Data processing method, device and equipment for project management and storage medium

Abstract

The present disclosure provides a data processing method and device in project management, equipment and storage medium, relating to the field of computer. The method comprises: obtaining generation description information for a target field in a work item, the work item comprising a plurality of fields, the generation description information describing generation requirements of a field value of the target field; selecting a target system prompt word from a plurality of system prompt words based on the type of the target field; determining prompt word information for field value generation of the target field based on the generation description information and the target system prompt word, the prompt word information comprising description information for a structured computer language used to describe content of a rich text type; and determining the field value of the target field by using a machine learning model based on the prompt word information. There may be fields of the rich text type in project management. By using the embodiments of the present disclosure, the generation of the field value related to the rich text content can be efficiently processed, thereby improving the efficiency of project management.

Description

TECHNICAL FIELD

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to a data processing method, apparatus, device, computer-readable storage medium and computer program product for project management. BACKGROUND

[0002] With the development of information technology, various terminal devices can provide people with various services in work and life, etc. An application providing services can be deployed in the terminal device. The terminal device presents corresponding content through the user interface of the application and realizes interaction with the user to meet various needs of the user. For example, in a project management scenario, the terminal device or the application can process data related to the project according to the request of the user to achieve the purpose of project management. SUMMARY

[0003] In a first aspect of the present disclosure, a data processing method for project management is provided. The method comprises: obtaining generation description information for a target field in a work item, the work item comprising a plurality of fields, the target field being one of the plurality of fields, and the generation description information describing generation requirements of a field value of the target field; selecting a target system prompt word from a plurality of system prompt words based on a type of the target field; determining prompt word information for field value generation of the target field based on the generation description information and the target system prompt word, wherein the generation description information indicates that the field value generation of the target field is based on rich text type content or the type of the target field is a rich text type, and the prompt word information comprises description information for a structured computer language used to describe the rich text type content; and determining the field value of the target field by using a machine learning model based on the prompt word information.

[0004] In a second aspect of the present disclosure, a data processing apparatus for project management is provided. The apparatus comprises: an acquisition module configured to obtain generation description information for a target field in a work item, the work item comprising a plurality of fields, the target field being one of the plurality of fields, and the generation description information describing generation requirements of a field value of the target field; a selection module configured to select a target system prompt word from a plurality of system prompt words based on a type of the target field; a first determination module configured to determine prompt word information for field value generation of the target field based on the generation description information and the target system prompt word, wherein the generation description information indicates that the field value generation of the target field is based on rich text type content or the type of the target field is a rich text type, and the prompt word information comprises description information for a structured computer language used to describe the rich text type content; and a second determination module configured to determine the field value of the target field by using a machine learning model based on the prompt word information.

[0005] In a third aspect of the disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. The instructions, when executed by the at least one processing unit, cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of the disclosure, a computer-readable storage medium is provided. The computer-readable storage medium has stored thereon a computer program, the computer program being executable by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of the disclosure, a computer program product is provided, the program product including a computer program executable by a processor to implement the method of the first aspect.

[0008] It should be understood that the contents described in this section are not intended to limit the key features or important features of the embodiments of the disclosure, nor are they used to limit the scope of the disclosure. Other features of the disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings in which:

[0010] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented is shown;

[0011] Figure 2 A schematic diagram showing an example interface for presenting work item base information according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A schematic block diagram showing an example flow of a data processing method according to some embodiments of the present disclosure is shown;

[0013] Figure 4 A schematic diagram showing a dialog interface for a field in a work item according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A schematic diagram showing an example interface for initiating a configuration request according to some embodiments of the present disclosure is shown;

[0015] Figure 6 A schematic diagram showing an example of a configuration request according to some embodiments of the present disclosure is shown;

[0016] Figure 7A diagram illustrating an example architecture for field value generation in case the referenced field includes rich text content, according to some embodiments of the present disclosure is shown;

[0017] Figure 8 A diagram illustrating an example architecture for field value generation in case the referenced field includes rich text content, according to some embodiments of the present disclosure is shown;

[0018] Figure 9 A diagram illustrating an example architecture for field value generation in case the referenced field includes rich text content, according to some embodiments of the present disclosure is shown;

[0019] Figure 10 A flow diagram illustrating an example process for a data processing method in project management, according to some embodiments of the present disclosure is shown;

[0020] Figure 11 A schematic block diagram of a data processing apparatus for use in project management, according to some embodiments of the present disclosure is shown; and

[0021] Figure 12 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. While several embodiments of the present disclosure are described, it should be understood that the present disclosure can be embodied in many other forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and fully convey the scope of the present disclosure to those skilled in the art. It should be understood that the figures and embodiments are only used to illustrate the present disclosure and should not be construed as limiting the scope of the present disclosure.

[0023] It should be noted that the headings provided herein are not limitations of the various embodiments described herein. The various embodiments described herein can be included under any heading and any type of embodiment can be included under any heading. Furthermore, embodiments described in any heading can be combined with any other embodiment described in the same heading and / or a different heading in any manner.

[0024] In the description of embodiments of the present disclosure, the term "includes" and its variants are to be read as open-ended terms that mean "includes, but is not limited to." The term "based on" is to be read as "based, at least in part, on." The term "one embodiment" or "an embodiment" are to be read as "at least one embodiment." The term "some embodiments" is to be read as "at least some embodiments." Other explicit and implicit definitions can also be included below. The terms "first," "second," etc. can refer to different or same objects. Other explicit and implicit definitions can also be included below.

[0025] The data of the user, the acquisition and / or use of the data, etc. can be involved in the embodiments of the present disclosure. These aspects comply with the corresponding laws and regulations and relevant provisions. In the embodiments of the present disclosure, the collection, acquisition, processing, processing, forwarding, use, etc. of all data are performed on the premise that the user is aware of and confirms. Accordingly, when implementing the embodiments of the present disclosure, the type, use range, use scenario, etc. of the data or information that can be involved should be informed to the user and the authorization of the user should be obtained through appropriate means according to the relevant laws and regulations. The specific informing and / or authorization manner can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this aspect.

[0026] In the present specification and embodiments, if the scheme involves processing of personal information, the processing is performed on the premise of having a legal basis (for example, obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.) and is performed only within the prescribed or agreed range. The user refuses to process personal information other than the necessary information required for the basic function, which does not affect the user's use of the basic function.

[0027] Example environment

[0028] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented is shown. In the environment 100, a component runtime platform 110 can support the running of a business component 125. A user 140 can interact with the business component 125 via a client of the component runtime platform 110.

[0029] In some embodiments, the business component 125 can be downloaded and installed on a terminal device of the user 140. In some embodiments, the business component 125 can also be accessed in other ways, such as accessed through a webpage, etc. In some embodiments, the business component 125 can be accessed through a browser of the terminal device of the user 140. Figure 1 In the environment 100, in response to the business component 125 being started, the client of the component runtime platform 110 can present an interface 150 of the business component 125.

[0030] The business component 125 includes, but is not limited to, one or more of the following: a chat business component (also referred to as an instant messaging business IM component), a document business component, an audio and video conference business component, a mail business component, a task business component, a calendar business component, an objective and key result (OKR) business component, a project management component, etc. It can be understood that although the business component 125 is shown as a single component in the environment 100, the business component 125 can include multiple components in some embodiments. Figure 1A single business component is shown in FIG. 1, but in practice multiple business components can be installed on the component runtime platform 110. Multiple business components can be integrated on the component runtime platform 110, which can be considered as a multi-functional collaboration platform. In the case where multiple business components are installed on the terminal device, the multiple business components can be integrated on one or more component runtime platforms 110. In the component runtime platform 110, different business components can be launched as needed to complete corresponding information processing, sharing, communication, etc. The business component 125 can provide a content entity 126. The content entity 126 can be a content instance created by the user 140 or other users on the business component 125. For example, depending on the type of the business component 125, the content entity 126 can be a document (e.g., a word document, a pdf document, a presentation, a table document, etc.), an email, a message (e.g., a conversation message on an instant messaging business component), a calendar, a schedule, a task, an audio, a video, an image, etc.

[0031] In some embodiments described below, for ease of discussion, the interaction window between the user and the digital assistant is mainly taken as an example of a conversation window.

[0032] The component runtime platform 110 can be deployed locally on the terminal device of each user 140 and / or can be supported by a server device. For example, the terminal device of the user 140 can run a client of the component runtime platform 110, which can support the interaction of the user 140 with the component runtime platform 110 provided by the server. In the case where the component runtime platform 110 runs locally on the terminal device of the user, the user 140 can directly interact with the local component runtime platform 110 using the terminal device. In the case where the component runtime platform 110 runs on the server device, the server device can implement service provision to the client running on the terminal device based on the communication connection between the terminal device and the server device. The component runtime platform 110 can present a corresponding interface 150 to the user 140 based on the operation of the user 140, to output and / or receive information related to the use of the component to the user 140.

[0033] In some embodiments, the implementation of at least part of the function of the business component 125 can be implemented based on a target model. One or more target models 155 can be called during the running of the business component 125. The target model 155 can be used to understand the user input and provide services based on the output of the target model 155, such as providing a reply to the user.

[0034] Although shown as running independently of the component runtime platform 110, one or more target models 155 can run on the component runtime platform 110, or other remote servers. In some embodiments, the target models 155 can be machine learning models, deep learning models, learning models, neural networks, etc. In some embodiments, the models can be based on language models (LMs), such as large language models. Language models can be capable of question answering by learning from a large corpus. The target models 155 can also be based on other suitable models. In some embodiments, the models can be multi-modal models capable of processing inputs in multiple modalities, such as text, vision, etc.

[0035] The component runtime platform 110 can run on a suitable electronic device. The electronic device here can be any type of device with computing capability, including an end device or a server device. The end device can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a game device, or any combination thereof, including accessories and peripherals of such devices or any combination thereof. The server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, etc. In some embodiments, the component runtime platform 110 can be implemented based on cloud services.

[0036] It should be understood that the structure and function of the environment 100 are described for illustrative purposes only, without implying any limitation on the scope of the present disclosure.

[0037] As mentioned above, the end device or the application can provide a project management service for a user. In one scenario, the service provider can provide the user with information related to the project in the form of fields, so that the user can accurately and intuitively understand the information such as project status, resources, risks, and progress, etc. In this scenario, the service provider mostly updates and manages the values of the fields through manual processing or automatic instruction sets determined based on preset rules.

[0038] However, the way of manually processing the field values by the administrator requires manual editing and processing of the data, resulting in low processing efficiency. In the case of a large amount of data, this way is easy to lose key information. The way of managing the field values by the automatic instruction sets can only process the project information based on the preset logic, and cannot understand the natural language instructions and context information, affecting the processing efficiency. Therefore, how to provide a new data processing method is a problem that those skilled in the art urgently need to solve.

[0039] Embodiments of the present disclosure provide a data processing method for project management. In the method, after obtaining generation description information for a target field in a work item, a target system prompt word is determined based on the type of the target field. Based on the target system prompt word and the generation description information, prompt word information for a machine learning model is determined. Further, a field value of the target field is determined by using the machine learning model.

[0040] In embodiments of the present disclosure, the field value of the target field is determined by using the machine learning model, thereby improving the data processing efficiency in project management. In addition, in order to enable the machine learning model to understand the content of the rich text type, a structured computer language that is easy for the machine learning model to understand is adopted. In the case where the field value generation involves the content of the rich text type, for example, in the case where the field value generation depends on the content of the rich text type or the field value is of the rich text type, the description information of the structured computer language is included in the prompt word information provided to the machine learning model, so as to facilitate the machine learning model to understand the content of the rich text type. In this way, the machine learning model does not need to understand the complex structure of the content of the rich text type, but can focus on the field value generation.

[0041] Unlike general data processing, there can be various fields of the rich text type in project management to better describe the situation of the project. By using embodiments of the present disclosure, the field value generation involving the content of the rich text type can be efficiently processed, thereby improving the efficiency of project management.

[0042] Various example implementations of the scheme are described in further detail below in conjunction with the accompanying drawings.

[0043] Example architecture

[0044] In some embodiments, the component running platform 110 can provide project management services for the user 140. For example, the component running platform 110 can provide a plurality of forms respectively corresponding to a plurality of project management tasks. The user can add a work item in the form. The project management tasks can include a project requirement task, a project defect task, etc.

[0045] In some embodiments, if it is detected that the user selects a certain type of task (for example, a requirement type or an approval type), the component running platform 110 can present a plurality of project management tasks corresponding to the type of task to the user 140. Figure 2 A schematic diagram of an example interface for presenting basic information of a work item is shown according to some embodiments of the present disclosure. As shown in FIG. 1, the interface can include a plurality of fields. The fields can include a task type field, a task name field, a task status field, a task assignee field, a task priority field, a task description field, etc. Figure 2As shown, a portion of a form 210 is presented in the interface 200. The form 210 includes a plurality of work items, corresponding to different tasks under the task type. If a selection of a work item in the form 210 is detected, the component runtime platform 110 can present basic information 220 of the work item to the user. Illustratively, if a selection of the work item “Requirement 03” is detected, the basic information 220 of “Requirement 03” is presented in the form of a window. The basic information 220 can include a plurality of fields, such as a name field 221-1, a business line field 221-2, a requirement type field 221-3, and a priority field 221-4. The field value of a certain field can be a system default value or a user input value, or can be determined based on the field values of other fields, which is not limited herein. In some embodiments, the component runtime platform 110 can present other information of the selected work item by the user 140, such as requirement target, requirement value, and requirement related documents, etc.

[0046] In some embodiments, the component runtime platform 110 can obtain a processing request input by the user, and process data in the work item according to the processing request. Illustratively, the component runtime platform 110 can obtain the processing request through a digital assistant. Figure 3 An illustrative block diagram of an example flow of a data processing method according to some embodiments of the present disclosure is shown. As shown, the component runtime platform 110 obtains a processing request 310, and determines a historical dialogue 320 corresponding to the processing request 310. Illustratively, the component runtime platform 110 can determine the corresponding historical dialogue 320 from the historical dialogue records based on the type of the processing request 310 or the fields related to the processing request 310. Figure 3

[0047] The component runtime platform 110 determines a model input 330 based on the processing request 310 and the historical dialogue 320. Illustratively, the component runtime platform 110 can determine the model input 330 in a splicing manner. Subsequently, the component runtime platform 110 provides the model input 330 to an intent determination unit 340, so as to determine the user intent indicated by the processing request 310 by using the intent determination unit 340. In some embodiments, the intent determination unit 340 can determine the user intent indicated by the processing request 310 based on a machine learning model (e.g., a large language model).

[0048] In some embodiments, if the user intent determined by the intent determination unit 340 is “field value generation”, the processing request 310 is provided to a field value generation unit 350.

[0049] ​The field value generation unit 350 is used to generate field values ​​for a target field based on the processing request 310, and it may be implemented or included in the component runtime platform 110. For example, the field value generation unit 350 may determine generation description information for a target field in a work item based on the processing request 310. The generation description information describes the generation requirements (e.g., generation rules, etc.) for the field value of the target field. In some embodiments, the field value generation unit 350 may determine the processing request 310 as the generation description information, or process the processing request 310 using a machine learning model (e.g., rewrite or supplement) and use it as the generation description information.

[0050] return Figure 2 In some embodiments, if a trigger is received for a field (e.g., selection, click, etc.), the component runtime platform 110 presents a dialogue interface with the digital assistant. Figure 4 A schematic diagram of a dialog interface for fields in a work item, according to some embodiments of this disclosure, is shown. For example... Figure 4 As shown, the component runtime platform 110 detects the user 140's selection of priority fields 221-4 and presents the digital assistant's dialogue interface 410 in the interface 400. The dialogue interface 410 includes guidance information provided by the digital assistant related to the target field, such as, "What can I do for you regarding the priority field?". Figure 4 As shown, the user-provided processing request 310 may include "return priority based on name content". In this case, the component runtime platform 110 can provide the processing request 310 to the field value generation unit 350 to determine the generation description information corresponding to the processing request 310.

[0051] Users can activate a digital assistant by triggering one of multiple fields (e.g., selecting, clicking, etc.) to provide the digital assistant with generated description information. In some embodiments, the target field can be the field triggered by the user. For example, if the user selects the "Priority" field, a dialog interface for the digital assistant is presented for the priority field. The target field for the processing request 310 provided by the user through this dialog interface is always the "Priority" field. In some embodiments, the component runtime platform 110 can determine the target field based on the processing request 310. For example, if the processing request 310 entered by the user is "Set the requirement type to technical requirement", the component runtime platform 110 can determine the target field as the "requirement type" field based on the processing request 310.

[0052] In some embodiments, the component runtime platform 110 selects a target system prompt from a plurality of system prompts based on a type of the target field. In some embodiments, the type of the target field can be a text type, a single-select type, a multi-select type, or a rich text type, etc. For example, if the type of the target field is a text type, a system prompt of the text type is determined. If the type of the target field is a single-select type, a prompt of the single-select type is determined. The system prompt can be a prompt predetermined for different types of fields for generating a field value of a field of a corresponding type. The system prompt includes information such as a role description, a workflow description, and an output format, etc.

[0053] Examples of the system prompt will be described below with reference to Tables 1-3. Table 1 is an example of a system prompt for a single-select type field, Table 2 is an example of a system prompt for a multi-select type field, and Table 3 is an example of a system prompt for a text type field.

[0054] Table 1:

[0055]

[0056] Table 2:

[0057]

[0058] Table 3:

[0059]

[0060] In some embodiments, the component runtime platform 110 determines prompt information for field value generation of the target field based on the generation description information and the determined target system prompt. For example, a user prompt can be generated based on the generation description information (which is also referred to as a “task description” in some examples) and other information. Examples of the other information can include, but are not limited to, information of fields required to be used for generating the target field, information of the target field, a list of options of field values of the target field, and additional reference information, etc. The component runtime platform 110 provides the prompt information to a machine learning model to obtain an output of the machine learning model. Subsequently, the component runtime platform 110 determines the field value 360 of the target field based on the output of the machine learning model. For example, the machine learning model can be a large language model.

[0061] Example embodiments regarding generation of the prompt information will be described below. In some embodiments, the component runtime platform 110 can determine a user prompt corresponding to the generation description information based on the generation description information and a prompt template. Subsequently, the user prompt and the target system prompt are combined (e.g., concatenated, etc.) to determine the prompt information for field value generation of the target field.

[0062] In some embodiments, the component running platform 110 can determine at least one field that needs to be referenced or relied on for generating a field value of a target field based on the generation description information. For example, if the generation description information includes "generate priority based on name field", the "priority" field is the target field and the "name" field is the referenced field. Then, the component running platform 110 can determine context information for generating the field value of the target field based on the at least one determined field. For example, the field name, the field type and the field value of the at least one field can be used as the context information. The component running platform 110 generates the prompt information based on the generation description information, the context information and the target system prompt word. For example, the component running platform 110 can use the generation description information and the context information as at least a part of the user prompt word, and concatenate the user prompt word and the target system prompt word as the prompt information.

[0063] The user prompt word will be explained below with reference to Table 4 and Table 5. Table 4 is an example of a template of the user prompt word.

[0064] Table 4:

[0065]

[0066] In the example of Table 4, for adding the generation description information, e.g. user input. for adding information about the at least one referenced field (i.e. the context information), e.g. name, type, field value, etc. for adding the name of the target field. for adding the candidate field value of the target field. for adding other information related to the field value generation.

[0067] Table 5:

[0068]

[0069] Table 5 shows an example of the user prompt word generated based on the template of Table 4. Table 5 shows a part of the user prompt word. Table 5 includes the generation description information (which corresponds to the "task description" part) and the corresponding context information (which corresponds to the content of the JSON {…} part in Table 5), and the context information is included in the prompt information in the form of reference, specifically, the reference to the context information is included in the task description (e.g. ). In this way, it prevents the prompt information from being too long to cause the machine learning model to fail to understand the real intention of the user.

[0070] One or more fields in a work item may be rich text types. Due to the complex style and linear, tiling data structure of rich text content, machine learning models may not be able to directly understand its content. In some embodiments, generating descriptive information can instruct the target field's field value to generate rich text-type content or that the target field is of rich text type. Accordingly, the prompt information determined based on the generated descriptive information can include explanatory information for a structured computer language used to describe rich text-type content. In this way, the machine learning model does not need to understand the complex structure of the rich text-type content, but can focus on field value generation.

[0071] When the target field includes rich text content or the field value of the target field generates content based on a rich text type, the performance of the model may be affected. Therefore, in some embodiments, rich text conversion tools (e.g., rich text software development kits) can be used to convert the rich text content into a structured computer language, such as JavaScript Object Notation (JSON) format or Markdown format.

[0072] Figure 7 A schematic diagram of an example architecture for processing rich text content according to some embodiments of this disclosure is shown. Figure 7 As shown, a rich text conversion tool 740 is deployed on both the front end (e.g., browser 710) and back end (e.g., server 750) of the component runtime platform 110. The rich text conversion tool 740 is used to convert the browser output 720 of the browser 710 into a structured computer language 730, and to convert the runtime output 760 of the server 750 into rich text content 770, thereby achieving the conversion between rich text content and computer language. The structured computer language can include any suitable form of computer language, such as a domain-specific language (DSL). In this way, the machine learning model can focus on understanding and outputting computer language without needing to understand the complex data structure of the rich text content. This reduces interference with the machine learning model, thereby improving the quality of the output.

[0073] In some embodiments, the component runtime platform 110 can implement a set of general runtime code based on a browser engine, enabling the rich text conversion tool used by the front end to run within the backend service. In this way, the rich text conversion tool can run across platforms (i.e., across server-side and browser-side), ensuring data consistency and reducing maintenance costs.

[0074] In some embodiments, if the generation description information indicates that the field value of the target field is generated based on rich text content (e.g., the type of the referenced field is rich text), the component runtime platform 110 can convert the rich text content (e.g., the field value of the referenced field) into field description information represented in a structured computer language based on predetermined conversion rules. Figure 8 A schematic diagram illustrating an example architecture for field value generation in the case where the referenced field includes rich text content, according to some embodiments of this disclosure. For example... Figure 8 As shown, the component runtime platform 110 converts rich text content 810 (e.g., field values ​​of referenced fields) into field description information represented in a structured computer language using a computer language conversion unit 820 (e.g., rich text conversion tool 740). Subsequently, the component runtime platform 110 determines first prompt word information 830 based on the field description information, generated description information, and target system prompt words. In some embodiments, the component runtime platform 110 may add explanatory information for the structured computer language to the first prompt word information 830 to facilitate the machine learning model's understanding of the structure of the rich text content. The explanatory information may, for example, include a definition of the structured computer language, such as a DSL definition. The first prompt word information 830 is then provided to the machine learning model 840 to obtain the field value 360 ​​of the target field.

[0075] Table 6 is an example of prompt words involving rich text type fields.

[0076] Table 6:

[0077]

[0078] As shown in Table 6, based on the rich text content in the referenced field, field description information represented in Structured Computer Language is determined. This field description information can be added to system prompts to generate prompt information for use with machine learning models.

[0079] In some embodiments, the target field can be of a rich text type, meaning that the field value 360 ​​of the target field can include rich text content. Figure 9 A schematic diagram of an example architecture for generating field values ​​of a rich text type, according to some embodiments of this disclosure, is shown. For example... Figure 9As shown, if the type of the target field to which the generated description information is directed is a rich text type, the component runtime platform 110 provides a processing request 910 for the rich text content to the referenced field resolution unit to determine the information of the referenced field. Subsequently, the component runtime platform 110 combines the information of the referenced field, the generated description information, and the target system prompt to obtain second prompt information 920. In some embodiments, the system prompt corresponding to the rich text type can include specification information for a structured computer language, such as a DSL definition. In this case, since the target field is a rich text field, the selected target system prompt includes the specification information. In this way, the second prompt information generated based on the target prompt also includes the specification information. The model can return a result in a structured computer language. Subsequently, the second prompt information 920 and the rich text content are provided to the machine learning model 840 to obtain a model output expressed in the structured computer language by the machine learning model 840. The model output can be provided to a rich text conversion unit 930. Subsequently, the rich text conversion unit 930 can convert the model output of the machine learning model 840 into rich text content based on predetermined conversion rules, as the field value 360 of the target field.

[0080] In the foregoing, embodiments in which the type of the referenced field is a rich text type and embodiments in which the type of the target field is a rich text type are described respectively. In some embodiments, the two cases can be combined, i.e., the field value of the target field of the rich text type can be generated based on the referenced field of the rich text type.

[0081] With reference to Figure 2 , after obtaining the field value 360 of the target field, the component runtime platform 110 can present the field value 360 of the target field and operation information related to the field value 360 of the target field to the user 140. Illustratively, the operation information can indicate an update operation for the target field, i.e., updating the target field with the obtained field value. In some embodiments, the field value 360 of the target field and the corresponding operation information can be presented to the user through an operable item of the dialog information 380 presented in the session. As Figure 4 shown, the dialog information 380 can include the session text "the field value of the priority is XXX", a first operable item for updating the target field, and a second operable item for regenerating the field value of the target field. If the selection of the first operable item by the user is detected, the determined field value is filled into the target field in the work item.

[0082] The above describes an example embodiment of the example interaction between the component running platform 110 and the user 140. In the above embodiment, the component running platform 110 presents the user 140 with the information related to the project management task through the work items and the fields, and generates the field value of the target field based on the processing request 310 provided by the user 140, thereby realizing the update and management of the field value by using the machine learning model. In some embodiments, the fields and work items provided by the component running platform 110 can include the configuration information provided by the administrator. The component running platform 110 can determine the corresponding field value based on the configuration information of the field, so as to realize the automatic update and management of the field value. In the following embodiments, the process of determining the configuration information by the administrator is described.

[0083] Figure 5 A schematic diagram of an example interface for initiating a configuration request according to some embodiments of the present disclosure is shown. If a configuration request of an administrator for a certain form is detected, the component running platform 110 presents the corresponding configuration item for a plurality of fields in the form. As shown in Figure 5 If a configuration request for the requirement form A is received, the component running platform 110 presents the administrator with an interface 500 for obtaining the configuration information of the requirement form A. The interface 500 includes a first area 510 for presenting information related to the field and a second area 520 for presenting the field configuration item. A plurality of fields are included in the interface 500, such as the proposal time, the completion time, the attention person, and the business line, etc. If the selection of a certain field by the administrator is detected, the component running platform 110 can present the configuration item corresponding to the field in the second area 520. For example, if the component running platform 110 detects that the administrator selects the “attention person” field, the configuration item presented in the second area 520 includes a first configuration item 530 for providing editing instructions, a second configuration item 540 for determining whether to update the field value based on the AI instruction, and a third configuration item 550 for configuring the basic information of the field.

[0084] In some embodiments, if the interaction information is received via the configuration item for a certain field, the component running platform 110 can determine to generate the description information based on the interaction information. For example, if the interaction operation for the first configuration item 530 is detected, the component running platform 110 presents an interface for obtaining the generated description information for the field. Figure 6 A schematic diagram of an example of a configuration request according to some embodiments of the present disclosure is shown. Figure 6An edit instruction obtaining interface 610 is shown, which includes an entry 620 for obtaining a generation description, a control 630 for selecting a debugging instance, and a presentation area 640 for presenting a debugging result. If the component running platform 110 detects the content input by the administrator in the entry 620, the input content can be directly taken as the generation description for the target field. In some embodiments, the component running platform 110 can process the input content to determine the generation description. Exemplary content input by the administrator in the entry 620 can be a natural language instruction referencing other fields, such as “generate title based on @feedback record”. After obtaining the user input, the component running platform 110 can parse the field reference relationship expressed in the natural language in the user input, thereby determining the generation description.

[0085] After determining the generation description, the component running platform 110 can provide the determined generation description to the debugging instance selected by the administrator in the control 630. Subsequently, the component running platform 110 runs the debugging instance to obtain a debugging output of the debugging instance, and presents the debugging output in the presentation area 640 for the administrator to view. If the debugging output does not meet the expectation of the administrator, the administrator can update the generation description.

[0086] In some embodiments, if the component running platform 110 detects that the information of a certain field in the work item is updated, an update operation is performed on the corresponding information of other fields referencing the field in the generation description based on the updated information of the field. For example, the generation description “update priority based on multi-line text field” for the priority field includes a reference to the “multi-line text” field. After the generation description for the priority field is applied, if the component running platform 110 detects that the content of the “multi-line text” field is updated, the field value of the “priority” field is updated based on the updated content of the “multi-line text” field. In this way, the purpose of automatically updating the field value can be achieved.

[0087] Figure 6 The control 650 is used to set the generation description corresponding to the input content of the entry 620 as the commonly used generation description of the corresponding administrator. If the component running platform 110 detects that the control 650 is selected, the generation description determined based on the user input of the entry 620 is taken as the commonly used generation description of the administrator initiating the configuration request. Exemplarily, if the generation description a for the field A is taken as the commonly used generation description of the administrator. In subsequent editing operations, the default generation description of all field A created by the administrator can be set as a.

[0088] Continuing to refer to Figure 3If the user intent determined by the intent determination unit is "conversation", the processing request 310 is provided to the machine learning model 370. The machine learning model 370 generates conversation information 380 based on the obtained processing request 310 to provide a conversational service to the user. In some embodiments, the machine learning model 370 can provide information related to the current form to the user. For example, if the processing request 310 is "summarize the content of the name field", the machine learning model 370 can generate a summary of the content of the "name" field based on the information related to the "name" field.

[0089] Table 7 is an example of system prompt words for a conversation.

[0090] Table 7:

[0091]

[0092] As shown in Table 7, in the case where the user intent is a normal conversation, the component runtime platform 110 can generate corresponding prompt word information based on the processing request 310 input by the user and the prompt word templates described above. Then, the prompt word information is provided to the machine learning model 370 to provide conversation information 380 to the user based on the output of the machine learning model 370.

[0093] In summary, in embodiments of the present disclosure, for a processing request provided by a user to a digital assistant, a target system prompt word is determined according to the field type, and prompt word information for a machine learning model is generated based on the generated description information and the target system prompt word, so as to determine the field value of the target field by using the machine learning model. In this way, field value updating based on conversational interaction is achieved. In some embodiments, context information is introduced into the prompt word information by generating a reference to other fields in the description information. In this way, accurate context information is provided to the machine learning model to improve the understanding ability of the machine learning model. In some embodiments, the conversion between rich text content and structured computer language is achieved by a rich text conversion tool, which improves the understanding ability of the large model for rich text content, and at the same time, a field value of a rich text type can be generated. For the administrator, by configuring the generated description information for each field in the form, the field value of the corresponding field can be automatically generated and updated.

[0094] Example process

[0095] Figure 10 A flowchart of an example process for a data processing method in project management is shown according to some embodiments of the present disclosure. The process 1000 can be implemented at the component runtime platform 110. The process 1000 is described below with reference to the component runtime platform 110. The process 1000 is described below with respect to the component runtime platform 110 only as an example. Figure 1 ​

[0096] As Figure 10 shown, at step 1010, generation description information for a target field in a work item is acquired, the work item includes a plurality of fields, the target field is one of the plurality of fields, and the generation description information describes generation requirements for a field value of the target field.

[0097] In some embodiments, the work item is included in a form having a plurality of fields, and acquiring the generation description information includes: in response to receiving a configuration request for the form, presenting respective configuration items for the plurality of fields; and determining the generation description information based on interaction information received via the configuration item for the target field.

[0098] In some embodiments, acquiring the generation description information includes: presenting basic information of the work item, the basic information including the plurality of fields; in response to receiving a selection for the target field, presenting a dialog interface with the digital assistant; and in response to receiving a processing request for the target field via the dialog interface, determining the generation description information based on the processing request.

[0099] In some embodiments, the process 1000 further includes: in response to determining the field value of the target field, presenting the field value and operation information related to the field value of the target field, the operation information indicating an update operation for the target field; and in response to receiving a selection for the update operation, filling the determined field value into the target field in the work item.

[0100] At step 1020, a target system prompt word is selected from a plurality of system prompt words based on a type of the target field.

[0101] In some embodiments, the type of the target field includes at least one of: a single selection type, a multiple selection type, a text type, a rich text type.

[0102] At step 1030, prompt word information for field value generation of the target field is determined based on the generation description information and the target system prompt word, wherein the generation description information indicates that the field value generation of the target field is based on content of a rich text type or the type of the target field is the rich text type, and the prompt word information includes specification information for a structured computer language used to describe the content of the rich text type.

[0103] In some embodiments, determining the prompt word information includes: based on the generation description information, determining at least one field of the plurality of fields, the generation description information indicating that the field value generation of the target field is based on the at least one field; based on the at least one field, determining context information for character value generation of the target field; and based on the generation description information, the context information, and the target system prompt word, generating the prompt word information, the context information being included in the prompt word information in a reference form.

[0104] In some embodiments, the generation description information indicates that the field value of the target field is generated based on a referenced field in the plurality of fields, and determining the prompt word information comprises: in response to determining that the type of the referenced field is a rich text type, converting the field value of the referenced field into field description information represented in a structured computer language based on a predetermined conversion rule; and determining the prompt word information based on the field description information, the instruction information, the generation description information and the target system prompt word.

[0105] At step 1040, based on the prompt word information, the field value of the target field is determined by using the machine learning model.

[0106] In some embodiments, the type of the target field is a rich text type, the target system prompt word includes instruction information for the structured computer language, and determining the field value of the target field comprises: obtaining model output represented in the structured computer language from the machine learning model; and converting the model output represented in the structured computer language into target rich text content as the field value of the target field based on a predetermined conversion rule.

[0107] Example apparatus and device

[0108] Embodiments of the present disclosure also provide a corresponding apparatus for implementing the above method or process. Figure 11 A schematic block diagram of a data processing apparatus for project management is shown according to some embodiments of the present disclosure. The data processing apparatus 1100 can be implemented as or included in a component runtime platform 110. Various modules / components in the data processing apparatus 1100 can be implemented by hardware, software, firmware or any combination thereof.

[0109] As Figure 11As shown, the data processing apparatus 1100 includes an obtaining module 1110 configured to obtain generation description information for a target field in a work item, the work item including a plurality of fields, the target field being one of the plurality of fields, and the generation description information describing generation requirements of a field value of the target field. The data processing apparatus 1100 further includes a selecting module 1120 configured to select a target system prompt word from a plurality of system prompt words based on a type of the target field. The data processing apparatus 1100 further includes a first determining module 1130 configured to determine prompt word information for field value generation of the target field based on the generation description information and the target system prompt word, wherein the generation description information indicates that the field value generation of the target field is based on rich text type content or the type of the target field is a rich text type, and the prompt word information includes specification information for a structured computer language used to describe the rich text type content. The data processing apparatus 1100 further includes a second determining module 1140 configured to determine the field value of the target field based on the prompt word information using a machine learning model.

[0110] In some embodiments, the work item is included in a form having a plurality of fields, and the obtaining module 1110 is further configured to, in response to receiving a configuration request for the form, present respective configuration items for the plurality of fields; and determine the generation description information based on interaction information received via the configuration item for the target field.

[0111] In some embodiments, the obtaining module 1110 is further configured to present basic information of the work item, the basic information including the plurality of fields; in response to receiving a selection for the target field, present a dialog interface with the digital assistant; and in response to receiving a processing request for the target field via the dialog interface, determine the generation description information based on the processing request.

[0112] In some embodiments, the data processing apparatus 1100 further includes an updating module further configured to, in response to determining the field value of the target field, present the field value and operation information related to the field value of the target field, the operation information indicating an update operation for the target field; and in response to receiving a selection for the update operation, fill the determined field value into the target field in the work item.

[0113] In some embodiments, the type of the target field includes at least one of the following: a single selection type, a multiple selection type, a text type, and a rich text type.

[0114] In some embodiments, the first determining module 1130 is further configured to determine at least one field among a plurality of fields based on the generated description information, the generated description information indicating that the field value of the target field is generated based on at least one field; determine context information for generating the character value of the target field based on at least one field; and generate prompt information based on the generated description information, context information and target system prompt, wherein the context information is included in the prompt information in the form of a reference.

[0115] In some embodiments, the generation description information indicates that the field value of the target field is generated based on the referenced field among multiple fields, and the first determining module 1130 is further configured to, in response to determining that the type of the referenced field is rich text type, convert the field value of the referenced field into field description information represented in a structured computer language based on a predetermined conversion rule; and determine prompt information based on the field description information, the description information, the generation description information and the target system prompt words.

[0116] In some embodiments, the target field is of type rich text, the target system prompt includes explanatory information for structured computer language, and the second determining module 1140 is further configured to obtain model output in structured computer language from the machine learning model; and convert the model output in structured computer language into target rich text content as the field value of the target field based on predetermined conversion rules.

[0117] like Figure 12 As shown, electronic device 1200 is in the form of a general-purpose electronic device. Components of electronic device 1200 may include, but are not limited to, one or more processors or processing units 1210, memory 1220, storage device 1230, one or more communication units 1240, one or more input devices 1250, and one or more output devices 1260. Processing unit 1210 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 1220. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 1200.

[0118] The electronic device 1200 typically includes a plurality of computer storage media. Such media can be removable, non-removable, or a combination thereof and can be volatile or non-volatile. The memory 1220 can be volatile (such as, for example, registers, cache, RAM), non-volatile (such as, for example, ROM, EEPROM, flash memory), or some combination thereof. The storage device 1230 can be a removable or non-removable media, and can include machine readable media such as flash drives, disks, or any other media capable of storing information and / or data and can be accessed within the electronic device 1200.

[0119] The electronic device 1200 can further include additional removable / non-removable, volatile / non-volatile storage media. For example, computer storage media 1245 can be included in the electronic device 1200 in place of, or in addition to, the memory 1220 and / or storage device 1230. Although the exemplary Figure 12 environments, a disk drive unit 1248 and a CD-ROM drive 1249 can be provided, as shown in FIG. 12. In such cases, each can be connected to the bus 1212 by one or more data media interfaces. The memory 1220 can include, for example, a computer program product (e.g., 1225) having computer program code configured to carry out the various methods or acts of the embodiments of the present disclosure.

[0120] The communication unit 1240 enables communications with other electronic devices over a communication medium. Additionally, the functionality of the components of the electronic device 1200 can be implemented in a single computing cluster or a plurality of computer machines capable of communicating over a communication connection. As such, the electronic device 1200 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes.

[0121] The input device 1250 can be one or more input devices such as a mouse, a keyboard, a trackball, etc. The output device 1260 can be one or more output devices such as a display, a speaker, a printer, etc. The electronic device 1200 can further communicate to one or more external devices (not shown) such as a storage device, a display device, etc. through the communication unit 1240, with one or more devices that enable a user to interact with the electronic device 1200, or with any devices (e.g., a network card, a modem, etc.) that enables the electronic device 1200 to communicate with one or more other electronic devices. Such communication can be enabled by an input / output (I / O) interface (not shown).

[0122] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0123] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0124] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0125] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0126] The computer program product of the present disclosure can have a signal including said computer program. This signal can be electronic, electromagnetic, optical, or any other suitable type of signal. Such a signal can be provided through a communication connection, such as electrical wiring, optical fiber, wireless interface, etc. Examples of computer program products include computer program implemented on a personal computer, server, or other networked device. A non-transitory computer readable medium, such as a floppy disk, CD-ROM, DVD-ROM, Blu-ray disk, hard disk, or other memory, can store the computer program.

[0127] Having described several implementations of the present disclosure, it is to be appreciated various alterations, modifications, and improvements will readily occur to those skilled in the art. Such alterations, modifications, and improvements are intended to be part of this disclosure. Accordingly, the foregoing description is by way of example only and is not intended to be limiting. The implementation described herein is implementations of the present disclosure. Other implementations of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the present disclosure. Therefore, this disclosure is intended to cover all such modifications and variations as fall within the scope of the implementations. It is intended that the specification and depicted embodiments are to be considered exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A data processing method for project management, characterized in that, include: Obtain generation description information for a target field in a work item, wherein the work item includes multiple fields, the target field is one of the multiple fields, and the generation description information describes the generation requirements for the field value of the target field; Based on the type of the target field, select the target system prompt word from multiple system prompt words; Based on the generated description information and the target system prompt words, prompt word information for generating field values ​​of the target field is determined, wherein the generated description information indicates that the field values ​​of the target field generate content based on rich text type or that the type of the target field is rich text type, and the prompt word information includes explanatory information for structured computer language, which is used to describe the content of the rich text type, and the explanatory information is used to enable machine learning models to understand the rich text type content; as well as Based on the prompt word information, a machine learning model is used to generate the field value of the target field, and the field value is filled into the target field in the work item; The target field is of the rich text type, the target system prompt includes the explanatory information for the structured computer language, and the field values ​​generated for the target field include: Obtain the model output represented in the structured computer language from the machine learning model; and Based on predetermined conversion rules, the model output, represented in the structured computer language, is converted into target rich text content, which is used as the field value of the target field. The conversion between rich text content and structured computer language is achieved through a rich text conversion tool provided by the component runtime platform. The component runtime platform implements a set of general runtime code based on a browser engine, and runs the rich text conversion tool used by the front end in the back end service.

2. The method according to claim 1, characterized in that, The work item is included in a form having the multiple fields, and obtaining the generated description information includes: In response to receiving a configuration request for the form, the corresponding configuration items for the multiple fields are presented; and The generated description information is determined based on the interaction information received via configuration items for the target field.

3. The method according to claim 1, characterized in that, Determining the prompt word information includes: Based on the generated description information, at least one field among the plurality of fields is determined, wherein the generated description information indicates that the field value of the target field is generated based on the at least one field; Based on the at least one field, determine the context information for generating the field value of the target field; and Based on the generated description information, the context information, and the target system prompt words, the prompt word information is generated, and the context information is included in the prompt word information in the form of a reference.

4. The method according to claim 1, characterized in that, Obtaining the generated description information includes: Present the basic information of the work item, which includes the multiple fields; In response to receiving a selection for the target field, a dialog interface with the digital assistant is presented; and In response to receiving a processing request for the target field via the dialog interface, the generated description information is determined based on the processing request.

5. The method according to claim 4, characterized in that, Also includes: In response to generating a field value for the target field, the field value and operation information related to the field value of the target field are presented, the operation information indicating an update operation for the target field; as well as In response to receiving a selection for the update operation, the determined field value is filled into the target field in the work item.

6. The method according to claim 1, characterized in that, The generated description information indicates that the field value of the target field is generated based on the referenced field among the plurality of fields, and the determined prompt word information includes: In response to determining that the type of the referenced field is the rich text type, based on a predetermined conversion rule, the field value of the referenced field is converted into field description information represented in the structured computer language; and The prompt word information is determined based on the field description information, the explanatory information, the generated description information, and the target system prompt word.

7. The method according to claim 1, characterized in that, The target field includes at least one of the following types: Single choice type, Multiple selection type, Text type, Rich text type.

8. A data processing device for project management, characterized in that, include: The acquisition module is configured to acquire generation description information for a target field in a work item, the work item including multiple fields, the target field being one of the multiple fields, and the generation description information describing the generation requirements for the field value of the target field; The selection module is configured to select a target system prompt word from multiple system prompt words based on the type of the target field. The first determining module is configured to determine prompt word information for generating field values ​​of the target field based on the generated description information and the target system prompt words, wherein the generated description information indicates that the field values ​​of the target field generate content based on a rich text type or that the type of the target field is a rich text type, and the prompt word information includes explanatory information for a structured computer language used to describe the content of the rich text type, and the explanatory information is used to enable a machine learning model to understand the rich text type content; as well as The second determining module is configured to generate the field value of the target field based on the prompt word information using a machine learning model, and fill the field value into the target field in the work item; The target field is of the rich text type, the target system prompt includes the explanatory information for the structured computer language, and the second determining module is further configured to obtain the model output represented in the structured computer language from the machine learning model; and convert the model output represented in the structured computer language into target rich text content based on a predetermined conversion rule, as the field value of the target field; The conversion between rich text content and structured computer language is achieved through a rich text conversion tool provided by the component runtime platform. The component runtime platform implements a set of general runtime code based on a browser engine, and runs the rich text conversion tool used by the front end in the back end service.

9. An electronic device, characterized in that, include: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 7 when executed by the at least one processing unit.

10. A computer-readable storage medium, characterized in that, It stores a computer program that can be executed by a processor to implement the method according to any one of claims 1 to 7.

11. A computer program product, characterized in that, Includes a computer program, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images