Project progress follow-up method

Abstract

The present application provides a method for following up on project progress. The method comprises: determining a superior-subordinate relationship diagram of member objects of a target project. Based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, the work progress information of the member objects' division of labor in the target project is determined from the work emails exchanged between the member objects. The work progress information of the member objects' division of labor in the target project is imported into the superior-subordinate relationship diagram to obtain a progress chart of the target project. The present application can intelligently identify and extract the work progress information of member objects from the work emails of project member objects to generate an intuitively expressed project progress chart.

Description

Technical Field

[0001] The present application relates to the technical field of computer programs, and in particular to a method for following up on project progress. Background Art

[0002] Mobile office can also be called 3A office, which means that employees can handle anything related to work (Anything) at any time (Anytime) and any place (Anywhere) through enterprise information software installed on mobile terminals such as mobile phones and tablets.

[0003] Currently, mobile office requires employees to regularly report work progress to their superiors so that they can have overall control. Since superiors have to manually organize employees' reporting information, it is inevitable that there will be omissions, which in turn affects the judgment of work decisions. Summary of the invention

[0004] The purpose of this application is to provide a project progress follow-up method that can intelligently identify and extract work progress information of project members from their work emails to generate an intuitive project progress chart.

[0005] In order to achieve the above purpose, the embodiment of the present application is implemented as follows: First, a method for following up on project progress is provided, including: Determine the hierarchical relationship diagram of the member objects of the target project; Based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, work progress information of the member objects in the target project is determined from work emails exchanged between the member objects; Import the work progress information of the member objects in the target project into the superior-subordinate relationship diagram to obtain a progress diagram of the target project.

[0006] The embodiment of the present application determines a superior-subordinate relationship diagram of the member objects of the target project, and uses the superior-subordinate relationship given in the superior-subordinate relationship diagram as a reference to determine information related to work plans, work plan deadlines, work completion content, etc. that can reflect the progress of the work from work emails exchanged between member objects; finally, the work progress information of the member objects' division of labor in the target project is imported into the superior-subordinate relationship diagram, and an accurate and intuitive progress diagram of the target project can be obtained, thereby assisting the superior member objects to globally control the target project. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the embodiments of the present application 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 recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0008] Figure 1 A flowchart of a method for following up on project progress according to an embodiment of the present application is shown.

[0009] Figure 2 A schematic diagram of comparing upper and lower levels of the decision tree model according to an embodiment of the present application.

[0010] Figure 3 This is a first schematic diagram for adjusting the superior-subordinate relationship diagram according to an embodiment of the present application.

[0011] Figure 4 This is a second schematic diagram of adjusting the superior-subordinate relationship diagram according to an embodiment of the present application.

[0012] Figure 5 A progress chart of a target project generated by the project progress tracking method of an embodiment of the present application.

[0013] Figure 6 Schematic diagram of the structure of a device for tracking project progress according to an embodiment of the present application.

[0014] Figure 7 A schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] As mentioned above, current mobile office requires employees to report work progress to their superiors regularly so that their superiors can take overall control. Since superiors have to manually organize employees' reporting information (usually summarizing employees' work emails), omissions are inevitable, which in turn affects the judgment of work decisions. In view of this, this application aims to propose a project progress follow-up plan that can intelligently identify and extract member objects' work progress information from their work emails to generate an intuitively expressed project progress chart, thereby avoiding the problems of manual organization that is prone to omissions and time-consuming.

[0016] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. 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 should fall within the scope of protection of this specification.

[0017] An embodiment of the present application provides a method for following up on project progress. Figure 1 This is a flowchart of the follow-up method for the project progress, including the following steps: S102, determining a superior-subordinate relationship diagram of member objects of the target project.

[0018] This embodiment intelligently identifies and extracts the work progress information of the project member objects from their work emails. The work progress information may include, but is not limited to: the work plan proposed by the superior member object, the deadline corresponding to the work plan, and the work completed by the subordinate member object, etc. Therefore, determining the superior-subordinate relationship of the member object can help determine the nature of the work email, so as to purposefully extract the corresponding work progress information.

[0019] For example, a work email sent by a superior member object to a subordinate member object generally includes a work plan and the corresponding deadline for the work plan; a work email sent by a subordinate member object to a superior member object generally includes a work plan and the corresponding deadline for the work plan.

[0020] In a feasible implementation, this embodiment can use artificial intelligence technology to identify corresponding superior-subordinate relationships from work emails exchanged between member objects to generate a superior-subordinate relationship diagram.

[0021] The following is an introduction to the principle of using artificial intelligence technology to generate a hierarchical relationship diagram.

[0022] First, a set of sample work emails interacting between member objects is prepared, in which each sample work email is marked with a superior-subordinate relationship label, and the superior-subordinate relationship label is used to indicate the superior-subordinate relationship between the sender and the recipient of the corresponding sample work email.

[0023] Afterwards, the target deep learning model is trained to recognize the superior-subordinate relationship based on the sample work email set. The training process is: the sample work emails in the sample work email set are input into the target deep learning model, and the target deep learning model attempts to recognize the superior-subordinate relationship between the sender and the recipient of the sample work email. Afterwards, the error between the recognition result of the target deep learning model and the superior-subordinate relationship indicated by the superior-subordinate relationship label is determined, and the model parameters of the target deep learning model are adjusted to reduce the error. By continuously iterating the model parameters in this adjustment method, the recognition result of the target deep learning model can eventually approach the superior-subordinate relationship indicated by the superior-subordinate relationship label, so that it has the ability to recognize the superior-subordinate relationship.

[0024] Correspondingly, after the training is completed, the target work email set is input into the target deep learning model to perform a superior-subordinate comparison on the multiple member objects, and the corresponding superior-subordinate relationship diagram can be determined.

[0025] As an exemplary introduction, the target deep learning model of this embodiment can be a decision tree model. Figure 2 It is a schematic diagram of the comparison between upper and lower levels based on the decision tree.

[0026] Assume that a, b, c, and d represent four member objects. First, take the work emails between member objects a, b, c, and d as input. Based on dimension 1 of superior-subordinate comparison, first find the member object with the highest level (it can also be the member object with the lowest level, which will not be given as an example here), such as member object c; and separate member object c into the left child node, and separate the remaining member objects a, b, and d into the right child nodes.

[0027] Next, using the work emails (including the email body text) between member objects a, b, and d as input, based on dimension 2 of superior-subordinate comparison, find the member object with the highest level among member objects a, b, and d, such as member object d; and separate member object d into a left child node, and separate the remaining member objects a and b into right child nodes.

[0028] Finally, using the work emails between member objects a and b as input, based on the dimension 3 of the superior-subordinate comparison, find the member object with the highest level among member objects a and b, such as member object a; and separate member object a into the left child node, and separate the remaining member object b into the right child node. At this point, the superior-subordinate relationship between member objects a, b, c, and d is determined.

[0029] The above is an exemplary introduction to the comparison of superiors and subordinates in the decision tree. Among them, the dimensions of the comparison of superiors and subordinates can be, but are not limited to: the dimension of work supervision words, the dimension of job title words, and the dimension of tone intensity words, etc., which can all reflect the relationship between superiors and subordinates. For example, when subordinates send work emails to their superiors, they often use honorifics, so the number of honorifics can be used as the dimension of tone intensity words; when superiors send work emails to subordinates, they often contain keywords that urge work (such as tight deadlines, heavy tasks, etc.), so the number of keywords that urge work can be used as the dimension of work supervision words; when subordinates send work emails to their superiors, they often carry job titles (such as General Manager X, Director X, etc.), so the presence or absence of the job in the top title can be used as the dimension of job title words.

[0030] In addition, it should be noted that the decision tree model may include multiple decision trees. For each work email in the target work email set, the email body may be extracted to perform a comparison between the upper and lower levels of each decision tree.

[0031] Here, we take the dimension of tone intensity as an example, and the corresponding formula for comparing superiors and subordinates is:

[0032] in, Represents the decision tree sequence number in the decision tree model; N represents the number of decision trees; Indicates tone intensity; Indicates the height of the current i-th decision tree; Represents the average height of K training samples when training the i-th decision tree; represents a constant; exist When a person uses emails, he or she assumes that work emails are sent from superiors to subordinates, which means that the sender is higher than the recipient in the superior-subordinate relationship.

[0033] exist When a person sends a work email, he or she assumes that the work email is sent from a subordinate to a superior, that is, the recipient is higher than the sender in the superior-subordinate relationship.

[0034] In addition, for the same pair of senders and recipients, if there are both work emails that can be confirmed to be sent from a superior to a subordinate and work emails that can be confirmed to be sent from a subordinate to a superior, the one with the highest percentage will be selected as the superior-subordinate relationship. For example, between sender A and recipient B, there are 5 work emails that can be confirmed to be sent from a superior to a subordinate, and 3 work emails that can be confirmed to be sent from a subordinate to a superior, then sender A is finally confirmed to be the superior of recipient B.

[0035] Based on the decision tree model, it is finally determined Figure 3 The superior-subordinate relationship diagram of the example.

[0036] In addition, in practical applications, this embodiment can also filter irrelevant words and / or perform standardized expression processing on the work emails in the target work email set before inputting them into the decision tree model to ensure the accuracy of the decision tree model. The irrelevant words mentioned here may include colloquial words, stop words, and templated words, which are meaningless for determining the superior-subordinate relationship.

[0037] It should be noted that the superior-subordinate relationship diagram of this embodiment is continuously maintained, and the work plan of the superior leader changes at any time. Therefore, it is necessary to dynamically adjust the superior-subordinate relationship diagram based on subsequent incremental work emails.

[0038] For example, when incremental work emails relative to a target work email set are generated between member objects, the semantic similarity between keywords expressing the start of work in the incremental work emails and the incremental work emails relative to the target work email set is determined.

[0039] If the number of keywords expressing the start of work in the incremental work email is greater than the first quantity threshold and the semantic similarity of the incremental work email to the target work email set is less than the first similarity threshold, it means that the incremental work email may involve new work arrangements, and the original superior-subordinate relationship may change (a new superior appears). At this time, if the sender of the incremental work email is not a root node in the superior-subordinate relationship graph, the sender of the incremental work email can be set as a new root node in the superior-subordinate relationship graph, and the recipient of the incremental work email can be set as the subordinate node corresponding to the new root node. At the same time, the original superior node and the same-level node of the sender of the incremental work email in the superior-subordinate relationship graph can also be removed.

[0040] If the number of keywords expressing the start of work in the incremental work email is greater than the second quantity threshold and the semantic similarity of the incremental work email to the target work email set is greater than the second similarity threshold, it means that the incremental work email does not involve new work arrangements, but there is a possibility of change in the superior-subordinate relationship. At this time, if the sender of the incremental work email is not a secondary root node in the superior-subordinate relationship graph, the sender of the incremental work email will be set as a new secondary root node in the superior-subordinate relationship graph.

[0041] In addition, based on the above, if the newly added root node in the superior-subordinate relationship diagram does not derive a subordinate node within the preset time, it means that the newly added root node may not be accurate and does not involve any work related to the subordinate. In this case, it can be removed from the superior-subordinate relationship diagram.

[0042] The following is an exemplary introduction to the dynamic adjustment of the superior-subordinate relationship diagram.

[0043] Specifically, this embodiment uses a pre-collected dictionary to match the word segmentation of the body of the incremental work email to obtain keywords indicating the start of the project (such as start, develop, etc.); then, the BERT model is used to encode the body of the incremental work email into a vector, and the cosine similarity is calculated with the vectors of the work emails in the last three months. If the number of keywords is greater than T1, and the cosine similarities are less than T2, it means that the incremental work email is the root node of the target project. In the superior-subordinate relationship diagram, the node where the sender of the incremental work email is located is the root node, and its superior and peer nodes are deleted; for example Figure 4 As shown, after determining "Li San" as the new root node, it is necessary to remove the superior node "Zhang San" relative to "Li San" and the peer nodes "Li Si, Li Wu" relative to "Li San" in the original superior-subordinate relationship diagram.

[0044] In addition, the recipient of the incremental work email can be further located as a child node of the root node, and other child nodes that are not located under the root node can be deleted. Figure 5 As shown in the figure, after determining "Li San" as the new root node, it is necessary to remove the upper node "Zhang San" relative to "Li San" and the same-level nodes "Li Si, Li Wu" relative to "Li San" in the original upper-lower relationship diagram. At the same time, in the incremental work mail, only "Zhao Yi, Zhao Er" are the recipients of "Li San", so all the original lower-level nodes of "Li San" can be deleted, and "Zhao Yi, Zhao Er" can be used as the lower-level nodes of "Li San".

[0045] After finding the root node, it is necessary to further update its corresponding secondary root node. The method is to extract the email body from the incremental work email with the root node as the sender, and preprocess and segment the email body, such as removing stop words, unifying expressions, and so on. Then, use the pre-collected dictionary to match the segmentation of the email body to obtain the keywords indicating the start of the project, and use the BERT model to encode the email body into a vector to calculate the cosine similarity with the vectors of work emails in the past three months. If the number of keywords is greater than T3, and the cosine similarity is greater than T4, it means that the recipient in the incremental work email with the root node as the sender is the secondary root node. In addition, considering the dynamic changes, the upper and lower nodes originally involved in the secondary root node that have not appeared in the incremental work emails within a week can also be deleted from the superior-subordinate relationship diagram.

[0046] S104, based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, determine the work progress information of the member objects in the target project from the work emails exchanged between the member objects.

[0047] The work progress information of this embodiment includes: work plan, deadline corresponding to the work plan, and work completion content. Specifically, based on keyword matching or a large language model, the work plan assigned to the subordinate member object and the deadline corresponding to the work plan can be determined from the work email sent by the member object that is the root node and / or sub-root node in the superior-subordinate relationship diagram. And the work completion content of the member object can be determined from the work email sent by the member object that is the subordinate node in the superior-subordinate relationship diagram.

[0048] For example, the work emails sent by the member objects of the root node and / or the sub-root node may be defined as "starting point emails".

[0049] For the standard "starting point email", the name of the member object is matched with the work keywords (such as responsible for, undertake, etc.) to find the work (sentence) that each subordinate member object is responsible for, segment the sentence, and find the keywords belonging to the work arrangement from the segmented words as the work plan, and find the deadline keywords (such as completed, concluded, etc.) and the time before / after the deadline keywords from the segmented words as the deadline.

[0050] For irregular "starting emails", the prompt of the large language model can be set as "Assuming that you are the person who sets the work, please indicate what the work content and deadline are for each person in the following work arrangement?", and submit the "starting email" to the large language model, so that the large language model can filter out the work plan and the deadline corresponding to the work plan according to the guidance of the prompt.

[0051] For another example, a work email sent by a member object that is a lower-level node may be defined as a "non-starting point email".

[0052] For standard "non-starting point emails", the work completion content can be matched from the email body by using keywords that clearly indicate the work has been completed.

[0053] For irregular "non-starting point emails", you can set the prompt of the large language model to "Assuming that you are the executor of the work, when performing XX work, please indicate the progress of XX work in the following work report?" and submit the "non-starting point email" to the large language model, so that the large language model can filter out the completed work content according to the guidance of the prompt words.

[0054] S106, importing the work progress information of the member objects in the target project into the superior-subordinate relationship diagram to obtain a progress diagram of the target project.

[0055] It should be understood that the progress chart determined in this embodiment can intuitively present the work plan and deadline of the work plan proposed by the superior member object, as well as the corresponding work completion content of the subordinate member object.

[0056] For example, in the planning and design of XX (game name), Li San sent the following email to Wang Yi, Wang Er, and Wang San: “Dear colleagues: XX is one of our company's future regular projects. Your work arrangements are as follows: 1. Wang Yi is responsible for determining the theme and target audience, creating the story background, and completing it before February 29, 2024.

[0057] 2. Wang San is responsible for setting up the main characters, designing the plot and tasks, and completing them before February 29, 2024.

[0058] 3. Wang Wu will be responsible for arranging the plot line and ending, and it will be completed before February 29, 2024. " Correspondingly, Wang Er wrote in some work emails: "Hello, Mr. Li: Among the main characters that my team is responsible for, we have completed the designs for the players themselves, teammates, enemies, and NPCs. When designing the characters, we comprehensively consider the characteristics of the characters, such as personality, background, and abilities, to provide players with a richer gaming experience. " Based on the work emails of Li San and Wang Wu, we can generate Figure 5 The progress chart shown. For Li San, he can intuitively view the work plans made for Wang Yi, Wang Er, and Wang San, as well as the work completed by Wang Er, and specify his subsequent work plan based on the work completed by Wang Er. It should be noted that the progress chart of this embodiment is dynamically updated based on the incremental work emails. The update principle can refer to the introduction of the adjustment of the superior-subordinate relationship diagram in the previous article.

[0059] To summarize, the method of this embodiment determines a superior-subordinate relationship diagram of the member objects of the target project, and uses the superior-subordinate relationship given in the superior-subordinate relationship diagram as a reference to determine information related to work plans, work plan deadlines, work completion content, etc. that can reflect the progress of the work from work emails exchanged between member objects; finally, the work progress information of the member objects' division of labor in the target project is imported into the superior-subordinate relationship diagram, and an accurate and intuitive progress diagram of the target project can be obtained, thereby assisting the superior member objects to take global control of the target project.

[0060] Corresponds to Figure 1 The method shown, another embodiment of the present application provides a project progress tracking device. Figure 6 : is a schematic diagram of the structure of the follow-up device 600, comprising: The superior-subordinate relationship determination module 610 is used to determine the superior-subordinate relationship diagram of the member objects of the target project.

[0061] The work progress determination module 620 determines the work progress information of the member objects in the target project from the work emails exchanged between the member objects based on the superior-subordinate relationship given by the superior-subordinate relationship diagram.

[0062] The progress chart generating module 630 is used to import the work progress information of the member objects in the target project into the superior-subordinate relationship chart to obtain the progress chart of the target project.

[0063] Optionally, the superior-subordinate relationship determination module 610 determines a superior-subordinate relationship diagram of member objects of the target project, including: inputting a target work email set interacting between multiple member objects into a target deep learning model to perform a superior-subordinate comparison on the multiple member objects to determine a corresponding superior-subordinate relationship diagram; wherein the target deep learning model is trained based on a sample work email set and a superior-subordinate relationship label annotated on each sample work email in the sample work email set, and the superior-subordinate relationship label is used to indicate the superior-subordinate relationship between the sender and the recipient of the corresponding sample work email.

[0064] Optionally, the target deep learning model is a decision tree model, and the dimensions used for superior-subordinate comparison in the decision tree model include: at least one of a work supervision word dimension, a job title word dimension, and a tone intensity word dimension.

[0065] Optionally, after determining the superior-subordinate relationship graph of the member objects of the target project, the superior-subordinate relationship determination module 610 is also used to: when an incremental work email relative to the target work email set is generated between the member objects, determine the keywords expressing the start of work in the incremental work email and the semantic similarity of the incremental work email relative to the target work email set; if the number of keywords expressing the start of work in the incremental work email is greater than a first quantity threshold, the semantic similarity of the incremental work email relative to the target work email set is less than a first similarity threshold, and the sender of the incremental work email is not a root node in the superior-subordinate relationship graph, then the sender of the incremental work email is set as a new root node in the superior-subordinate relationship graph, and the recipient of the incremental work email is set as a subordinate node corresponding to the new root node.

[0066] Optionally, the superior-subordinate relationship determination module 610 is also used for: if the sender of the incremental work email is set as a new root node in the superior-subordinate relationship diagram, then the original superior node and the same-level node of the sender of the incremental work email in the superior-subordinate relationship diagram are removed.

[0067] Optionally, the superior-subordinate relationship determination module 610 is also used for: if the number of keywords expressing the start of work in the incremental work email is greater than a second number threshold, the semantic similarity of the incremental work email to the target work email set is greater than a second similarity threshold, and the sender of the incremental work email is not a secondary root node in the superior-subordinate relationship graph, then the sender of the incremental work email is set as a new secondary root node in the superior-subordinate relationship graph.

[0068] Optionally, the superior-subordinate relationship determination module 610 is further configured to: remove the root node in the superior-subordinate relationship graph that has not derived a subordinate node for a preset period of time.

[0069] Optionally, the superior-subordinate relationship determination module 610 is also used to: summarize all the incremental work emails relative to the target work email set generated within a specified period window, and remove the nodes in the superior-subordinate relationship diagram that are not senders and / or recipients in all the incremental work emails obtained by summary; wherein the specified period window is located after the time corresponding to the target work email set.

[0070] Optionally, the work progress information includes: a work plan and a deadline corresponding to the work plan; the work progress determination module 620 determines the work progress information of the member objects in the target project from the work emails exchanged between the member objects based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, including: Based on keyword matching or a large language model, a work plan assigned to a subordinate member object and a deadline corresponding to the work plan are determined from work emails sent by member objects that are root nodes and / or sub-root nodes in the superior-subordinate relationship graph.

[0071] Optionally, the work progress information includes: work completion content; the work progress determination module 620 determines the work progress information of the member objects' division of labor in the target project from work emails exchanged between the member objects based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, including: based on keyword matching or a large language model, determining the work completion content of the member object from work emails sent by the member object that is a subordinate node in the superior-subordinate relationship diagram.

[0072] It should be noted that the project progress tracking device of this embodiment can be used as Figure 1 The execution subject of the method shown can thus realize Figure 1 The steps and functions in the method shown are not repeated here.

[0073] Figure 7 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 7At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0074] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0075] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0076] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a follow-up device for the above project progress at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations: Determine the parent-child relationship diagram of the member objects of the target project.

[0077] Based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, work progress information of the member objects' division of labor in the target project is determined from work emails exchanged between the member objects.

[0078] Import the work progress information of the member objects in the target project into the superior-subordinate relationship diagram to obtain a progress diagram of the target project.

[0079] The above application Figure 1The method disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in one or more embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with one or more embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0080] Of course, in addition to software implementation methods, the electronic device of the present application does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0081] The present application also provides a computer program product, which includes a computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the following operations: Determine the parent-child relationship diagram of the member objects of the target project.

[0082] Based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, work progress information of the member objects' division of labor in the target project is determined from work emails exchanged between the member objects.

[0083] Import the work progress information of the member objects in the target project into the superior-subordinate relationship diagram to obtain a progress diagram of the target project.

[0084] In short, the above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the present application shall be included in the protection scope of one or more embodiments of the present application.

[0085] The systems, devices, and modules described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0086] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0087] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0088] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

Claims

1. A project progress follow-up method, characterized in that: include: Determine the hierarchical relationship diagram of the member objects of the target project; Based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, work progress information of the member objects in the target project is determined from work emails exchanged between the member objects; Import the work progress information of the member objects in the target project into the superior-subordinate relationship diagram to obtain a progress diagram of the target project.

2. The method according to claim 1, characterized in that Determine the parent-child relationship diagram of the member objects of the target project, including: Inputting a target work email set interacting between the plurality of member objects into a target deep learning model to compare the plurality of member objects to determine a corresponding superior-subordinate relationship diagram; Among them, the target deep learning model is trained based on a sample work email set and a superior-subordinate relationship label annotated on each sample work email in the sample work email set, and the superior-subordinate relationship label is used to indicate the superior-subordinate relationship between the sender and the recipient of the corresponding sample work email.

3. The method according to claim 2, characterized in that The target deep learning model is a decision tree model, and the dimensions used by the decision tree model for comparison between superiors and subordinates include: at least one of the dimensions of work supervision words, the dimension of job title words, and the dimension of tone intensity words.

4. The method according to claim 1, characterized in that: After determining the superior-subordinate relationship diagram of the member objects of the target project, the method further includes: When incremental work emails relative to the target work email set are generated between the member objects, determining the semantic similarity between a keyword expressing the start of work in the incremental work email and the incremental work email relative to the target work email set; If the number of keywords expressing the start of work in the incremental work email is greater than a first quantity threshold, the semantic similarity of the incremental work email to the target work email set is less than a first similarity threshold, and the sender of the incremental work email is not a root node in the superior-subordinate relationship graph, then the sender of the incremental work email is set as a new root node in the superior-subordinate relationship graph, and the recipient of the incremental work email is set as a subordinate node corresponding to the new root node.

5. The method according to claim 4, characterized in that Also includes: If the sender of the incremental work email is set as a new root node in the superior-subordinate relationship diagram, the original superior node and the same-level node of the sender of the incremental work email in the superior-subordinate relationship diagram are removed.

6. The method according to claim 4, characterized in that Also includes: If the number of keywords expressing the start of work in the incremental work email is greater than a second quantity threshold, the semantic similarity of the incremental work email to the target work email set is greater than a second similarity threshold, and the sender of the incremental work email is not a secondary root node in the superior-subordinate relationship graph, then the sender of the incremental work email is set as a new secondary root node in the superior-subordinate relationship graph.

7. The method according to claim 6, characterized in that Also includes: Root nodes in the superior-subordinate relationship graph that have not derived subordinate nodes for a preset period of time are removed.

8. The method according to claim 6, characterized in that Also includes: Summarize all the incremental work emails relative to the target work email set generated within a specified period window, and remove the nodes in the superior-subordinate relationship diagram that are not senders and / or recipients in all the incremental work emails obtained by summarization; wherein the specified period window is located after the time corresponding to the target work email set.

9. The method according to claim 1, characterized in that: The work progress information includes: a work plan and a deadline corresponding to the work plan; Based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, work progress information of the member objects in the target project is determined from the work emails exchanged between the member objects, including: Based on keyword matching or a large language model, a work plan assigned to a subordinate member object and a deadline corresponding to the work plan are determined from work emails sent by member objects that are root nodes and / or sub-root nodes in the superior-subordinate relationship graph.

10. The method according to claim 1, characterized in that The work progress information includes: work completion content; Based on the superior-subordinate relationship given by the superior-subordinate relationship diagram, work progress information of the member objects in the target project is determined from the work emails exchanged between the member objects, including: Based on keyword matching or a large language model, the work completion content of the member object is determined from the work email sent by the member object as a subordinate node in the superior-subordinate relationship graph.

Images