Project management method and system

Abstract

The invention provides a project management method and system, and the method comprises the steps: obtaining a scene demand of a project, carrying out the feature layering collection according to the scene demand, and generating a project fingerprint vector; constructing a single-person ability portrait, determining a professional team ability aggregation portrait according to the single-person ability portrait, and generating a resource ability portrait vector; according to the item fingerprint vector, calculating a scene reference proportion of each specialty; constructing a nonlinear bearing function for each specialty, calculating the bearing degree, and dynamically adjusting the scene reference proportion by using the bearing degree to obtain a preliminary correction proportion; for each specialty, extracting a historical case, similar to the current project scene, of the corresponding specialty, and determining a deviation correction factor; according to the deviation correction factor, correcting the preliminary correction proportion to obtain a final proportion; and performing normalization processing on the final proportions of all professions, and generating a distribution coefficient table, thereby finally solving the problem of unreasonable workload distribution caused by a fixed workload distribution proportion coefficient.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of project management, and particularly relates to a project management method and system. BACKGROUND

[0002] Project management refers to a comprehensive and overall project management process carried out to ensure that various works of a project can be coordinated and cooperated organically. In project management, workload allocation and performance allocation are usually involved.

[0003] Generally, the workload needs to be quantified and allocated, and the workday is taken as a unified unit of measurement of the workload, and the workday calculation rules in various scenarios are specified in detail. Then, the performance allocation is calculated according to the preset calculation formula according to the workload (workday).

[0004] In the prior art, a proportion table is established when allocating various stages of various professions in a project, and corresponding coefficients are provided in the table to allocate according to the set coefficients. For example, for a traffic port project, the allocation proportion coefficient of the whole profession in the preliminary design stage is 0.15, the allocation proportion coefficient of the building profession is 0.55, the allocation proportion coefficient of the structure profession is 0.05, the allocation proportion coefficient of the water supply and drainage profession is 0.27, the allocation proportion coefficient of the heating and ventilation profession is 0.05, and the allocation proportion coefficient of the electrical drainage profession is 0.08, and the total is 1. It can be found that the allocation proportion coefficient is fixed and is set artificially, and there may be problems of unreasonable allocation caused by setting deviation. SUMMARY

[0005] Therefore, the embodiments of the present application provide a project management method and system, aiming at solving the problem of unreasonable allocation caused by the fixed allocation proportion coefficient in the prior art.

[0006] The first aspect of the embodiments of the present application provides a project management method, which comprises: obtaining the scene requirement of a project, collecting features in layers according to the scene requirement, and generating a project fingerprint vector; constructing a single-person ability portrait, determining a professional team ability aggregation portrait according to the single-person ability portrait, and generating a resource ability portrait vector; calculating the scene benchmark proportion of each profession according to the project fingerprint vector; for each profession, constructing a nonlinear bearing function, calculating a bearing degree, and using the bearing degree to dynamically adjust the scene benchmark proportion to obtain a preliminary correction proportion; for each profession, extracting a historical case similar to the current project scene of the corresponding profession, and determining a deviation correction factor; According to the deviation correction factor, the preliminary correction ratio is corrected to obtain a final ratio; The final ratios of all specialties are normalized to generate a distribution coefficient table as a basis for workload distribution and assessment.

[0007] Further, the step of obtaining the scene requirements of the project, and collecting feature hierarchies according to the scene requirements, and generating a project fingerprint vector includes: According to the project type and stage, main features are collected, and 2-level main labels are set; The main features are refined, specifically including complexity sub-features, delivery constraint sub-features, and risk sub-features; The sub-features are quantified and standardized to obtain processed sub-features; The main labels are converted into embedding vectors, and the processed sub-features are spliced with the embedding vectors to generate the project fingerprint vector.

[0008] Further, the single-person capability profile includes a basic capability dimension, a state dimension, and a collaboration dimension, the basic capability dimension at least includes skill proficiency and efficiency coefficient, the skill proficiency is a recent similar task quality score, and the efficiency coefficient is a ratio of actual time consumption to standard time consumption; The state dimension at least includes real-time load rate and responseable time length, the real-time load rate is a ratio of current working hours to weekly full load working hours, and the responseable time length is daily additional working hours; The state dimension at least includes average communication time length with other specialties and cross-specialty cooperation good comment rate.

[0009] Further, the step of constructing a single-person capability profile, determining a specialty team capability aggregation profile according to the single-person capability profile, and generating a resource capability profile vector includes: For all members of each specialty, the team mean is calculated by weighting the proportion of personnel currently participating in the project, wherein the team mean includes team proficiency, team load rate, and team cooperation good comment rate; The team proficiency, team load rate, and team cooperation good comment rate are converted into a resource capability profile vector.

[0010] Further, the step of calculating the scene benchmark ratio of each specialty according to the project fingerprint vector includes: The historical project library is called to filter historical cases with a similarity between the project fingerprint vector and the current project exceeding a threshold, and the historical distribution ratio of each specialty in the historical cases is extracted; The cosine similarity between the current project fingerprint vector and the project fingerprint vector of each historical case is calculated, and the historical distribution ratio is weighted averaged with the cosine similarity as the weight to obtain the scene benchmark ratio of each specialty.

[0011] Further, the step of extracting, for each specialty, a deviation correction factor from historical cases similar to the current project scenario includes: extracting a deviation rate of the allocation ratio of the corresponding specialty in the historical cases similar to the current project scenario and the efficiency coefficient; obtaining a mapping relationship between a deviation rate range and a preset deviation correction factor, and determining the deviation correction factor according to the deviation rate and the mapping relationship.

[0012] Further, the step of extracting, for each specialty, a deviation correction factor from historical cases similar to the current project scenario includes: calculating a project scenario difference index and a resource capability fluctuation index, and respectively judging whether the project scenario difference index and the resource capability fluctuation index are greater than corresponding preset values; If the project scenario difference index is greater than the corresponding preset value, it indicates that the project scenario difference is large, and then a scenario deviation sensitivity score is calculated based on the complexity sub-feature and the risk sub-feature; According to the scenario deviation sensitivity score and the deviation rate, a deviation correction factor is calculated; If the resource capability fluctuation index is greater than the corresponding preset value, it indicates that the resource capability fluctuation is frequent, then a deviation rate of the corresponding specialty in a historical project similar to the current project by more than a threshold value is extracted, a time sequence is constructed, and a trend slope is calculated; According to the trend slope, a trend penalty coefficient is determined; According to the team mean, a capability score of the resource capability portrait is calculated, and according to the capability score, an attribution penalty coefficient is determined; According to the deviation rate, the trend penalty coefficient and the attribution penalty coefficient, a deviation correction factor is calculated.

[0013] The second aspect of the embodiment of the application provides a project management system for implementing the project management method provided by the first aspect of the embodiment of the application, and the system comprises: A first generation module is configured to obtain a scenario requirement of a project, perform feature hierarchical collection according to the scenario requirement, and generate a project fingerprint vector; A second generation module is configured to construct a single-person capability portrait, determine a professional team capability aggregation portrait according to the single-person capability portrait, and generate a resource capability portrait vector; A first calculation module is configured to calculate a scenario benchmark ratio of each specialty according to the project fingerprint vector; A second calculation module is configured to, for each specialty, construct a non-linear bearing function, calculate a bearing degree, and use the bearing degree to dynamically adjust the scenario benchmark ratio to obtain a preliminary correction ratio; an extraction module configured to extract, for each specialty, historical cases similar to the current project scenario and determine a deviation correction factor; a correction module configured to correct the preliminary correction ratio according to the deviation correction factor to obtain a final ratio; a normalization processing module configured to normalize the final ratios of all specialties and generate an allocation coefficient table as a basis for workload allocation and assessment.

[0014] A third aspect of the embodiment of the present application provides a computer readable storage medium, comprising: The readable storage medium stores one or more programs, which are executed by a processor to implement the project management method according to the first aspect.

[0015] A fourth aspect of the embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein: The memory is configured to store a computer program; The processor is configured to execute the computer program stored in the memory to implement the project management method according to the first aspect.

[0016] The project management method and system provided in the embodiment of the present application, by acquiring the scene requirement of a project, collecting feature layers according to the scene requirement, and generating a project fingerprint vector, constructing a single-person ability portrait, determining a professional team ability aggregation portrait according to the single-person ability portrait, and generating a resource ability portrait vector, calculating the scene benchmark ratio of each specialty according to the project fingerprint vector, for each specialty, constructing a nonlinear bearing function, calculating the bearing degree, and using the bearing degree to dynamically adjust the scene benchmark ratio to obtain a preliminary correction ratio, extracting, for each specialty, historical cases similar to the current project scenario, and determining a deviation correction factor, correcting the preliminary correction ratio according to the deviation correction factor to obtain a final ratio, normalizing the final ratios of all specialties, and generating an allocation coefficient table as a basis for workload allocation and assessment, specifically, using the multidimensional dynamic characteristics (project fingerprint) of the project to match the real-time resource ability (resource portrait) of the corresponding specialty, replacing the logic of “single project type corresponding to fixed coefficient”, and realizing “one project one coefficient”. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 An implementation flowchart of the project management method provided in the first embodiment of the present application; Figure 2 A structural block diagram of the project management system provided in the third embodiment of the present application; Figure 3 A structural block diagram of the electronic device provided in the fourth embodiment of the present application. Detailed Implementation

[0018] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0019] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0021] Example 1 Embodiment 1 of this invention provides a project management method; please refer to [link / reference]. Figure 1 This is a flowchart for implementing a project management method, specifically including steps S01 to S07.

[0022] Step S01: Obtain the scenario requirements of the project, collect features in layers according to the scenario requirements, and generate a project fingerprint vector.

[0023] Specifically, based on the project type and stage, the main features are collected and two-level main tags are set. The project type refers to traffic intersection projects, construction intersection projects, general single-building projects, etc., and the stage refers to the scheme stage, preliminary design stage, construction drawing stage, etc. The set two-level main tags can be understood as the form of traffic project - scheme stage. The main features are further refined. Specifically, three types of sub-features are added to each main label: complexity sub-features, delivery constraint sub-features, and risk sub-features. Among them, the complexity sub-features can be further refined into the number of intersections and the number of circulation types for traffic intersection projects, the number of floors and building area for construction intersection projects, and the number of functional modules for general single buildings. The delivery constraint sub-features include the number of deliverables, the number of review rounds, and the priority of the client's requirements (high / medium / low). The risk sub-features include the delay rate of similar projects in the past and the number of quality issues. Sub-features are then quantized and standardized to obtain the processed sub-features. It should be noted that numerical sub-features are normalized, i.e., the number of intersections (e.g., 5) and building area (e.g., 10,000 square meters). 2 The values ​​are converted into 0-1 range values. For example, the number of intersections ≤3 is converted into 0.3, 3-5 into 0.6, and ≥5 into 1.0. In addition, the sub-features are encoded, that is, the priority of the client (high / medium / low) is converted into one-hot encoding (high → [1,0,0]), and the risk level is converted into a score. For example, the delay rate ≤5% is converted into 10 points, and 5%-10% is converted into 8 points. The main label is converted into an embedding vector, and the processed sub-features are concatenated with the embedding vector to generate the project fingerprint vector, which is used to uniquely represent the scenario requirements of the current project. Specifically, the main label of project type + stage is converted into an embedding vector, which can be generated by a pre-trained project scenario classification model. The project scenario classification model can be an end-to-end semantic feature extraction model based on a lightweight Transformer encoder + multilayer perceptron (MLP).

[0024] Step S02: Construct a single-person capability profile, determine a professional team capability aggregation profile based on the single-person capability profile, and generate a resource capability profile vector.

[0025] Specifically, the individual's capability profile includes a basic capability dimension, a status dimension, and a collaboration dimension. The basic capability dimension includes at least skill proficiency and efficiency coefficient. Skill proficiency is the quality score of similar tasks in recent times. In this embodiment of the invention, the quality scores of similar tasks in the past 6 months are statistically analyzed, ranging from 0 to 10. The efficiency coefficient is the ratio of actual time spent to standard time spent. A ratio of <1 indicates high efficiency. The status dimension includes at least real-time load rate and response time, wherein the real-time load rate is the ratio of current working hours to weekly full load working hours, and the response time is the daily additional working hours; The status dimension includes at least the average communication time (minutes / task) with other professions and the positive feedback rate for cross-professional cooperation.

[0026] More specifically, for all members of each profession, the team average is calculated by weighting the proportion of people currently participating in the project. The team average includes team proficiency, team workload, and team collaboration satisfaction rate. For example, if two members participate: A accounts for 60% and B accounts for 40%, then the team proficiency = A proficiency × 0.6 + B proficiency × 0.4. The team's proficiency, workload, and team collaboration satisfaction rate are transformed into resource capability profile vectors.

[0027] Step S03: Calculate the scene benchmark ratio for each profession based on the project fingerprint vector.

[0028] It should be noted that the historical project database is accessed to filter historical cases whose project fingerprint vectors have a similarity to the current project that exceeds a threshold. The historical distribution ratio of each profession in the historical cases is extracted. Specifically, the enterprise's historical project database can be initially filtered based on the "project type-stage" main label associated with the project fingerprint vector (such as "transportation project-solution stage") to select a subset of historical projects with the same main label to reduce computational complexity. Then, the semantic similarity (range 0-1) between the current project fingerprint vector and all historical project fingerprint vectors in the subset is calculated one by one using the cosine similarity algorithm to accurately select historical projects with a similarity ≥ 0.8 (i.e., 80%). Finally, duplicate items are removed from the filtering results (for multiple versions of fingerprint data of the same project) and sorted in descending order of similarity score to form a set of historical cases focusing on core scenario matching. Calculate the cosine similarity between the current project fingerprint vector and the project fingerprint vector of each historical case. Using the cosine similarity as the weight, perform a weighted average of the historical allocation ratios to obtain the scene benchmark ratio for each profession. For example, the scene benchmark ratio for the architecture profession = Σ(historical ratio × similarity) / Σsimilarity.

[0029] Step S04: For each specialty, construct a nonlinear load-bearing function, calculate the load-bearing capacity, and use the load-bearing capacity to dynamically adjust the baseline ratio of the scene to obtain a preliminary corrected ratio.

[0030] In this embodiment of the invention, the load capacity = (team proficiency × 0.6) × (1 - team load rate) × 0.3 + (team collaboration satisfaction rate × 0.1). The load capacity ranges from 0 to 1. The higher the value, the more workload the profession can handle. Furthermore, the initial correction ratio = scenario baseline ratio × load capacity.

[0031] Step S05: For each major, extract historical cases that are similar to the current project scenario and determine the deviation correction factor.

[0032] Extract the deviation rate between the allocation ratio of the corresponding major in historical cases similar to the current project scenario and the efficiency coefficient. Deviation rate = |allocation ratio - efficiency coefficient|. Obtain the mapping relationship between the deviation rate range and the preset deviation correction factor. Determine the deviation correction factor based on the deviation rate and the mapping relationship. For example, the deviation correction factor is generated as follows: if the deviation rate is >15%, the deviation correction factor = 0.9; if the deviation rate is 5%-15%, the deviation correction factor = 0.95; if the deviation rate is <5%, the deviation correction factor = 1.0.

[0033] Step S06: Adjust the preliminary correction ratio according to the deviation correction factor to obtain the final ratio.

[0034] Wherein, final ratio = preliminary correction ratio × deviation correction factor Step S07: Normalize the final proportions of all specialties and generate an allocation coefficient table as the basis for workload allocation and assessment.

[0035] Specifically, a Softmax process is applied to the final proportions of all majors to ensure that the sum of the proportions of all majors is 1. Then, it is verified whether the normalized proportions meet the requirement that the proportion of a single major is not less than 5% (to avoid extreme allocation). If not, it is fine-tuned to 5% and then normalized again. Finally, the final allocation proportions of each major in the current stage are output.

[0036] In summary, the project management method proposed in this embodiment of the invention obtains the scenario requirements of the project, performs feature layering collection based on the scenario requirements, and generates a project fingerprint vector; constructs individual personnel capability profiles, determines professional team capability aggregation profiles based on individual personnel capability profiles, and generates resource capability profile vectors; calculates the scenario baseline ratio for each profession based on the project fingerprint vector; constructs a nonlinear carrying capacity function for each profession, calculates the carrying capacity, and uses the carrying capacity to dynamically adjust the scenario baseline ratio to obtain a preliminary correction ratio; extracts historical cases similar to the current project scenario for each profession and determines a deviation correction factor; corrects the preliminary correction ratio based on the deviation correction factor to obtain the final ratio; normalizes the final ratios of all professions and generates an allocation coefficient table as the basis for workload allocation and assessment. Specifically, it uses the multi-dimensional dynamic features of the project (project fingerprint) to match the real-time resource capabilities (resource profile) of the corresponding profession, replacing the logic of "a fixed coefficient for a single project type" and achieving "one coefficient per project".

[0037] Example 2 Embodiment 2 of the present invention provides a project management method. The difference between this method and the one provided in Embodiment 1 is that, to obtain more accurate allocation coefficients, the simple logic of a deviation rate interval → fixed mapping is replaced. Specifically, after the step of extracting the deviation rate between the allocation ratio of the corresponding specialty in historical cases similar to the current project scenario and the efficiency coefficient, the method includes: Calculate the project scenario difference index and the resource capability fluctuation index, and determine whether the project scenario difference index and the resource capability fluctuation index are greater than the corresponding preset values. Specifically, the project scenario difference index is used to judge the magnitude of the project scenario difference, and the resource capability fluctuation index is used to judge whether the resource capability fluctuates frequently. It should be noted that the scenario feature distribution of similar projects is used as a benchmark. By quantifying the degree of difference between the current project and the benchmark group, the magnitude of the scenario difference is judged. The more significant the difference, the more difficult it is to adapt the fixed coefficient. In order to calculate the project scenario difference index, in this embodiment of the invention, a benchmark group is first defined according to the project main label (type + stage): for example, "transportation intersection project - solution stage" is a benchmark group, and the fingerprint vectors of all projects in this group in the past two years are extracted. Subsequently, the project scenario difference index is calculated. This index includes the fingerprint similarity coefficient of variation, the core feature coefficient of variation, and the constraint uniqueness score. Specifically, the cosine similarity between the current project fingerprint vector and the fingerprint vectors of all projects in the benchmark group is calculated to obtain a similarity sequence. Then, the coefficient of variation (coefficient of variation = standard deviation / mean) of this similarity sequence is calculated to obtain the fingerprint similarity coefficient of variation. It can be understood that the larger the coefficient of variation, the more dispersed the similarity distribution between the current project and the benchmark group. Key scenario features, namely complexity sub-features, delivery constraint sub-features, and risk sub-features, are extracted from the project fingerprint vector and quantified as 0-1 values. The coefficient of variation of the core features between the current project fingerprint vector and the benchmark group is then calculated. ; The larger the coefficient of variation of the core feature, the more significant the deviation between the key feature and the population baseline. Count the number of "constraint features that exceed the scope of 90% of projects in the benchmark group" in the fingerprint vector of the current project (e.g., 90% of projects in the benchmark group have ≤3 delivery reviews, while the current project has 5 reviews). Each unique constraint is worth 1 point, with a total score of 0-3 points (the higher the score, the more unique the scenario constraint). If the project scenario difference index is greater than the corresponding preset value, it indicates that the project scenario difference is large. Then, based on the complexity sub-feature and the risk sub-feature, the scenario deviation sensitivity score is calculated. In this embodiment of the invention, a graded judgment threshold is set, which can be referred to in the following table:

[0038] It should be noted that a three-level difference standard of "high / medium / low" is set. If any "high difference" condition is met, it is judged as "large difference in project scenario". For example, if the fingerprint similarity dispersion coefficient of the current "transportation intersection project - solution stage" is 0.32 (>0.3), then it is judged as large difference in project scenario. Furthermore, a mapping relationship is established between complexity sub-features and risk sub-features and scene deviation sensitivity scores. For example, for high complexity + high risk projects (such as traffic projects with ≥5 intersections + delay rate >10%): sensitivity score 8-10 points (low tolerance for deviation, requiring strong correction); for low complexity + low risk projects (such as single project functional modules ≤3 + delay rate <5%): sensitivity score 3-5 points (high tolerance for deviation, weak correction). Based on the scene deviation sensitivity score and the deviation rate, calculate the deviation correction factor, which is expressed as: Deviation correction factor = 1 - (deviation rate × scene deviation sensitivity score / 10). In addition, in order to calculate the resource capability fluctuation index, in this embodiment of the invention, the resource capability profile data of the target profession (such as architecture) for the past 3 months is first extracted and a time series dataset is formed according to the preset update frequency. Each record contains 6 core capability dimensions, namely skill proficiency, efficiency coefficient, real-time load rate, response time, average communication time with other professions and cross-professional cooperation satisfaction rate. Subsequently, a resource capability fluctuation index is calculated, which includes the coefficient of variation of capability dimensions, the frequency of mutation events, and the slope of capability trends. Specifically, for each capability dimension, the coefficient of variation (coefficient of variation = standard deviation / mean) of the time series data is calculated, and the average of the coefficients of variation of the six dimensions is taken as the overall fluctuation amplitude, i.e., the coefficient of variation of capability dimensions. A mutation threshold is set; when the change rate of a certain capability dimension data from the previous record is ≥20%, it is judged as a "mutation event," and the total number of mutation events within 3 months (cumulative by dimension) is counted, i.e., the mutation event frequency. For each capability dimension, linear regression is used to fit the time series data to obtain the trend slope (slope > 0 indicates an upward trend, < 0 indicates a downward trend), and the average of the absolute values ​​of the slopes is calculated, i.e., the capability trend slope. It can be understood that the larger the average value, the more significant the overall change trend of the capability dimension (the more persistent the fluctuation). If the resource capacity fluctuation index is greater than the corresponding preset value, it indicates that the resource capacity fluctuates frequently. Then, the deviation rate of historical projects with similarity exceeding a threshold to the current project in the corresponding specialty is extracted, a time series is constructed, and the trend slope is calculated. In this embodiment of the invention, a graded judgment threshold is set, as shown in the table below:

[0039] It should be noted that a three-level fluctuation standard of "frequent / moderate / gradual" is set. Meeting any "frequent" condition is judged as "frequent fluctuation of resource capacity". For example, if the overall fluctuation range of the construction industry within 3 months is 0.22 (>0.2), it is judged as frequent fluctuation of resource capacity. Furthermore, based on the time series constructed from the historical project deviation rates, the trend slope is calculated. A positive slope (continuous increase in deviation) is marked as a "deteriorating trend"; a slope close to 0 (deviation fluctuation) is marked as a "stable trend"; and a negative slope (continuous decrease in deviation) is marked as an "optimizing trend". Based on the trend slope, a trend penalty coefficient is determined. In this embodiment of the invention, the trend penalty coefficients are: deteriorating trend = 0.2, stable trend = 0.1, and optimizing trend = 0. Based on the team average, a capability score for the resource capability profile is calculated. Based on the capability score, an attribution penalty coefficient is determined. Specifically, the team proficiency, team load rate, and team collaboration satisfaction rate are weighted and summed to obtain the capability score. In this embodiment of the invention, if the capability score is <6 (insufficient resource capability), the attribution is "capability mismatch," which requires strong correction; if the capability score is ≥8 (sufficient resource capability), the attribution is "sudden change in project requirements" (such as a temporary increase in delivery constraints in the fingerprint), which requires weak correction. The attribution penalty coefficients are: capability mismatch = 0.2, sudden change in project requirements = 0.05. The deviation correction factor is calculated based on the deviation rate, the trend penalty coefficient, and the attribution penalty coefficient. The calculation formula is: Deviation correction factor = 1 - (deviation rate × 0.3 + trend penalty coefficient × 0.4 + attribution penalty coefficient × 0.3).

[0040] Example 3 Embodiment 3 of the present invention provides a project management system 200. Please refer to [link / reference]. Figure 2 Here is a structural diagram of a project management system 200, which includes: The first generation module 21 is used to obtain the scenario requirements of the project, perform feature layer collection according to the scenario requirements, and generate a project fingerprint vector. The second generation module 22 is used to construct a single person's ability profile, determine a professional team's ability aggregation profile based on the single person's ability profile, and generate a resource ability profile vector. The single person's ability profile includes a basic ability dimension, a status dimension, and a collaboration dimension. The basic ability dimension includes at least skill proficiency and efficiency coefficient. The skill proficiency is the quality score of similar tasks in recent times, and the efficiency coefficient is the ratio of actual time consumption to standard time consumption. The status dimension includes at least real-time load rate and response time, wherein the real-time load rate is the ratio of current working hours to weekly full load working hours, and the response time is the daily additional working hours; The status dimension includes at least the average communication duration with other disciplines and the positive feedback rate for cross-disciplinary cooperation; The first calculation module 23 is used to calculate the scene benchmark ratio of each profession based on the project fingerprint vector; The second calculation module 24 is used to construct a nonlinear load-bearing function for each specialty, calculate the load-bearing capacity, and use the load-bearing capacity to dynamically adjust the baseline ratio of the scene to obtain a preliminary correction ratio. Extraction module 25 is used to extract historical cases similar to the current project scenario for each major and determine the deviation correction factor; Correction module 26 is used to correct the preliminary correction ratio according to the deviation correction factor to obtain the final ratio; The normalization module 27 is used to normalize the final proportions of all specialties and generate an allocation coefficient table as the basis for workload allocation and assessment.

[0041] Furthermore, in some other embodiments of the present invention, the first generation module 21 includes: The data collection unit is used to collect key features based on project type and stage, and set two-level key tags; The refinement unit is used to refine the main features, specifically including complexity sub-features, delivery constraint sub-features, and risk sub-features; The processing unit is used to perform feature quantization and standardization on the sub-features to obtain the processed sub-features. The concatenation unit is used to convert the main label into an embedding vector and concatenate the processed sub-features with the embedding vector to generate the project fingerprint vector.

[0042] Furthermore, in some other embodiments of the present invention, the second generation module 22 includes: The first calculation unit is used to calculate the team average for all members of each profession based on the proportion of people currently participating in the project. The team average includes team proficiency, team workload, and team collaboration satisfaction rate. The conversion unit is used to transform team proficiency, team workload, and team collaboration satisfaction rate into resource capability profile vectors.

[0043] Furthermore, in some other embodiments of the present invention, the first calculation module 23 includes: The calling unit is used to call the historical project library, filter historical cases whose similarity to the current project fingerprint vector exceeds a threshold, and extract the historical allocation ratio of each profession in the historical cases. The second calculation unit is used to calculate the cosine similarity between the current project fingerprint vector and the project fingerprint vector of each historical case, and to perform a weighted average of the historical allocation ratios using the cosine similarity as the weight to obtain the scene benchmark ratio for each profession.

[0044] Furthermore, in some other embodiments of the present invention, the extraction module 25 includes: The extraction unit is used to extract the deviation rate between the allocation ratio of the corresponding major in historical cases similar to the current project scenario and the efficiency coefficient; The acquisition unit is used to acquire the mapping relationship between the deviation rate range and the preset deviation correction factor, and to determine the deviation correction factor based on the deviation rate and the mapping relationship.

[0045] Furthermore, in some other embodiments of the present invention, the extraction module 25 further includes: The judgment unit is used to calculate the project scenario difference index and the resource capability fluctuation index, and to determine whether the project scenario difference index and the resource capability fluctuation index are greater than the corresponding preset values. The third calculation unit is used to calculate the scenario deviation sensitivity score based on the complexity sub-feature and the risk sub-feature if the project scenario difference index is greater than the corresponding preset value, indicating that the project scenario difference is large. The fourth calculation unit is used to calculate the deviation correction factor based on the scene deviation sensitivity score and the deviation rate; The fifth calculation unit is used to extract the deviation rate of historical projects with similarity to the current project that exceed the threshold if the resource capacity fluctuation index is greater than the corresponding preset value, indicating that the resource capacity fluctuates frequently, to construct a time series sequence and calculate the trend slope. A determining unit is used to determine a trend penalty coefficient based on the trend slope; The sixth calculation unit is used to calculate the capability score of the resource capability profile based on the team average, and to determine the attribution penalty coefficient based on the capability score; The seventh calculation unit is used to calculate the deviation correction factor based on the deviation rate, the trend penalty coefficient, and the attribution penalty coefficient.

[0046] Example 4 Embodiment 4 of this invention proposes an electronic device; please refer to [link / reference]. Figure 3 This is a structural block diagram of an electronic device, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, it implements the project management method described above.

[0047] In some embodiments, the processor 10 may be a central processing unit (CPU), controller, microcontroller, microprocessor or other data processing chip, used to run program code stored in memory 20 or process data, such as executing access restriction programs.

[0048] The memory 20 includes at least one type of readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of the electronic device, such as a plug-in hard disk, SmartMediaCard (SMC), SecureDigital (SD) card, FlashCard, etc., equipped on the electronic device. Furthermore, the memory 20 can include both internal and external storage units of the electronic device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or will be output.

[0049] This invention also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the project management method described above.

[0050] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0051] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0052] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0053] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0054] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A project management method characterized by, The method comprises: acquiring a scene requirement of a project, collecting features in layers according to the scene requirement, and generating a project fingerprint vector; constructing a single-person capability profile, determining a professional team capability aggregation profile according to the single-person capability profile, and generating a resource capability profile vector; calculating a scene benchmark proportion of each profession according to the project fingerprint vector; for each profession, constructing a nonlinear bearing function, calculating a bearing degree, and using the bearing degree to dynamically adjust the scene benchmark proportion to obtain a preliminary correction proportion; for each profession, extracting historical cases similar to the current project scene of the corresponding profession, and determining a deviation correction factor; correcting the preliminary correction proportion according to the deviation correction factor to obtain a final proportion; normalizing the final proportion of all professions and generating an allocation coefficient table as a basis for workload allocation and assessment.

2. The project management method according to claim 1, characterized by, The step of acquiring a scene requirement of a project, collecting features in layers according to the scene requirement, and generating a project fingerprint vector comprises: collecting main features according to the type and stage of the project, and setting 2-level main tags; refining the main features, specifically including complexity sub-features, delivery constraint sub-features, and risk sub-features; quantifying and standardizing the sub-features to obtain processed sub-features; converting the main tags into embedded vectors, and splicing the processed sub-features with the embedded vectors to generate the project fingerprint vector.

3. The project management method according to claim 2, characterized by, The single-person capability profile comprises a basic capability dimension, a state dimension, and a collaboration dimension, the basic capability dimension at least includes skill proficiency and efficiency coefficient, the skill proficiency is a recent similar task quality score, and the efficiency coefficient is a ratio of actual time consumption to standard time consumption; The state dimension at least includes real-time load rate and responsive duration, the real-time load rate is a ratio of current working hours to weekly full load working hours, and the responsive duration is daily additional working hours; The state dimension at least includes average communication duration with other professions and cross-profession cooperation good evaluation rate.

4. The project management method according to claim 3, characterized by, The step of constructing a single-person capability profile, determining a professional team capability aggregation profile according to the single-person capability profile, and generating a resource capability profile vector comprises: for all members of each profession, calculating a team mean by weighting according to the proportion of personnel currently participating in the project, wherein the team mean includes team proficiency, team load rate, and team cooperation good evaluation rate; converting the team proficiency, team load rate, and team cooperation good evaluation rate into a resource capability profile vector.

5. The project management method according to claim 4, characterized by The step of calculating a scene benchmark proportion of each profession according to the project fingerprint vector comprises: calling a historical project library, screening historical cases with a similarity of project fingerprint vectors to the current project exceeding a threshold, and extracting historical allocation proportions of each profession in the historical cases; calculating a cosine similarity of the current project fingerprint vector and the project fingerprint vector of each historical case, and weighting the historical allocation proportions to obtain a weighted average to obtain a scene benchmark proportion of each profession.

6. The project management method according to claim 5, characterized by, The step of extracting historical cases similar to the current project scene of the corresponding profession for each profession, and determining a deviation correction factor comprises: extract a deviation rate of the allocation proportion of the corresponding specialty in the historical case similar to the current project scenario and the efficiency coefficient; obtain a mapping relationship between the deviation rate and a preset deviation correction factor, and determine the deviation correction factor according to the deviation rate and the mapping relationship.

7. The project management method according to claim 6, characterized by, The step of extracting the deviation rate of the allocation proportion of the corresponding specialty in the historical case similar to the current project scenario and the efficiency coefficient comprises: calculating a project scenario difference index and a resource capability fluctuation index, and respectively judging whether the project scenario difference index and the resource capability fluctuation index are greater than corresponding preset values; if the project scenario difference index is greater than the corresponding preset value, it indicates that the project scenario difference is large, and then a scenario deviation sensitivity score is calculated based on the complexity sub-feature and the risk sub-feature; a deviation correction factor is calculated according to the scenario deviation sensitivity score and the deviation rate; if the resource capability fluctuation index is greater than the corresponding preset value, it indicates that the resource capability fluctuation is frequent, then a deviation rate of the corresponding specialty in a historical project similar to the current project is extracted, a time sequence is constructed, and a trend slope is calculated; a trend penalty coefficient is determined according to the trend slope; a capability score of the resource capability portrait is calculated according to the team mean, and an attribution penalty coefficient is determined according to the capability score; a deviation correction factor is calculated according to the deviation rate, the trend penalty coefficient and the attribution penalty coefficient.

8. A project management system characterized by The system for implementing the project management method according to any one of claims 1-7 comprises: a first generation module configured to obtain a scenario requirement of a project, perform feature hierarchical collection according to the scenario requirement, and generate a project fingerprint vector; a second generation module configured to construct a single-person capability portrait, determine a professional team capability aggregation portrait according to the single-person capability portrait, and generate a resource capability portrait vector; a first calculation module configured to calculate a scenario benchmark proportion of each specialty according to the project fingerprint vector; a second calculation module configured to, for each specialty, construct a non-linear bearing function, calculate a bearing degree, and perform dynamic adjustment on the scenario benchmark proportion using the bearing degree to obtain a preliminary correction proportion; an extraction module configured to, for each specialty, extract a historical case similar to the current project scenario of the corresponding specialty, and determine a deviation correction factor; a correction module configured to correct the preliminary correction proportion according to the deviation correction factor to obtain a final proportion; a normalization processing module configured to perform normalization processing on the final proportion of all specialties, and generate an allocation coefficient table as a basis for workload allocation and assessment.

9. A computer-readable storage medium, characterized in that, The system comprises: The readable storage medium stores one or more programs, which are executed by the processor to implement the project management method according to any one of claims 1-7.

10. An electronic device, comprising: The electronic device comprises a memory and a processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer programs stored on the memory to implement the project management method according to any one of claims 1-7.

Images