CN115700659A

CN115700659A - Project feasibility evaluation method, device, equipment and medium

Info

Publication number: CN115700659A
Application number: CN202211118731.7A
Authority: CN
Inventors: 郭红霞; 贾一飞; 杨珂; 林瑶; 冯强
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2022-09-14
Filing date: 2022-09-14
Publication date: 2023-02-07

Abstract

The disclosure provides a project feasibility evaluation method which can be applied to the technical field of artificial intelligence. The method comprises the following steps: responsive to an end of each phase in a lifecycle of the project, obtaining most up-to-date data for the project, wherein the lifecycle of the project comprises a plurality of phases; extracting features from the latest data and establishing a current attribute matrix of the project; and taking the current attribute matrix as the input of the trained machine learning model, and obtaining the feasibility evaluation result output by the machine learning model. The present disclosure also provides a project feasibility assessment apparatus, device, storage medium and program product.

Description

Project feasibility evaluation method, device, equipment and medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly, to a project feasibility assessment method, apparatus, device, medium, and program product.

Background

Existing project review is typically a manual expert review. Generally, the evaluation is carried out by switching into the expert online of the organization business at the initial stage of project establishment or the middle stage of acceptance check and the like, and then the evaluation is simply weighted according to expert rules or multiple factors. The organization evaluated at one time in the evaluation mode takes longer time and has lower efficiency. In addition, for the reason of reducing the organization cost of the review party, a plurality of related projects are generally collected into one batch for one-time review, so that the project review takes longer time and the review is not timely. For example, in the whole life cycle of a project, the project can only be reviewed in the project establishment stage or a plurality of significant progress stages, and the feasibility of the project cannot be evaluated in time in the process of project progress, so that if the project cannot be found in time in the process of project progress if the feasibility requirement is not met, the project can continue to advance, and the waste of resources can be caused.

Disclosure of Invention

In view of the foregoing, the present disclosure provides project feasibility assessment methods, apparatus, devices, media, and program products that improve project review timeliness and efficiency.

In a first aspect of the disclosed embodiments, a 1-project feasibility assessment method is provided. The method comprises the following steps: responsive to an end of each phase in a lifecycle of the project, obtaining most up-to-date data for the project, wherein the lifecycle of the project comprises a plurality of phases; extracting features from the latest data, and establishing a current attribute matrix of the project; and taking the current attribute matrix as the input of the trained machine learning model to obtain the feasibility evaluation result output by the machine learning model.

According to an embodiment of the present disclosure, the method further comprises: when the feasibility assessment result represents that the project is feasible, indicating to continue the next stage of the project; and indicating to pause the project when the feasibility assessment result indicates that the project is not feasible.

According to an embodiment of the present disclosure, said obtaining the latest data of the project in response to the end of each phase in the life cycle of the project comprises: receiving node report data manually reported after each stage of the project is finished; in response to receiving the node report data, sending a notification of reporting the latest data to an implementing user of the project; and acquiring the reported latest data.

According to an embodiment of the present disclosure, the starting phase of the life cycle of the project is an establishment phase, and the sending of the notification of reporting the latest data to the implementation user of the project includes: after the project item standing phase is finished, obtaining item standing information of the project; extracting the value of the matching field by segmenting the standing information of the project; determining an implementation user having a mapping relation with the value of the matching field according to a preset mapping relation between each value in the matching field and the implementation user, so as to obtain the implementation user of the project; assigning the item to a conducting user of the item; and sending a notification for reporting the latest data to the project implementing user.

According to an embodiment of the present disclosure, the sending the notification of reporting the latest data to the implementation user of the project includes: and informing the implementation user of the project to report the latest data according to a preset data table.

According to an embodiment of the present disclosure, the sending the notification of reporting the latest data to the implementation user of the project includes: and informing the implementation user of the project to report the latest data in an online demonstration mode. The obtaining the reported latest data includes: and acquiring the audio data demonstrated on the line, and extracting the latest data from the audio data demonstrated on the line through voice recognition.

According to an embodiment of the present disclosure, after the notifying the implementing user of the project reports the latest data in a manner of online presentation, the method further includes: sending the links of the online demonstration to N expert users, wherein N is an integer greater than or equal to 1; obtaining the scores of the N expert users after the online demonstration is finished; weighting the scores of the N expert users based on expert rules to obtain weighted scores; obtaining an expert evaluation result of the feasibility of the project based on the weighted scores; when the expert evaluation result is consistent with the feasibility evaluation result, determining the feasibility of the project according to the feasibility evaluation result; and when the expert evaluation result is inconsistent with the feasibility evaluation result, replacing the feasibility evaluation result with the expert evaluation result to determine the feasibility of the project, and adjusting parameters of the machine learning model based on the expert evaluation result.

According to an embodiment of the present disclosure, the current attribute matrix of the item includes attribute data of at least one dimension of: progress, cost, information security, human resources, or projected resource requirements.

In a second aspect of the disclosed embodiment, a project feasibility assessment apparatus is provided. The device comprises a first obtaining module, a feature extraction module and a prediction module. The first obtaining module is used for obtaining the latest data of the project in response to the end of each phase in the life cycle of the project, wherein the life cycle of the project comprises a plurality of phases. The feature extraction module is used for extracting features from the latest data and establishing a current attribute matrix of the project. And the prediction module is used for taking the current attribute matrix as the input of the trained machine learning model and acquiring the feasibility evaluation result output by the machine learning model.

In a third aspect of the disclosed embodiments, an electronic device is provided. The electronic device includes one or more processors and memory. The memory is used to store one or more programs which, when executed by the one or more processors, cause the one or more processors to perform the above-described method.

In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is further provided, on which executable instructions are stored, and when executed by a processor, the instructions cause the processor to execute the above method.

In a fifth aspect of the embodiments of the present disclosure, there is also provided a computer program product comprising a computer program which, when executed by a processor, implements the above method.

One or more of the embodiments described above have the following advantages or benefits: the problem that the traditional offline evaluation usually needs to wait for a batch of projects to progress more or less before centralized organization offline evaluation and timely evaluation management of the full life cycle of the projects is difficult to realize is solved, the feasibility of the projects can be automatically judged in real time by synchronously inputting the data of each stage into a machine learning model after being updated according to the respective frequency of the data of each stage in the full life cycle of the projects, the output result is updated, and the management and tracking of the full life cycle of the projects are realized.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, taken in conjunction with the accompanying drawings of which:

FIG. 1 schematically illustrates an application scenario diagram of a project feasibility assessment method, apparatus, device, medium, and program product according to embodiments of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a project feasibility assessment method according to an embodiment of the present disclosure;

fig. 3 schematically shows a structural diagram of a BP neural network used for constructing a machine learning model in a project feasibility assessment method according to an embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating the use of a trained machine learning model to predict project feasibility in a project feasibility assessment method according to an embodiment of the present disclosure;

FIG. 5 schematically illustrates a flow chart of obtaining the latest data of a project in a project feasibility assessment method according to an embodiment of the present disclosure;

FIG. 6 schematically illustrates a flow diagram for notifying an implementing user of an item to report the most up-to-date data of the item after the completion of an establishment phase according to another embodiment of the disclosure;

FIG. 7 schematically illustrates a flow diagram of a project feasibility assessment method according to yet another embodiment of the present disclosure;

FIG. 8 schematically illustrates a block diagram of a project feasibility assessment apparatus according to an embodiment of the present disclosure; and

FIG. 9 schematically illustrates a block diagram of an electronic device suitable for implementing a project feasibility assessment method in accordance with an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "A, B and at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include, but not be limited to, systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features.

The embodiment of the disclosure provides a project feasibility assessment method, a project feasibility assessment device, a project feasibility assessment apparatus, a project feasibility assessment medium and a program product. According to the embodiment of the disclosure, the feasibility of the project can be automatically predicted and evaluated by using the trained machine learning model at the end of each stage of the project, so that the tracking and evaluation of the full life cycle of the project can be realized, and the timeliness and efficiency of project evaluation are improved.

Fig. 1 schematically illustrates an application scenario diagram of a project feasibility assessment method, apparatus, device, medium, and program product according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, an application scenario 100 according to this embodiment may include a first terminal 101, a server 102, and a database 103 or a second terminal 104. The connection between the first terminal 101 and the server 102, and between the server 102 and the database 103 or the second terminal 104, may be through a wired network or a wireless network.

The server 102 may perform a project feasibility assessment method according to an embodiment of the present disclosure. Specifically, after each stage of the project is finished, the server 102 may automatically obtain the latest data of the project from the database 103, or may manually send a notification of reporting data to the second terminal 104 used by the implementing user of the project, and receive the latest data reported by the implementing user of the project using the second terminal 104. The server 102 may then evaluate the feasibility of the project using the trained machine learning model based on the processing of the up-to-date data, and then present the staged feasibility evaluation results of the project to the project progress decision user via the first terminal 101. Accordingly, project feasibility assessment apparatus, devices, media and program products according to embodiments of the present disclosure may be deployed in the server 102.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for an implementation.

The project feasibility assessment method of the embodiment of the present disclosure will be described in detail below with reference to fig. 2 to 7 based on the scenario described in fig. 1.

FIG. 2 schematically shows a flow diagram of a project feasibility assessment method according to an embodiment of the disclosure.

As shown in fig. 2, a project feasibility assessment method according to an embodiment of the present disclosure may include operations S210 to S230.

First, in operation S210, the most recent data for a project is obtained in response to the end of each phase in the project' S lifecycle. The up-to-date data for a project may include various data that the project has implemented (such as progress, cost consumption, problems and solutions that occur in progress, completion of a plan, or the degree to which it is consistent or departed from a plan or expectation, etc.), as well as subsequent planning data (such as resources required for the next stage to be predicted, time to be predicted, human and material investment to be predicted, smoothness of progress to be predicted, or degree to which it departs from an expectation, etc.).

The lifecycle of a project may include multiple phases. In conventional project review, the life cycle of a project may generally include an establishment phase, a middle acceptance phase, and a final acceptance phase after the project is over. According to the embodiment of the disclosure, the division of the phases in the life cycle of the project can be more detailed, and more phases can be further divided in addition to the project standing phase, the middle acceptance phase and the final acceptance phase after the project is finished. For example, the development or development of one task in a project may be divided into one stage, and when different tasks have a parallel relationship, corresponding stages may also have a parallel relationship. Thus, the stages of the project may not be in a single upstream-downstream series relationship. For another example, a plurality of tasks that can be developed in parallel in a project may be grouped into one stage, and tasks that cannot be developed in parallel may be grouped into different stages.

In some embodiments, obtaining project update data may be automated. For example, server 102 may be coupled to various databases (e.g., database 103) and, after a phase of a project has ended, server 102 may automatically crawl the latest data for the project from the databases that record various data for the project in response to receiving information that characterizes the project after the phase of the project has ended. In this case, the server 102 is usually informed of information such as a database address, a data table, and a data field that needs to be crawled, which are configured in advance.

In other embodiments, the acquisition of the latest data of the project may be manually reporting the data. For example, after each phase of the project is over, the most recent data of the project is reported to the server 102 by the project-enforcing user using the second terminal 104.

Then, in operation S220, features are extracted from the latest data, and a current attribute matrix of the item is established.

The current attribute matrix for the item may include attribute data for at least one of the following dimensions: progress, cost, information security, human resources, or projected resource requirements.

The data for the progress dimension may include a rate of schedule execution deviation, a progress performance index, and/or a progress deviation project schedule detail, among others.

The data of the cost dimension can be characterized by cost function development progress information, and can include resource flow rate, resource load rate, resource utilization rate, cost performance index and/or cost deviation.

The data of the information security dimension can include physical security, network security, data security, application security, management security, and/or personnel security in the execution of the project.

The data for the human resources dimension may include personnel status information, including human resources index information, average daily output labor, average productivity, and/or overtime percentage, entered into the project.

According to one embodiment of the present disclosure, the created attribute matrix is shown in table 1 below, which contains data of progress, cost, information security, human resource indicator, and user dimension.

According to an embodiment of the present disclosure, the indexes listed in table 1 may be extracted from the latest data of the item to obtain data of each dimension in the current attribute matrix in operation S220.

TABLE 1

In some embodiments, when some index values are extracted from the latest data of the item and are non-quantized data (such as data of an information security dimension in table 1), the values of the indexes may be quantized in a predetermined data normalization manner, and then the quantized data may be used as the index value of the dimension in the attribute matrix. For example, the data of the information security dimension in table 1 above may be converted into numerical data according to a predetermined level.

In one embodiment, the index data of the information security dimension can be converted into numerical index data by scoring each item from 1 to 5 as listed in table 2 below, and accumulating all indexes.

TABLE 2

Next, in operation S230, a feasibility evaluation result output by the machine learning model is obtained by using the current attribute matrix as an input of the trained machine learning model. The machine learning model is a pre-trained model for evaluating and predicting the feasibility of a project at any stage in the lifecycle.

In one embodiment, a BP (back propagation) neural network may be selected for use in constructing the machine learning model. The structure of the BP neural network can refer to the schematic diagram of fig. 3.

Fig. 3 schematically shows a structural diagram of a BP neural network used for constructing a machine learning model in a project feasibility assessment method according to an embodiment of the present disclosure.

As shown in fig. 3, the BP network consists of an input layer, a hidden layer and an output layer, and the hidden layer may have one or more layers. The network selects an S-shaped transfer function as shown in the following formula (1):

continuously adjusting the network weight and the threshold value through a back propagation error function shown in the formula (2) to enable an error function E to be minimum,

in equation (2), ti is the desired output and Oi is the calculated output of the network.

The BP neural network has high nonlinearity and strong generalization capability, but also has the defects of low convergence speed, more iteration steps, easy falling into local minimum, poor global search capability and the like. The BP neural network can be optimized by using a genetic algorithm, a better search space is found in an analysis space, and then the BP neural network is used for searching an optimal solution in a smaller search space.

Fig. 4 schematically illustrates a schematic diagram of predicting feasibility of a project using a trained machine learning model in a project feasibility assessment method according to an embodiment of the present disclosure.

And (3) building a machine learning model by using a BP neural network, training the model by using data and feasibility evaluation results of a large number of historical projects at each stage, and outputting the trained model after continuously adjusting the network weight and the threshold value by a back-propagation error function to enable the error function E to be minimum. And then may be used for project feasibility prediction in operation S230.

Specifically, during training, data of a large number of historical items and feasibility evaluation results at each stage can be collected. Wherein the phases should include all phases within the life cycle of the item under prediction. The feasibility evaluation result of the historical project at each stage may be preferably a manual evaluation result if the result of the past manual review is available for reference, or may be a feasibility evaluation result of a corresponding stage deduced in conjunction with the intermediate acceptance or final acceptance of the historical project if the result of the manual review is not available (for example, the manual review is not performed before some stages because the stage division is more detailed).

And then, processing the collected original data in the same way of extracting features, and constructing an attribute matrix of each historical item at a corresponding stage. Specifically, the process of constructing the attribute matrix through data processing is similar to the process of extracting the current attribute matrix from the latest data of the project in operation S220, and is not described herein again.

And dividing the processed data into training data and test data, wherein the training data is used for model training, and the test data is used for testing whether the training accuracy of the model meets the requirement. Specifically, firstly, the algorithm model weight (namely the weight occupied by each input parameter during fitting), the threshold value and the data normalization are initialized, and the original weight is obtained according to the training data. The training data is then input into the BP neural network. And then inputting the test data into the BP neural network to obtain output data after the precision of the algorithm model reaches the requirement and stopping iteration. And finally, performing inverse normalization on the obtained data to obtain predicted data. And when the accuracy of the prediction result in the test data reaches a preset requirement, determining that the model training is finished.

And when the model is solved, each index of the attribute matrix of each historical item in the training data is used as an input, and the feasibility evaluation result of the historical item is used as an output.

When the attribute matrix includes data of 5 dimensions as shown in table 1, the number of nodes of the input layer is 5, and the number of nodes of the output layer is 1.

Relevant researches show that a BP neural network with a hidden layer can approximate a nonlinear function with any precision as long as hidden nodes are enough. Therefore, in one embodiment of the present disclosure, a three-layer multi-input single-output BP neural network with one hidden layer may be used to build a prediction model. In the network design process, the determination of the number of hidden layer neurons is very important. Too many hidden layer neurons will increase the network computation and easily generate overfitting problem. If the number of the neurons is too small, the network performance is affected and the expected effect cannot be achieved. The number of hidden layer neurons in the network has a direct link to the complexity of the real problem, the number of neurons in the input and output layers, and the setting of the expected error. At present, there is no clear formula for determining the number of neurons in the hidden layer, and only some empirical formulas exist, and the final determination of the number of neurons still needs to be determined according to experience and multiple experiments. In one embodiment, the problem of selecting the number of hidden neurons is referred to an empirical formula shown in the following equation (3):

wherein n is the number of neurons in the input layer, m is the number of neurons in the output layer, and a is a constant between [1 and 10 ]. The number of the neurons can be calculated to be between 3 and 12 according to the formula (3). According to one embodiment of the present disclosure, the number of hidden layer neurons is selected to be 8.

The trained model may be used in operation S230 for project feasibility prediction, in this way enabling automatic assessment of project feasibility. Therefore, the project feasibility prediction algorithm based on factors such as project progress, cost and information safety can be constructed, the BP neural network model can be applied to project feasibility prediction, and project feasibility can be predicted more accurately. And optimizing the BP neural network through a genetic algorithm to find out a better search space in an analysis space, and searching an optimal solution in a smaller search space by using the BP neural network, thereby further improving the accuracy of project feasibility prediction.

According to the embodiment of the disclosure, the model can be synchronously input after the frequency of the data of each stage is updated in the whole life cycle of the project, and the model judges the feasibility of the project in real time according to the latest data and updates the output result.

According to the method disclosed by the embodiment of the disclosure, the project can be automatically evaluated in time after each stage is finished by utilizing the machine learning model, so that the problem that the project needs to be intensively organized and evaluated in a line when a batch of projects are almost developed in the conventional offline evaluation is avoided, and the project is usually evaluated only in one or more important stages of one project implementation and is difficult to realize the timely evaluation management of each stage of the whole life cycle of the project.

Further, in some embodiments, when the feasibility assessment result characterizing item in operation S230 is feasible, it is indicated to continue the next stage of the item, and when the feasibility assessment result characterizing item in operation S230 is not feasible, it is indicated to suspend the item. Of course, in other implementations, when the project division stages are more detailed, or considering various uncertainties and other factors that may exist in the project process, the feasibility assessment result in operation S230 may be used as a record, and when the feasibility assessment results of two or more stages in succession are not passed, the project is indicated to be suspended. Whether the project is continued or not is determined according to the feasibility evaluation result predicted by the machine learning model, and timely discovery is facilitated at the early stage of the fact that the project is infeasible, so that measures can be timely taken, for example, the project is paused or the project is redesigned and then the project is started again, and therefore resource waste caused by the fact that the infeasible factors in the project are difficult to timely discover can be avoided.

Fig. 5 schematically shows a flowchart for acquiring latest data of a project in a project feasibility assessment method according to an embodiment of the present disclosure.

As shown in fig. 5, according to this embodiment, the obtaining of the latest data of the project in operation S210 may be implemented by means of manual semi-automation, and specifically may include operations S501 to S503.

First, in operation S501, node report data manually reported after each stage of a project is completed is received. The node report data is used to characterize the end of a phase of the project.

Then, in response to receiving the node report data, a notification of reporting the latest data is transmitted to the implementing user of the project in operation S502.

In one embodiment, if the user reporting data by the reporting node is the same user as the user implementing the project, a notification may be sent to the user reporting data by the reporting node.

However, in other embodiments, the user reporting the data by the reporting node is not always the same user as the user implementing the project, so that the user implementing the project may be identified and then a notification may be sent to the user implementing the project in operation S502. For example, in the project establishment phase, usually a business demander or a research and development planning management department leads to project establishment, and the established project is distributed to different IT departments or research and development teams for research and development, in this case, the business demander or the research and development planning management department submits node report data after the project establishment is finished, and in operation S502, a notification of acquiring the latest data is sent to the IT department or the research and development team that undertakes the project. For another example, different stages of the project may be assumed by different implementation users, a former implementation user may report the node report data after the development of the stage assumed by the former implementation user is completed, and then the implemented data of the project is transferred to a latter implementation user of the project in an equal flow manner, and the latter implementation user arranges the next implementation plan data according to the implemented data and the next development task. In this case, in operation S502, a notification may be sent to the subsequent implementation user of the project, and the project implemented data and the subsequent implementation plan data may be acquired together from the subsequent implementation user.

Next, in operation S503, the latest data reported is obtained.

In one embodiment, the fulfillment user of the project may be notified to report the latest data according to a predefined data table.

In another embodiment, the user of the project may be notified to report the latest data in the form of an online presentation, and then the audio data of the online presentation may be acquired and the latest data may be extracted from the audio data of the online presentation through speech recognition. For example, audio data of an online presentation is converted into text information by a speech-to-text technology (speech-to-text), and then data in respective fields as shown in tables 1 and 2, and the like are extracted from the text information. The online report demonstration mode can continue the project display mode in the traditional review for the implementation user without changing the project report habit of the implementation user.

FIG. 6 schematically illustrates a flow diagram for notifying an implementing user of an item to report the most up-to-date data of the item after the completion of an establishment phase according to another embodiment of the disclosure.

As shown in fig. 6, the beginning stage of the life cycle of the project is the project establishment stage, and after the project establishment stage is finished, the operation S502 of sending the notification of reporting the latest data to the project implementing user may include operations S601 to S605.

First, in operation S601, after the project establishment phase is finished, project establishment information is acquired. The standing information of the item may include information of a name, a type, a function, or a purpose of the item. Project standing information may be provided by business demanders or business sales or project aggregation organizations, rather than by the implementing users of the project.

In some embodiments, when the project-enforcing user is included in the interest information, the enforcing user can be determined from the interest information. In yet other embodiments, the information may not include information about the user of the project. For example, mechanisms in large enterprises are relatively complex. When a business demander or a research and development plan management department puts forward an establishment requirement, information such as the type, purpose, function and the like of a project can be directly determined, and the establishment information of the project can be compiled according to the establishment requirement specification in an enterprise. The implementing user of the project can then be determined by word segmentation and matching in the following operations.

Specifically, in operation S602, a value of the matching field is extracted by performing word segmentation on the standing item information of the item.

Next, in operation S603, according to the mapping relationship between each value in the preset matching field and the implementation user, the implementation user having the mapping relationship with the value of the matching field is determined, so as to obtain the implementation user of the item.

The matching field may comprise, for example, any one or combination of fields in the project clause information. In one embodiment, the enforcing user of an item may be mapped by a value to a certain bit in the item number, in which case the matching field is the number of the item. Or in other embodiments, the primary implementation user may be located by a value of a specific bit in the item number, and then the secondary implementation user of the item may be associated by the item type, where the primary implementation user may be a superior unit of the secondary implementation user. In this case, the matching field is a combination of an item number and an item type.

In one embodiment, in the process of assigning the implementation users of the project by segmenting the standing information of the project and assigning the implementation users of the project, the implementation users of the project can be assigned according to the organizational structure of the enterprise. Firstly, the project is distributed to corresponding departments according to a preset mapping relation by analyzing the item standing information of the project, so that feasibility analysis initial data is obtained. In the process of distributing the projects, the standing information of the projects is segmented, the project type information, the project name information and the project association information are respectively obtained through the segmentation, and the projects are automatically distributed to corresponding departments according to the projects and the preset mapping relation.

In one embodiment, the example of the logic for determining the matching field is as follows: and when the project type is a conventional project, directly distributing the project type to first-level personnel of the enterprise, and creating a task list of the persons to be processed for the first-level personnel. When the project type is a simplified project, the simplified project can be directly distributed to the second-level personnel (department members) of the enterprise according to the application English abbreviation in the last bracket in the project name and the mapping table of application-department room. When the item type is associated with the conventional item, the association relationship is firstly judged: (a) If the annual innovation plan is not related or a responsible person cannot be obtained, judging and automatically distributing to department personnel according to the following rule sequence: i) A corresponding department at a scientific and technological research and development department ii) a demand proposing department iii) a comprehensive administration department iiii) to distribute the missed rules to the first-level personnel of the enterprise; the project type is a related simplified project, whether the handover requirement is included is judged, and if yes, the project type is directly distributed to a product line responsible person where the requirement handover person is located; if not, automatically distributing according to the parameters in the step (b). And for the simplified project, secondary judgment can be carried out, wherein whether the flow field is light or not is further judged, if not, a time field is given, regular reminding is carried out, and a project establishment feedback result is obtained due to expiration. If so, the time field is empty and periodically closed.

For the processing of non-first-time project allocation and the processing of backtracking, closing and the like encountered in the distribution flow, when project standing allocation is restarted, the project standing allocation is automatically allocated to the last distribution node, namely breakpoint re-lifting, and the project standing allocation is not required to be re-allocated.

Next, after the project user is determined, in operation S604, the project is assigned to the project user.

Finally, in operation S605, a notification for reporting the latest data is sent to the implementation user of the project. After the project establishment phase is finished, more effective data in the data reported by the user are project planning data, such as predicted human resource indexes, user and information safety data.

The embodiment of the disclosure can automatically determine the implementation user of the project in a way of segmenting the standing information of the project. The distribution of the project can be performed quickly and efficiently for the case where the user is not explicitly given at the time of project establishment. In this way, the project can be automatically transferred to the corresponding department or the responsible person of the department through the comprehensive analysis of the information of project establishment, and meanwhile, the department is informed to collect the feedback data, so that the latest data of the project can be conveniently and timely collected.

FIG. 7 schematically shows a flow diagram of a project feasibility assessment method according to yet another embodiment of the present disclosure.

As shown in fig. 7, according to the embodiment, the project feasibility method may include operations S701 to S702, operations S713 to S716, operations S723 to S726, and operations S707 to S710.

First, in operation S701, node report data manually reported after each stage of a project is completed is received. Reference may be made specifically to the description of operation S501 above.

In operation S702, the user is notified of the implementation of the project to report the latest data in the manner of an online presentation.

The feasibility of the project can then be evaluated by two parallel paths. One is automatic evaluation by using a machine learning model, and the other is continuous manual evaluation. This review using two parallel paths can be used for review of certain stages (e.g., items progressing to mid-term), or for review of full life cycles of certain significant items.

Specifically, the flow of automatic evaluation using the machine learning model may include operations S713 to S716.

In operation S713, audio data for the online presentation is acquired.

In operation S714, the latest data is extracted through voice recognition from the audio data presented on-line. The text information may be converted by a speech to text technology (speech to text), and then data in the respective fields as shown in table 1 and table 2 are extracted from the text information.

In operation S715, features are extracted from the latest data, and a current attribute matrix of the item is established. Reference may be made specifically to the description of operation S220 above.

In operation S716, the feasibility assessment result output by the machine learning model is obtained by using the current attribute matrix as an input of the trained machine learning model. Reference is made in particular to the description relating to operation S230 described above.

The process of manual review includes operations S723 to S726.

In operation S723, the links or videos demonstrated on the line are transmitted to N expert users, where N is an integer greater than or equal to 1;

in operation S724, scores of the N expert users are acquired after the online presentation is finished.

In operation S725, the scores of the N expert users are weighted based on the expert rules, resulting in weighted scores. The expert rules may be expert rules used in conventional offline reviews, for example, setting different weights for each expert's score based on the expert's business domain or the expert's seniority, experience level, etc.

In operation S726, an expert evaluation result of the feasibility of the project is obtained based on the weighted scores. For example, a maximum score may be set in advance, and then whether a project is feasible or not may be determined according to whether the ratio of the weighted score to the maximum score is above or below a preset feasibility ratio value.

In operation S707, it is determined whether the expert evaluation result coincides with the feasibility evaluation result. If so, operation S708 is performed; if not, operations S709 to S710 are performed.

In operation S708, when the expert evaluation result coincides with the feasibility evaluation result, the feasibility of the project is determined with the feasibility evaluation result.

In operation S709, when the expert evaluation result is inconsistent with the feasibility evaluation result, the feasibility evaluation result is replaced with the expert evaluation result to determine the feasibility of the project. And adjusts parameters of the machine learning model based on the expert evaluation result in operation S710.

In this way, automatic review and manual review based on the machine learning model can be combined with each other by means of online demonstration. And when the result of the automatic evaluation conflicts with the result of the manual evaluation, the result of the manual evaluation is taken as the standard. Meanwhile, the parameters of the machine learning model are adjusted according to the artificial evaluation result, so that the result of automatic evaluation by using the artificial intelligence model is more intelligent.

Based on the project feasibility assessment method, the disclosure also provides a project feasibility assessment device. The apparatus will be described in detail below with reference to fig. 8.

Fig. 8 schematically shows a block diagram of a project feasibility assessment apparatus 800 according to an embodiment of the present disclosure.

As shown in fig. 8, the project feasibility assessment apparatus 800 of this embodiment includes a first acquisition module 810, a feature extraction module 820, and a prediction module 830. The apparatus 800 may be used to perform the methods described with reference to fig. 2-7.

The first obtaining module 810 is configured to obtain the most recent data of the project in response to an end of each phase in a lifecycle of the project, where the lifecycle of the project includes a plurality of phases. In one embodiment, the first obtaining module 810 may perform the operations S210, S501 to S503, or the operations S701, S702, S713, and S714 described above.

The feature extraction module 820 is used to extract features from the latest data and establish a current attribute matrix of the project. In one embodiment, the feature extraction module 820 may perform operation S220 or operation S715 described previously.

The prediction module 830 is configured to use the current attribute matrix as an input of the trained machine learning model to obtain a feasibility evaluation result output by the machine learning model. In one embodiment, the prediction module 830 may perform operations S230 and S716 described previously.

According to another embodiment of the present disclosure, the project feasibility assessment apparatus 800 may further comprise an indication module. The indicating module is used for indicating to continue the next stage of the project when the feasibility evaluation result represents that the project is feasible; and indicating to suspend the project when the feasibility assessment result indicates that the project is not feasible.

According to still another embodiment of the present disclosure, the first obtaining module 810 may further include a first receiving unit, a first notifying unit, and a first obtaining unit.

The first receiving unit is used for receiving node report data manually reported after each stage of the project is finished.

The first notification unit is used for responding to the received node report data and sending a notification of reporting the latest data to the implementation user of the project. According to an embodiment of the present disclosure, the starting phase of the life cycle of the project is an item standing phase, and the first notification unit may be specifically configured to: after the project establishment phase is finished, acquiring project establishment information, performing word segmentation on the project establishment information, extracting values of matching fields, determining implementation users having mapping relations with the values of the matching fields according to the mapping relations between each value in the preset matching fields and the implementation users, so as to obtain the implementation users of the projects, distributing the projects to the implementation users of the projects, and sending a notification for reporting latest data to the implementation users of the projects.

The first obtaining unit is used for obtaining the reported latest data.

In one embodiment, the first notification unit may be specifically configured to notify the implementing user of the item to report the latest data according to a predetermined data table.

In another embodiment, the first notification unit may also be used to notify the implementing user of the item to report the latest data in an online presentation. Accordingly, the first acquisition unit may be configured to acquire audio data presented on-line and extract latest data from the audio data presented on-line through speech recognition.

According to an embodiment of the present disclosure, any plurality of the first obtaining module 810, the feature extracting module 820, the predicting module 830, and the indicating module may be combined into one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first obtaining module 810, the feature extracting module 820, the predicting module 830 and the indicating module may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware and firmware, or an appropriate combination of any several of them. Alternatively, at least one of the first obtaining module 810, the feature extraction module 820, the prediction module 830 and the indication module may be at least partially implemented as a computer program module, which when executed, may perform a corresponding function.

FIG. 9 schematically illustrates a block diagram of an electronic device 900 suitable for implementing a project feasibility assessment method in accordance with an embodiment of the present disclosure.

As shown in fig. 9, an electronic apparatus 900 according to an embodiment of the present disclosure includes a processor 901 which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 902 or a program loaded from a storage portion 908 into a Random Access Memory (RAM) 903. Processor 901 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 901 may also include on-board memory for caching purposes. The processor 901 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to embodiments of the present disclosure.

In the RAM 903, various programs and data necessary for the operation of the electronic apparatus 900 are stored. The processor 901, ROM 902, and RAM 903 are connected to each other by a bus 904. The processor 901 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM 902 and/or the RAM 903. Note that the programs may also be stored in one or more memories other than the ROM 902 and the RAM 903. The processor 901 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

Electronic device 900 may also include input/output (I/O) interface 905, input/output (I/O) interface 905 also connected to bus 904, according to an embodiment of the present disclosure. The electronic device 900 may also include one or more of the following components connected to the I/O interface 905: an input portion 906 including a keyboard, a mouse, and the like; an output section 907 including components such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a LAN card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the I/O interface 905 as necessary. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 910 as necessary, so that a computer program read out therefrom is mounted into the storage section 908 as necessary.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement a method according to an embodiment of the disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 902 and/or the RAM 903 described above and/or one or more memories other than the ROM 902 and the RAM 903.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. When the computer program product runs in a computer system, the program code is used for causing the computer system to realize the method provided by the embodiment of the disclosure.

The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 901. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, and downloaded and installed through the communication section 909 and/or installed from the removable medium 911. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 909 and/or installed from the removable medium 911. The computer program, when executed by the processor 901, performs the above-described functions defined in the system of the embodiment of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. A project feasibility assessment method, comprising:

responsive to an end of each phase in a lifecycle of a project, obtaining latest data for the project; wherein the lifecycle of the project comprises a plurality of phases;

extracting features from the latest data and establishing a current attribute matrix of the project; and

and taking the current attribute matrix as the input of the trained machine learning model, and obtaining the feasibility evaluation result output by the machine learning model.

2. The method of claim 1, wherein the method further comprises:

when the feasibility assessment result represents that the project is feasible, indicating to continue the next stage of the project; and

when the feasibility assessment result indicates that the project is not feasible, indicating to pause the project.

3. The method of claim 1, wherein said obtaining the most recent data for the project in response to the end of each phase in the project's lifecycle comprises:

receiving node report data manually reported after each stage of the project is finished;

in response to receiving the node report data, sending a notification of reporting the latest data to an implementing user of the project; and

and acquiring the reported latest data.

4. The method of claim 3, wherein the beginning phase of the life cycle of the project is a standing phase, and the sending the notification of reporting the latest data to the implementing user of the project comprises:

after the project establishment stage is finished, acquiring project establishment information of the project;

extracting the value of the matching field by segmenting the standing information of the project;

determining an implementation user having a mapping relation with the value of the matching field according to a preset mapping relation between each value in the matching field and the implementation user, so as to obtain the implementation user of the project;

assigning the item to a conducting user of the item; and

and sending a notice for reporting the latest data to the implementation user of the project.

5. The method of claim 3 or 4, wherein said sending a notification to an enforcing user of said project to report said latest data comprises:

and informing the implementation user of the project to report the latest data according to a preset data table.

6. The method of claim 3 or 4,

the sending the notification of reporting the latest data to the implementation user of the project includes: informing the implementation user of the project to report the latest data in an online demonstration mode;

the obtaining the reported latest data includes: acquiring audio data demonstrated on the line; and extracting the latest data from the audio data presented on the line through voice recognition.

7. The method of claim 6, wherein after said notifying an implementing user of said project reports said most recent data in an online presentation, said method further comprises:

sending the links of the online demonstration to N expert users, wherein N is an integer greater than or equal to 1;

obtaining the scores of the N expert users after the online demonstration is finished;

weighting the scores of the N expert users based on expert rules to obtain weighted scores;

obtaining an expert evaluation result of the feasibility of the project based on the weighted scores;

when the expert evaluation result is consistent with the feasibility evaluation result, determining the feasibility of the project according to the feasibility evaluation result; and

when the expert evaluation result is inconsistent with the feasibility evaluation result, the feasibility evaluation result is replaced by the expert evaluation result to determine the feasibility of the project, and parameters of the machine learning model are adjusted based on the expert evaluation result.

8. The method of claim 1, wherein the current attribute matrix of items includes attribute data for at least one of the following dimensions: progress, cost, information security, human resources, or projected resource requirements.

9. A project feasibility assessment apparatus comprising:

a first obtaining module for obtaining the latest data of the project in response to the end of each phase in the life cycle of the project; wherein the lifecycle of the project comprises a plurality of phases;

the feature extraction module is used for extracting features from the latest data and establishing a current attribute matrix of the project;

and the prediction module is used for taking the current attribute matrix as the input of the trained machine learning model and acquiring the feasibility evaluation result output by the machine learning model.

10. An electronic device, comprising:

one or more processors;

a memory for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-8.

11. A computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method of any one of claims 1 to 8.

12. A computer program product comprising computer program instructions which, when executed by a processor, implement the method of any one of claims 1 to 8.