding to the process, determines the hardware interface information and service protocol information required to implement the process, obtains the implementation information of the process, and specifically performs:

[0169] Extracting descriptive information representing a specific processing process of the process from the text corresponding to the process through the processing model corresponding to the process;

[0170] Matching among a plurality of preset hardware interfaces and a plurality of service protocols according to the description information, and determining at least one target hardware interface and at least one target service protocol whose matching degree satisfies a matching condition;

[0171] The hardware interface information corresponding to the at least one target hardware interface and the service protocol information corresponding to the at least one target service protocol are acquired to obtain implementation information of the process.

[0172] In one embodiment, the plurality of preset natural language processing models are created by a process management system for processing the product;

[0173] The processor 501 executes the processing model corresponding to the process, extracts description information representing the specific processing process of the process from the text corresponding to the process, and specifically performs:

[0174] By using the processing model corresponding to the process, initial description information representing the specific processing process of the process is extracted from the text corresponding to the process, and the version of the initial description information is converted into a version that complies with the process management system to obtain description information.

[0175] In one embodiment, the hardware interface information includes at least one application program interface and interface information of the application program interface, and the service protocol information includes at least one service provider interface related to the application program interface and interface information of the service provider interface.

[0176] In one embodiment, the processor 501 executes the extraction of multiple processes for processing the product in the initial text, and the texts corresponding to the multiple processes, specifically performing:

[0177] A large-scale pre-trained model is used to extract multiple processes for processing the product from the initial text, and the initial text is segmented to obtain texts corresponding to the multiple processes.

[0178] In one embodiment, before the processor 501 executes the steps of extracting multiple processes for processing the product from the initial text by using a large-scale pre-trained model and segmenting the initial text to obtain texts corresponding to the multiple processes, the processor 501 further executes:

[0179] Perform prompt word fine-tuning training on the large-scale pre-trained model based on the prompt word template to obtain target prompt words, wherein the target prompt words are used to prompt the large-scale pre-trained model to extract multiple processes including sample text;

[0180] The processor 501 executes the extraction of multiple processes for processing the product from the initial text through the large-scale pre-trained model, and segmenting the initial text to obtain texts corresponding to the multiple processes, including:

[0181] The target prompt word is used to instruct the large-scale pre-trained model to extract multiple processes for processing the product from the initial text, and to segment the initial text to obtain texts corresponding to the multiple processes.

[0182] In one embodiment, the processor 501 performs the visualization processing of the multiple processes and the implementation information respectively corresponding to the multiple processes to obtain the process arrangement information for indicating the processing of the product, specifically performing:

[0183] The multiple processes are sorted based on the processing order for processing the product, and visual description data is added at the location of the process according to the implementation information of the process, so as to obtain a process arrangement report for indicating the processing of the product.

[0184] In one embodiment, the processor 501 performs the visualization processing of the multiple processes and the implementation information respectively corresponding to the multiple processes to obtain the process arrangement information for indicating the processing of the product, specifically performing:

[0185] Visualizing the multiple processes and the implementation information respectively corresponding to the multiple processes to obtain initial process arrangement information for indicating processing of the product;

[0186] At least one correction instruction is received from a user, and in response to the at least one correction instruction, at least one target process in the initial process choreography information and / or the implementation information of the target process is corrected to obtain the process choreography information.

[0187] In an embodiment of the present specification, based on the initial text, multiple processes for processing a product in the initial text, and the texts corresponding to the multiple processes are extracted. Further, based on the text corresponding to each process, the hardware interface information and service protocol information required to implement the process are determined, and the hardware interface information and service protocol information are used to indicate that the system completes the processing for the product corresponding to the process node based on at least one hardware interface and at least one service protocol. Further, the hardware interface information and service protocol information corresponding to the multiple processes and the multiple processes are visualized to obtain process orchestration information for indicating the complete processing of the product. Therefore, the embodiment of the present specification can realize efficient and automatic process orchestration based on the process orchestration method, and the obtained process orchestration information can be a visual report in the form of a chart. Through the visual report, the user can quickly understand the multiple processes for complete processing of the product, as well as the hardware interface information and service protocol information required for each process.

[0188] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0189] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0190] The above disclosure is only the preferred embodiment of this specification, which certainly cannot be used to limit the scope of rights of this specification. Therefore, equivalent changes made according to the claims of this specification are still within the scope covered by this specification.

Claims

1. A process scheduling method, the method comprising: Get the initial text with content related to product processing; Extracting multiple processes for processing the product from the initial text, and texts corresponding to the multiple processes; According to the text corresponding to the process, determine the hardware interface information and service protocol information required to implement the process, and obtain the implementation information of the process; Visual processing is performed on the multiple processes and the implementation information respectively corresponding to the multiple processes to obtain process arrangement information for indicating processing of the product.

2. The process arrangement method according to claim 1, wherein the step of determining the hardware interface information and service protocol information required to implement the process according to the text corresponding to each process, and obtaining the implementation information of the process comprises: According to the field to which the process belongs, matching a processing model corresponding to the process from a plurality of preset natural language processing models belonging to different fields; The text corresponding to the process is processed by the processing model corresponding to the process, the hardware interface information and service protocol information required to implement the process are determined, and the implementation information of the process is obtained.

3. The process arrangement method according to claim 2, wherein the text corresponding to the process is processed by the processing model corresponding to the process, the hardware interface information and service protocol information required to implement the process are determined, and the implementation information of the process is obtained, including: Extracting descriptive information representing a specific processing process of the process from the text corresponding to the process through the processing model corresponding to the process; Matching among a plurality of preset hardware interfaces and a plurality of service protocols according to the description information, and determining at least one target hardware interface and at least one target service protocol whose matching degree satisfies a matching condition; The hardware interface information corresponding to the at least one target hardware interface and the service protocol information corresponding to the at least one target service protocol are acquired to obtain implementation information of the process.

4. The process orchestration method according to claim 3, wherein the plurality of preset natural language processing models are created by a process management system for processing the product; The extracting, from the text corresponding to the process, description information representing the specific processing process of the process through the processing model corresponding to the process, includes: By using the processing model corresponding to the process, initial description information representing the specific processing process of the process is extracted from the text corresponding to the process, and the version of the initial description information is converted into a version that complies with the process management system to obtain description information.

5. According to the process orchestration method according to claim 1 or 3, the hardware interface information includes at least one application program interface and interface information of the application program interface, and the service protocol information includes at least one service provider interface related to the application program interface and interface information of the service provider interface.

6. The process arrangement method according to claim 1, wherein the extracting of multiple processes for processing the product from the initial text and the texts corresponding to the multiple processes respectively comprises: A large-scale pre-trained model is used to extract multiple processes for processing the product from the initial text, and the initial text is segmented to obtain texts corresponding to the multiple processes.

7. The process arrangement method according to claim 6, before extracting multiple processes for processing the product from the initial text by using a large-scale pre-trained model and segmenting the initial text to obtain texts corresponding to the multiple processes, further comprising: Perform prompt word fine-tuning training on the large-scale pre-trained model based on the prompt word template to obtain target prompt words, wherein the target prompt words are used to prompt the large-scale pre-trained model to extract multiple processes including sample text; The extracting multiple processes for processing the product from the initial text by using a large-scale pre-trained model, and segmenting the initial text to obtain texts corresponding to the multiple processes, respectively, includes: The target prompt word is used to instruct the large-scale pre-trained model to extract multiple processes for processing the product from the initial text, and to segment the initial text to obtain texts corresponding to the multiple processes.

8. The process arrangement method according to claim 1, wherein the visualizing of the plurality of processes and the implementation information respectively corresponding to the plurality of processes to obtain process arrangement information for indicating the processing of the product comprises: The multiple processes are sorted based on the processing order for processing the product, and visual description data is added at the location of the process according to the implementation information of the process, so as to obtain a process arrangement report for indicating the processing of the product.

9. The process arrangement method according to claim 1, wherein the visualizing of the plurality of processes and the implementation information respectively corresponding to the plurality of processes to obtain process arrangement information for indicating the processing of the product comprises: Visualizing the multiple processes and the implementation information respectively corresponding to the multiple processes to obtain initial process arrangement information for indicating processing of the product; At least one correction instruction is received from a user, and in response to the at least one correction instruction, at least one target process in the initial process choreography information and / or the implementation information of the target process is corrected to obtain the process choreography information.

10. A process scheduling device, comprising: A text acquisition module, used to acquire initial text with content related to product processing; A process extraction module, used to extract multiple processes for processing the product from the initial text, and texts corresponding to the multiple processes; An information determination module, used to determine the hardware interface information and service protocol information required to implement the process according to the text corresponding to the process, and obtain the implementation information of the process; The process arrangement module is used to visualize the multiple processes and the implementation information respectively corresponding to the multiple processes to obtain process arrangement information for indicating the processing of the product.

11. A computer storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 9.

12. A computer program product, wherein the computer program product stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 9.

13. An electronic device comprising: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 9.

Images