Quality management personnel work evaluation alarm method and device for informatization research and development project

Abstract

The invention provides a quality management personnel work evaluation alarm method and device for an informatization research and development project. The method comprises the following steps: receiving an alarm request sent by a project quality control platform; performing recognition processing on the plurality of pieces of work information through a natural language processing technology and a voice recognition technology to obtain a plurality of pieces of work data; determining a plurality of target statistical strategies, and performing statistical processing on the plurality of pieces of working data through the plurality of target statistical strategies to obtain a plurality of pieces of target statistical information; inputting the plurality of pieces of target statistical information into a prediction model to obtain a plurality of target improvement measures, and generating alarm information according to the plurality of pieces of target statistical information and the plurality of target improvement measures; and sending the alarm information to a project management platform, so that the project management platform completes alarm prompt for the target worker. According to the scheme, recognition processing is performed through a natural language processing technology and a voice recognition technology, and compared with a manual mode, the recognition efficiency can be effectively improved, so that the alarm prompting efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for warning quality control personnel of an information technology research and development project. Background Art

[0002] In information technology R&D projects, in order to achieve product standardization and improve the level of refinement of project management, quality management and process improvement are required during project execution. Specifically, quality control personnel can verify whether the project execution process meets the preset quality standards, issue early warnings for risks and problems in the project execution process, and provide improvement suggestions. They can continue to follow up on the project until the risks disappear to achieve quality management, thereby improving R&D efficiency and product quality.

[0003] In actual applications, there will be problems when quality control personnel perform quality management work, which leads to quality management problems. In related technologies, problems in the work of quality control personnel are manually identified and alarms are issued to improve the standardization of R&D projects.

[0004] However, there is a problem of low efficiency in manually issuing alarm prompts. Summary of the invention

[0005] The present application provides a method and device for warning the quality control personnel of an information technology research and development project, so as to improve the efficiency of warning prompts.

[0006] In the first aspect, the present application provides a method for quality control personnel work evaluation alarm of an information-based R&D project, which is applied to a server, and includes: receiving an alarm request sent by a project quality control platform, the alarm request including multiple work information corresponding to multiple target staff members; identifying and processing the multiple work information through natural language processing technology and speech recognition technology to obtain multiple work data; determining multiple target statistical strategies, and performing statistical processing on the multiple work data through the multiple target statistical strategies to obtain multiple target statistical information, wherein the multiple target statistical information is used to indicate the degree of work completion; inputting the multiple target statistical information into a prediction model to obtain multiple target improvement measures, and generating alarm information based on the multiple target statistical information and the multiple target improvement measures, wherein the target improvement measures are used to improve the degree of work completion; sending the alarm information to the project management platform so that the project management platform completes the alarm prompt for the target staff members.

[0007] In a possible implementation, the multiple work information are identified and processed by natural language processing technology and speech recognition technology to obtain multiple work data, including: determining multiple first voice information and multiple first text information from the multiple work information; converting the multiple first voice information into multiple second text information by speech recognition technology; identifying and processing the multiple first text information and the multiple second text information by natural language processing technology to obtain the multiple work data.

[0008] In one possible implementation, the multiple first voice information are converted into multiple second text information through voice recognition technology, including: inputting the multiple first voice information into a voice recognition model respectively to obtain multiple voice feature information; inputting the multiple voice features into a decoder respectively to obtain multiple initial text information; inputting the multiple initial text information into a generative adversarial network model respectively to obtain the multiple second text information, wherein the generative adversarial network model is used to perform grammatical error correction on the initial text information.

[0009] In a possible implementation, the multiple working data include multiple data type identifiers; the alarm request also includes multiple target evaluation indicators; the multiple working data are statistically processed using the multiple target statistical strategies to obtain multiple target statistical information, including: determining the correspondence between the evaluation indicators and the data type identifiers; determining multiple target working data from the multiple working data based on the multiple target evaluation indicators and the correspondence; and the multiple target working data are statistically processed using the multiple target statistical strategies to obtain the multiple target statistical information.

[0010] In a possible implementation, the multiple target working data are statistically processed by the multiple target statistical strategies to obtain the multiple target statistical information, including: calculating and processing the multiple target working data according to the multiple target evaluation indicators to obtain multiple indicator values, wherein each indicator value corresponds to a target evaluation indicator; and statistically processing the multiple indicator values ​​by the multiple target statistical strategies to obtain the multiple target statistical information.

[0011] In one possible implementation, the multiple target statistical information is input into a prediction model to obtain multiple target improvement measures, including: determining multiple historical statistical information of the multiple staff members; inputting the multiple historical statistical information and the multiple target statistical information into the prediction model to obtain the multiple target improvement measures.

[0012] In a possible implementation, the method further includes: determining sample data, the sample data including multiple sample statistical information and corresponding multiple sample improvement measures; performing model training through the sample data to obtain the prediction model, and the prediction model is used to generate corresponding target improvement measures based on the target statistical information.

[0013] In a second aspect, the present application provides a work evaluation alarm device for quality control personnel of an information-based R&D project, which is applied to a server and includes: a receiving module, which is used to receive an alarm request sent by a project quality control platform, wherein the alarm request includes multiple work information corresponding to multiple target staff members; an identification module, which is used to identify and process the multiple work information through natural language processing technology and speech recognition technology to obtain multiple work data; a statistical module, which is used to determine multiple target statistical strategies, and perform statistical processing on the multiple work data through the multiple target statistical strategies to obtain multiple target statistical information, wherein the multiple target statistical information is used to indicate the degree of work completion; a prediction module, which is used to input the multiple target statistical information into a prediction model to obtain multiple target improvement measures, and generate alarm information based on the multiple target statistical information and the multiple target improvement measures, wherein the target improvement measures are used to improve the degree of work completion; a sending module, which is used to send the alarm information to the project management platform so that the project management platform can complete the alarm prompt for the target staff members.

[0014] In a possible implementation, the recognition module is specifically used to determine multiple first voice information and multiple first text information from the multiple work information; the recognition module is also specifically used to convert the multiple first voice information into multiple second text information through voice recognition technology; the recognition module is also specifically used to recognize and process the multiple first text information and the multiple second text information through natural language processing technology to obtain the multiple work data.

[0015] In one possible implementation, the recognition module is specifically used to input the multiple first voice information into a voice recognition model respectively to obtain multiple voice feature information; the recognition module is also specifically used to input the multiple voice features into a decoder respectively to obtain multiple initial text information; the recognition module is also specifically used to input the multiple initial text information into a generative adversarial network model respectively to obtain the multiple second text information, wherein the generative adversarial network model is used to perform grammatical error correction on the initial text information.

[0016] In a possible implementation, the multiple working data include multiple data type identifiers; the alarm request also includes multiple target evaluation indicators; the device also includes: an execution module, used to determine the correspondence between the evaluation indicators and the data type identifiers; the execution module is also used to determine multiple target working data from the multiple working data based on the multiple target evaluation indicators and the correspondence; the execution module is also used to perform statistical processing on the multiple target working data through the multiple target statistical strategies to obtain the multiple target statistical information.

[0017] In a possible implementation, the execution module is specifically used to calculate and process the multiple target work data according to the multiple target evaluation indicators to obtain multiple indicator values, wherein each indicator value corresponds to a target evaluation indicator; the execution module is also specifically used to perform statistical processing on the multiple indicator values ​​through the multiple target statistical strategies to obtain the multiple target statistical information.

[0018] In a possible implementation, the device further includes: a processing module for determining multiple historical statistical information of the multiple staff members; the processing module is also used to input the multiple historical statistical information and the multiple target statistical information into the prediction model to obtain the multiple target improvement measures.

[0019] In a possible implementation, the device also includes: a training module for determining sample data, the sample data including multiple sample statistical information and corresponding multiple sample improvement measures; the training module is also used to perform model training through the sample data to obtain the prediction model, and the prediction model is used to generate corresponding target improvement measures based on the target statistical information.

[0020] In a third aspect, the present application provides an electronic device comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement any method described in the first aspect.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by a processor as described in any one of the methods in the first aspect.

[0022] In a fifth aspect, the present application provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor as in any one of the methods in the first aspect.

[0023] The present application provides a method and device for alarming the work evaluation of quality control personnel in an information-based R&D project. The method includes: receiving an alarm request sent by a project quality control platform, wherein the alarm request includes multiple work information corresponding to multiple target staff members; identifying and processing the multiple work information through natural language processing technology and speech recognition technology to obtain multiple work data; determining multiple target statistical strategies, statistically processing the multiple work data through the multiple target statistical strategies to obtain multiple target statistical information, wherein the multiple target statistical information is used to indicate the degree of work completion; inputting the multiple target statistical information into a prediction model to obtain multiple target improvement measures, and generating alarm information based on the multiple target statistical information and the multiple target improvement measures, wherein the target improvement measures are used to improve the degree of work completion; sending the alarm information to a project management platform so that the project management platform completes the alarm prompting of the target staff members. The above scheme uses natural language processing technology and speech recognition technology for recognition and processing, which can effectively improve the recognition efficiency compared to the manual method, thereby improving the efficiency of alarm prompting. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0025] Figure 1 A schematic diagram of an application scenario of a method for providing an alarm for quality control personnel's work evaluation in an information-based R&D project provided in an embodiment of the present application;

[0026] Figure 2 A flowchart of a method for assessing and alerting quality control personnel in an information-based R&D project provided in an embodiment of the present application;

[0027] Figure 3 A flowchart of a method for assessing and alerting quality control personnel in an information-based R&D project provided in an embodiment of the present application;

[0028] Figure 4 A schematic diagram of grammatical error correction processing provided in an embodiment of the present application;

[0029] Figure 5 A schematic diagram of identification work data provided in an embodiment of the present application;

[0030] Figure 6 A schematic diagram of an application prediction model provided in an embodiment of the present application;

[0031] Figure 7 A schematic diagram of the structure of a work evaluation alarm device for quality control personnel of an information-based R&D project provided in an embodiment of the present application;

[0032] Figure 8 A schematic diagram of the structure of a work evaluation alarm device for quality control personnel of an information-based R&D project provided in an embodiment of the present application;

[0033] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0034] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0035] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0036] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0037] In addition, this application involves conducting big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and using artificial intelligence technology to make automated decisions, and making technical solutions that have a significant impact on personal rights and interests based on the results of automated decisions. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decisions; if the user chooses to reject, the expert decision-making process will be entered.

[0038] It should be noted that the quality control personnel work evaluation alarm method and device of the information technology research and development project of the present application can be used in the field of data processing technology, and can also be used in any field other than data processing. The application field of the quality control personnel work evaluation alarm method and device of the information technology research and development project of the present application is not limited.

[0039] Figure 1The present invention provides a schematic diagram of an application scenario of a method for evaluating and warning the work of quality control personnel in an information-based R&D project, and uses the scenario in the diagram as an example: During the execution of an information-based R&D project, the corresponding product is obtained by realizing the project requirements. There may be problems in the execution process, resulting in the product not meeting expectations. The quality control personnel manage the execution process through preset quality standards to improve the quality of the product.

[0040] In actual applications, there may be problems in the quality management process of quality control personnel, which will affect the quality of the product. Therefore, it is necessary to evaluate and warn the work of quality control personnel.

[0041] In the related art, problems in the work of quality control personnel are identified manually, and alarms are issued based on the problems. However, the work of quality control personnel generates a large amount of work information, and manually identifying problems from the work information is inefficient, resulting in low efficiency in evaluation and alarm.

[0042] The method for work evaluation and alarm of quality control personnel in information technology research and development projects provided in this application is intended to solve the above technical problems of the prior art.

[0043] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0044] Figure 2 A flowchart of a method for providing an alarm for quality control personnel's work evaluation of an information-based R&D project provided in an embodiment of the present application, the method comprising the following steps:

[0045] S201. Receive an alarm request sent by a project quality control platform, where the alarm request includes multiple work information corresponding to multiple target staff members.

[0046] Among them, the project quality management platform is used to carry out quality management of information technology R&D projects. The work information is the information generated by the execution of quality management work, and the project quality management platform stores the work information.

[0047] Exemplarily, the alarm request is used to request verification of whether there are problems in multiple work information of the target staff member. If there are problems, targeted work optimization is performed in a timely manner to improve the accuracy of quality management.

[0048] S202. Recognize and process multiple work information using natural language processing technology and speech recognition technology to obtain multiple work data.

[0049] The work information is the original information generated during the work process, for example, the work information may include work reports, meeting minutes, or test reports, etc. The work data is the key information extracted from the work information.

[0050] In the related art, target data is manually identified from multiple pieces of work information. However, due to the large amount of work information, this method has the problem of low efficiency.

[0051] S203, determining multiple target statistical strategies, performing statistical processing on multiple working data using the multiple target statistical strategies, and obtaining multiple target statistical information.

[0052] Among them, multiple target statistics are used to indicate the degree of work completion.

[0053] For example, the degree of work completion is used to evaluate whether the work tasks are completed on time, with quality and quantity guaranteed.

[0054] Exemplarily, multiple target statistical strategies correspond to multiple evaluation indicators, multiple target statistical information corresponds to multiple evaluation indicators, and each evaluation indicator corresponds to a different improvement measure.

[0055] Optionally, multiple evaluation indicators include but are not limited to at least one of the following: timely release rate of quality control weekly reports, number of process problems per team member, team process improvement rate, average weekly report release time, number of quality control weekly reports released, total number of team risks warned, total number of team process problems reported, and number of people in the management team.

[0056] Combined with the scenario example, the timely release rate of the quality control weekly report can reflect the punctuality of the staff's work. If the timely release rate of the quality control weekly report is low, the corresponding improvement measures can be to monitor the staff's work in real time and remind the staff to publish the weekly report on time.

[0057] The average number of process problems per team member can reflect the contribution ratio of the staff in the team. If the average number of process problems per team member is small, it means that the contribution ratio of the staff is small. The corresponding improvement measure can be to strengthen professional skills training.

[0058] The team process improvement rate can reflect the effectiveness of the team in solving problems. If the team process improvement rate is small, the corresponding improvement measures can be to introduce new tools to deeply analyze and solve problems.

[0059] The average weekly report publishing time can reflect the efficiency of weekly report preparation. If the average weekly report publishing time is long, the corresponding improvement measures can be to introduce standardized templates to reduce the workload of weekly reports, thereby improving the efficiency of weekly report preparation.

[0060] The number of quality control weekly reports can reflect the frequency of weekly reports. If the number of quality control weekly reports is small, it may affect the retrospective of work, and the corresponding improvement measures can be to formulate a weekly report release plan. If the number of quality control weekly reports is large, there may be a problem of redundant weekly report content, resulting in an increase in workload. The corresponding improvement measures can be to guide staff to optimize the content of the weekly reports to avoid duplication or irrelevant information in the weekly reports.

[0061] The total number of team risks warned can reflect the risk awareness of the staff. If the total number of team risks warned is small, it may indicate that the risk awareness of the staff is weak. The corresponding improvement measures can be to enhance risk management capabilities to accurately identify potential risk points.

[0062] The total number of team process problems reported can reflect the staff's ability to identify problems. If the total number of team process problems reported is small, the corresponding improvement measures can be to establish a practical guide for problem identification.

[0063] The number of people in the management team can reflect whether the workload of the staff is reasonable. If the number of people in the management team is small or large, the corresponding improvement measures can be to optimize resource allocation.

[0064] S204: Input multiple target statistical information into the prediction model to obtain multiple target improvement measures, and generate warning information according to the multiple target statistical information and the multiple target improvement measures.

[0065] Among them, target improvement measures are used to improve the degree of work completion.

[0066] Exemplarily, the prediction model determines multiple target improvement measures corresponding to multiple target statistical information according to a mapping relationship between statistical information and improvement measures.

[0067] In the related art, target improvement measures are obtained manually based on target statistical information identification. This method relies on experience and knowledge level and has the problem of low accuracy.

[0068] It can be understood that the present application generates target improvement measures through a prediction model, which can effectively improve the accuracy of the target improvement measures compared to manual methods, thereby improving the accuracy of the alarm prompts.

[0069] S205: Send the warning information to the project management platform so that the project management platform can complete the warning prompt to the target staff.

[0070] Exemplarily, the project management platform establishes a communication connection with each work team, issues an alarm to the work team based on the communication connection, and the work team optimizes the work of the staff members under the work team based on the alarm.

[0071] Optionally, the project management platform establishes a correspondence between each work team and a communication connection, determines a target communication connection based on the correspondence, and issues an alarm to the work team through the target communication connection.

[0072] The method for alarming the work evaluation of quality control personnel in an information-based R&D project provided in an embodiment of the present application includes: receiving an alarm request sent by a project quality control platform, the alarm request including multiple work information corresponding to multiple target staff members; identifying and processing multiple work information through natural language processing technology and speech recognition technology to obtain multiple work data; determining multiple target statistical strategies, statistically processing multiple work data through multiple target statistical strategies to obtain multiple target statistical information, wherein multiple target statistical information is used to indicate the degree of work completion; inputting multiple target statistical information into a prediction model to obtain multiple target improvement measures, and generating alarm information based on multiple target statistical information and multiple target improvement measures, wherein the target improvement measures are used to improve the degree of work completion; sending the alarm information to the project management platform so that the project management platform completes the alarm prompting of the target staff members. The above scheme uses natural language processing technology and speech recognition technology for recognition and processing, which can effectively improve the recognition efficiency compared to the manual method, thereby improving the efficiency of the alarm prompting.

[0073] Based on any of the above embodiments, Figure 3 , explains the detailed process of work evaluation alarm for quality control personnel in information technology R&D projects.

[0074] Figure 3 A flowchart of a quality control personnel work evaluation and alarm method for an information-based R&D project provided by an embodiment of the present application. Figure 3 As shown, the method includes:

[0075] S301. Receive an alarm request sent by a project quality control platform, where the alarm request includes multiple work information corresponding to multiple target staff members.

[0076] It should be noted that the execution process of S301 refers to S201 and will not be repeated here.

[0077] S302: Determine a plurality of first voice information and a plurality of first text information from a plurality of work information.

[0078] Exemplarily, the work information may be stored in the form of voice or text, and different storage forms correspond to different formats. A plurality of first voice information and a plurality of first text information are determined from the work information according to the format.

[0079] In combination with the scenario example, the staff can record the first voice information at work in the form of audio recording, or can record the first text information at work in the form of text.

[0080] Exemplarily, the first text information is in natural language form.

[0081] S303: Input the multiple first voice information into the voice recognition model respectively to obtain multiple voice feature information.

[0082] The voice feature information is an abstract representation of the first voice information.

[0083] Exemplarily, the voice feature information includes important information of the first voice information, including but not limited to at least one of the following: tone, speaking speed, or pronunciation characteristics, etc.

[0084] Optionally, the speech feature information includes but is not limited to at least one of the following: a spectrogram, Mel-Frequency Cepstral Coefficients (MFCCs), or filter bank energy (FBE).

[0085] Based on the above implementation, the high-dimensional original audio signal is converted into a low-dimensional feature vector to facilitate subsequent processing.

[0086] S304: Input the multiple voice features into the decoder respectively to obtain multiple initial text information.

[0087] Optionally, the decoder is combined with a language model, such as an N-gram model or an RNN language model, to improve the coherence and accuracy of the generated text using context information.

[0088] Combined with scenario examples, when the decoder encounters ambiguous pronunciations or similar words, it can determine the most likely text through context.

[0089] S305: Input the multiple initial text information into the generative adversarial network model respectively to obtain multiple second text information.

[0090] Among them, the generative adversarial network model is used to perform grammatical error correction on the initial text information.

[0091] Among them, the generative adversarial network model includes a generator and a discriminator.

[0092] Exemplarily, the generator is responsible for processing the input initial text information to generate second text information that has been processed with grammatical errors and is more in line with language specifications. The discriminator is responsible for evaluating whether the second text information is authentic and natural, thereby evaluating the generation quality of the generator.

[0093] Next, combine Figure 4 The grammatical error correction process is described.

[0094] Figure 4 This is a schematic diagram of the grammatical error correction process provided by the embodiment of the present application. Figure 4 As shown, the initial text information may have grammatical errors. The initial text information is input into the generator to obtain the generated text information. The discriminator receives the generated text information and evaluates the generated text information to obtain a discrimination result. The discrimination result is fed back to the generator so that the generator optimizes the generated text information. The confrontation process is repeated to obtain the optimized second text information.

[0095] S306: Identify and process the plurality of first text information and the plurality of second text information by using natural language processing technology to obtain a plurality of working data.

[0096] Exemplarily, natural language processing technology is used to identify and process keywords, sentiment words, or entity names in the plurality of first text information and the plurality of second text information to obtain a plurality of work data related to the evaluation work.

[0097] Exemplarily, keywords, sentiment words, or entity names are determined based on evaluation indicators of the evaluation work.

[0098] Next, combine Figure 5 The identification work data will be described.

[0099] Figure 5 This is a schematic diagram of the identification work data provided by the embodiment of the present application. Figure 5 As shown, a plurality of first voice messages and a plurality of first text messages are distinguished from a plurality of work messages. The plurality of first voice messages are converted into a plurality of corresponding second text messages by voice recognition technology. A plurality of work data are extracted from the plurality of first text messages and the plurality of second text messages by natural language processing technology.

[0100] S307: Determine the corresponding relationship between the evaluation index and the data type identifier.

[0101] The multiple working data include multiple data identifiers.

[0102] The data type identifier is used to distinguish the type of data.

[0103] Exemplarily, each evaluation indicator is associated with a corresponding data type.

[0104] Optionally, the corresponding relationship is obtained by dynamic adjustment according to actual business.

[0105] In conjunction with the scenario examples, the types of data include but are not limited to the number of weekly reports, the length of time it takes to publish weekly reports, the number of risks warned of, or the number of issues reported.

[0106] S308. Determine multiple target working data from multiple working data according to multiple target evaluation indicators and corresponding relationships.

[0107] The alarm request also includes multiple target evaluation indicators.

[0108] Among them, the project quality management platform requests evaluation and alarm of multiple work information from the dimensions corresponding to the target evaluation indicators.

[0109] Exemplarily, for any target evaluation indicator, the data type identifier corresponding to the target evaluation indicator is determined based on the target evaluation indicator and the corresponding relationship, and the data corresponding to the data type identifier among multiple working data is determined as the target working data corresponding to the target evaluation indicator. Similarly, multiple target working data are obtained in sequence.

[0110] Combined with the scenario example, multiple work data are grouped and processed through multiple target evaluation indicators and corresponding relationships, and the target work data in each group corresponds to one target evaluation indicator.

[0111] S309: Perform statistical processing on multiple target working data through multiple target statistical strategies to obtain multiple target statistical information.

[0112] Among them, multiple target statistical information evaluates the work information from multiple evaluation indicators respectively.

[0113] A feasible implementation method can perform statistical processing through the following method: calculate and process multiple target work data according to multiple target evaluation indicators to obtain multiple indicator values, where each indicator value corresponds to a target evaluation indicator; perform statistical processing on multiple indicator values ​​through multiple target statistical strategies to obtain multiple target statistical information.

[0114] Combined with the scenario examples, different evaluation indicators correspond to different indicator value calculation methods, for example:

[0115] The timely release rate of quality control weekly reports is the ratio of the number of weekly reports released on time by staff to the total number of weekly reports released.

[0116] The number of process problems per team member is the number of process problems generated, that is, the ratio of the total number of team problems to the total number of team members.

[0117] The team process improvement rate is the ratio of the number of problems improved by the team to the total number of problems in the team.

[0118] The average weekly report release time is the ratio of the total time staff spend on process improvement to the total number of weekly reports released.

[0119] The number of quality control weekly reports published is the total number of weekly reports published by staff during the preset period.

[0120] The total number of team risks warned is the number of team risks for which staff members submit warnings during the preset period.

[0121] The total number of team process issues reported is the number of team issues reported by staff during the preset period.

[0122] The management team size refers to the total number of people in the team managed by the staff member.

[0123] Among them, each target statistical strategy corresponds to a target evaluation indicator, and each target statistical strategy performs statistical processing on the indicator value corresponding to the corresponding target evaluation indicator.

[0124] Combined with the scenario example, taking the timely release rate evaluation indicator of the quality control weekly report as an example, the calculation formula for calculating the target statistical information can be:

[0125]

[0126] Among them, T represents the target statistical information, A represents the standard score, the standard score corresponds to the target evaluation index, B represents the index value of the target staff member, C represents the minimum value among the index values ​​of multiple staff members, D represents the maximum value among the index values ​​of multiple staff members, γ1 is the first coefficient, γ2 is the second coefficient, the first coefficient and the second coefficient correspond to the index type respectively, and the sum of the first coefficient and the second coefficient is 1.

[0127] Taking the average weekly report release duration evaluation indicator as an example, the calculation formula for calculating the target statistical information can be:

[0128]

[0129] Among them, T represents the target statistical information, A represents the standard score, the standard score corresponds to the target evaluation index, B represents the index value of the target staff member, C represents the minimum value among the index values ​​of multiple staff members, D represents the maximum value among the index values ​​of multiple staff members, γ1 is the first coefficient, γ2 is the second coefficient, the first coefficient and the second coefficient correspond to the index type respectively, and the sum of the first coefficient and the second coefficient is 1.

[0130] It should be noted that this application does not limit the specific implementation method of the target statistical strategy.

[0131] In this feasible implementation, by performing statistical calculations on each target evaluation indicator separately, interference between different data can be avoided, thereby accurately providing alarm prompts.

[0132] S310, inputting multiple target statistical information into a prediction model to obtain multiple target improvement measures, and generating alarm information according to the multiple target statistical information and the multiple target improvement measures.

[0133] A feasible implementation method can determine multiple target improvement measures by the following method: determine multiple historical statistical information of multiple staff members; input the multiple historical statistical information and multiple target statistical information into the prediction model to obtain multiple target improvement measures.

[0134] Optionally, historical statistics are determined by the personnel ID of the target worker.

[0135] Optionally, historical statistics are stored in a database.

[0136] Next, combine Figure 6 The application of the prediction model is described.

[0137] Figure 6 Schematic diagram of the application prediction model provided in the embodiment of the present application. Figure 6 As shown, the alarm request includes multiple work information and multiple staff identifications. Multiple target statistical information is obtained by evaluating the multiple work information. The corresponding multiple historical statistical information is obtained from the database through the multiple staff identifications. The multiple target statistical information and the multiple historical statistical information are input into the prediction model to obtain multiple target improvement measures.

[0138] Combined with the scenario example, the historical statistical information reflects the historical work situation of the target staff. The prediction model uses the historical statistical information as a reference standard to predict the target statistical information and obtain the target improvement measures.

[0139] In this feasible implementation, by combining target statistical information and historical statistical information for prediction, the content of input data can be enriched, and the data obtained by the prediction model can be increased, thereby improving the prediction accuracy of the prediction model.

[0140] A feasible implementation method is to train a prediction model by: determining sample data, where the sample data includes multiple sample statistical information and corresponding multiple sample improvement measures; training the model through the sample data to obtain a prediction model, where the prediction model is used to generate corresponding target improvement measures based on the target statistical information.

[0141] Optionally, the sample improvement measures are verified improvement measures.

[0142] For example, the sample improvement measures are used as labels for model training. The prediction model obtained through model training can learn the correlation between statistical information and improvement measures, and the prediction model predicts through the correlation to obtain the target improvement measures.

[0143] In this feasible implementation, the verified improvement measures are used as samples for model training, so that the prediction model can learn accurate mapping relationships, thereby improving the accuracy of alarm prompts.

[0144] S311. Send the alarm information to the project management platform so that the project management platform can complete the alarm prompt to the target staff.

[0145] It should be noted that the execution process of S311 refers to S205 and will not be repeated here.

[0146] Figure 7 A schematic diagram of a work evaluation alarm device for quality control personnel of an information-based R&D project provided in an embodiment of the present application. Figure 7 As shown, the quality control personnel work evaluation alarm device 70 of the information technology R&D project may include: a receiving module 71, an identification module 72, a statistical module 73, a prediction module 74, and a sending module 75, wherein:

[0147] The receiving module 71 is used to receive an alarm request sent by the project quality control platform, where the alarm request includes multiple work information corresponding to multiple target staff members.

[0148] The recognition module 72 is used to recognize and process multiple work information through natural language processing technology and speech recognition technology to obtain multiple work data.

[0149] The statistical module 73 is used to determine multiple target statistical strategies, perform statistical processing on multiple work data through the multiple target statistical strategies, and obtain multiple target statistical information, wherein the multiple target statistical information is used to indicate the degree of work completion.

[0150] The prediction module 74 is used to input multiple target statistical information into the prediction model to obtain multiple target improvement measures, and generate alarm information based on the multiple target statistical information and the multiple target improvement measures, wherein the target improvement measures are used to improve the degree of work completion.

[0151] The sending module 75 is used to send the alarm information to the project management platform so that the project management platform can complete the alarm prompt to the target staff.

[0152] Optionally, the receiving module 71 may execute Figure 2 S201 in the embodiment.

[0153] Optionally, the identification module 72 may execute Figure 2 S202 in the embodiment.

[0154] Optionally, the statistics module 73 may execute Figure 2 S203 in the embodiment.

[0155] Optionally, the prediction module 74 may perform Figure 2 S204 in the embodiment.

[0156] Optionally, the sending module 75 may execute Figure 2 S205 in the embodiment.

[0157] It should be noted that the work evaluation alarm device for quality control personnel of the information-based R&D project shown in the embodiment of the present application can execute the technical solution shown in the above method embodiment, and its implementation principle and beneficial effects are similar, which will not be repeated here.

[0158] In a possible implementation, the recognition module 72 is specifically used to: determine multiple first voice information and multiple first text information from multiple work information; convert the multiple first voice information into multiple second text information through voice recognition technology; and recognize and process the multiple first text information and multiple second text information through natural language processing technology to obtain multiple work data.

[0159] In one possible implementation, the recognition module 72 is specifically used to: input multiple first voice information into the voice recognition model respectively to obtain multiple voice feature information; input multiple voice features into the decoder respectively to obtain multiple initial text information; input multiple initial text information into the generative adversarial network model respectively to obtain multiple second text information, wherein the generative adversarial network model is used to perform grammatical error correction on the initial text information.

[0160] Figure 8 A schematic diagram of a work evaluation alarm device for quality control personnel of an information-based R&D project provided in an embodiment of the present application. Figure 7 Based on the embodiment shown, Figure 8 As shown, the quality control personnel work evaluation alarm device 80 of the information technology R&D project also includes: an execution module 76, a processing module 77, and a training module 78, wherein:

[0161] The multiple working data include multiple data type identifiers; the alarm request also includes multiple target evaluation indicators; the execution module 76 is used to: determine the correspondence between the evaluation indicators and the data type identifiers; determine multiple target working data from the multiple working data based on the multiple target evaluation indicators and the correspondence; perform statistical processing on the multiple target working data through multiple target statistical strategies to obtain multiple target statistical information.

[0162] In one possible implementation, the execution module 76 is specifically used to: calculate and process multiple target work data according to multiple target evaluation indicators to obtain multiple indicator values, where each indicator value corresponds to a target evaluation indicator; and perform statistical processing on the multiple indicator values ​​through multiple target statistical strategies to obtain multiple target statistical information.

[0163] The processing module 77 is used to: determine multiple historical statistical information of multiple staff members; input the multiple historical statistical information and multiple target statistical information into the prediction model to obtain multiple target improvement measures.

[0164] The training module 78 is used to: determine sample data, the sample data includes multiple sample statistical information and corresponding multiple sample improvement measures; perform model training through the sample data to obtain a prediction model, and the prediction model is used to generate corresponding target improvement measures according to the target statistical information.

[0165] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Fig. 9 As shown, the electronic device includes:

[0166] The electronic device includes a processor 291 and a memory 292; it may also include a communication interface 293 and a bus 294. The processor 291, the memory 292, and the communication interface 293 may communicate with each other through the bus 294. The communication interface 293 may be used for information transmission. The processor 291 may call the logic instructions in the memory 292 to execute the method of the above embodiment.

[0167] In addition, the logic instructions in the above-mentioned memory 292 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0168] The memory 292 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present application. The processor 291 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 292, that is, implementing the methods in the above method embodiments.

[0169] The memory 292 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 292 may include a high-speed random access memory and may also include a non-volatile memory.

[0170] An embodiment of the present application provides a non-temporary computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method as described in the above embodiment.

[0171] An embodiment of the present application provides a computer program product, including a computer program, which implements the method of the above embodiment when the computer program is executed by a processor.

[0172] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0173] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0174] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0175] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0176] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. The processor may be any appropriate hardware processor, such as CPU, GPU, FPGA, DSP, and ASIC, etc. The storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0177] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0178] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0179] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0180] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for warning the quality control personnel of an information technology R&D project, characterized in that: Applicable to servers, including: Receiving an alarm request sent by a project quality control platform, wherein the alarm request includes multiple work information corresponding to multiple target staff members; Recognize and process the plurality of work information by using natural language processing technology and speech recognition technology to obtain a plurality of work data; Determine a plurality of target statistical strategies, perform statistical processing on the plurality of work data by using the plurality of target statistical strategies, and obtain a plurality of target statistical information, wherein the plurality of target statistical information is used to indicate the degree of completion of the work; Inputting the plurality of target statistical information into a prediction model to obtain a plurality of target improvement measures, and generating warning information according to the plurality of target statistical information and the plurality of target improvement measures, wherein the target improvement measures are used to improve the degree of work completion; The warning information is sent to the project management platform so that the project management platform can complete the warning prompt to the target staff member.

2. The method according to claim 1, characterized in that: The plurality of work information are identified and processed by natural language processing technology and speech recognition technology to obtain a plurality of work data, including: Determine a plurality of first voice information and a plurality of first text information from the plurality of work information; Converting the plurality of first voice information into a plurality of second text information by using voice recognition technology; The plurality of first text information and the plurality of second text information are identified and processed by natural language processing technology to obtain the plurality of working data.

3. The method according to claim 2, characterized in that The method of converting the plurality of first voice information into a plurality of second text information by using a voice recognition technology comprises: Inputting the plurality of first voice information into a voice recognition model respectively to obtain a plurality of voice feature information; Inputting the plurality of speech features into a decoder respectively to obtain a plurality of initial text information; The multiple initial text information are respectively input into a generative adversarial network model to obtain the multiple second text information, wherein the generative adversarial network model is used to perform grammatical error correction processing on the initial text information.

4. The method according to any one of claims 1 to 3, characterized in that The multiple working data include multiple data type identifiers; the alarm request also includes multiple target evaluation indicators; the multiple working data are statistically processed by the multiple target statistical strategies to obtain multiple target statistical information, including: Determine the correspondence between evaluation indicators and data type identifiers; Determining a plurality of target working data from the plurality of working data according to the plurality of target evaluation indicators and the corresponding relationship; The multiple target statistical information is obtained by performing statistical processing on the multiple target working data using the multiple target statistical strategies.

5. The method according to claim 4, characterized in that The plurality of target working data are statistically processed by the plurality of target statistical strategies to obtain the plurality of target statistical information, including: Calculating and processing the plurality of target working data according to the plurality of target evaluation indicators to obtain a plurality of indicator values, wherein each indicator value corresponds to a target evaluation indicator; The multiple target statistical information is obtained by performing statistical processing on the multiple indicator values ​​using the multiple target statistical strategies.

6. The method according to claim 1, characterized in that Inputting the plurality of target statistical information into the prediction model obtains a plurality of target improvement measures, including: determining a plurality of historical statistics of the plurality of workers; The multiple historical statistical information and the multiple target statistical information are input into the prediction model to obtain the multiple target improvement measures.

7. The method according to claim 6, characterized in that The method further comprises: Determine sample data, where the sample data includes a plurality of sample statistical information and a corresponding plurality of sample improvement measures; The prediction model is obtained by performing model training through the sample data, and the prediction model is used to generate corresponding target improvement measures according to the target statistical information.

8. A work evaluation alarm device for quality control personnel of an information technology R&D project, characterized in that: Applicable to servers, including: A receiving module, used to receive an alarm request sent by a project quality control platform, wherein the alarm request includes multiple work information corresponding to multiple target staff members; A recognition module, used for recognizing and processing the plurality of work information by using natural language processing technology and speech recognition technology to obtain a plurality of work data; A statistical module, used to determine a plurality of target statistical strategies, and to perform statistical processing on the plurality of work data according to the plurality of target statistical strategies to obtain a plurality of target statistical information, wherein the plurality of target statistical information is used to indicate the degree of completion of the work; A prediction module, configured to input the plurality of target statistical information into a prediction model to obtain a plurality of target improvement measures, and to generate warning information according to the plurality of target statistical information and the plurality of target improvement measures, wherein the target improvement measures are used to improve the degree of work completion; The sending module is used to send the alarm information to the project management platform so that the project management platform can complete the alarm prompt to the target staff member.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images