Project risk prediction methods, devices, equipment, media and program products

Abstract

The present disclosure provides a project risk prediction method, which can be applied to the field of artificial intelligence technology. The project risk prediction method includes: obtaining the demand text of the risk to be predicted in the project and the product application involved in the demand text; calculating the similarity between the demand text and the historical production problem set, and obtaining at least one historical production problem whose similarity with the demand text is higher than a predetermined threshold, wherein the historical production problem set includes the problem text corresponding to each historical production problem; performing frequent item calculation based on the historical production problem set, and obtaining at least one risk product application associated with the product application; outputting at least one historical production problem and at least one risk product application to prompt the project risk associated with the demand text. The project risk prediction method provided by the present disclosure can improve the efficiency of risk prediction and has comprehensive prediction. The present disclosure also provides a project risk prediction device, equipment, storage medium and program product.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, specifically to the field of risk prediction, and more specifically to a project risk prediction method, device, equipment, medium and program product. Background Art

[0002] In the process of project management, in order to quickly adapt to business needs, the banking industry has gradually transformed the project development process from traditional methods to agile development to meet the market requirements for rapid product launch. Each project consists of multiple requirements, and each requirement is jointly developed and implemented by one or more product applications. After the project is launched, if there is a problem in production, the root cause of the problem will be analyzed and the name of the product application that caused the problem will be marked. If, during the project construction process, it can be automatically identified that similar production problems have occurred in the content of this transformation before, the possible production risks of the project can be verified during the testing process, greatly improving the operational stability of the project after it is launched.

[0003] In terms of predicting project risks, the traditional method is to rely on project developers to review their own development functions and propose potential problems as project risks for testing. Or rely on test managers or experts with rich work experience to predict possible production risks based on the requirements description and evaluate the risks after going online. Both methods rely entirely on human processing and require high work experience of risk identifiers. For current bank projects with fast iteration speeds, human errors are prone to occur when the project manager has too much workload.

[0004] In summary, in the current project management process, there is no method that can fully liberate manpower and automatically predict project risks. How to find a solution that can predict possible project risks from existing production problems is a technical problem that needs to be solved urgently in this field. Summary of the invention

[0005] In view of the above problems, the present disclosure provides a project risk prediction method, apparatus, device, medium and program product for improving risk prediction efficiency.

[0006] According to a first aspect of the present disclosure, a project risk prediction method is provided, including: obtaining a demand text of a risk to be predicted in a project and a product application involved in the demand text; calculating the similarity between the demand text and a set of historical production problems, and obtaining at least one historical production problem whose similarity to the demand text is higher than a predetermined threshold, wherein the set of historical production problems includes problem texts corresponding to each historical production problem; performing frequent item calculation based on the set of historical production problems, and obtaining at least one risky product application associated with the product application; and outputting at least one historical production problem and at least one risky product application to indicate a project risk associated with the demand text.

[0007] According to an embodiment of the present disclosure, calculating the similarity between a demand text and a set of historical production problems to obtain at least one historical production problem whose similarity to the demand text is higher than a predetermined threshold comprises: extracting multiple first keywords from the demand text, and extracting multiple second keywords from the problem text of each historical production problem; vectorizing the multiple first keywords to obtain a first feature vector, and respectively vectorizing the multiple second keywords of each historical production problem to obtain multiple second feature vectors; respectively calculating the similarity between the first feature vector and each second feature vector to obtain the similarity between the demand text and each problem text, so as to determine at least one historical production problem whose similarity to the demand text is higher than a predetermined threshold.

[0008] According to an embodiment of the present disclosure, extracting multiple first keywords of a demand text and extracting multiple second keywords of a problem text of each historical production issue include: separately performing word segmentation processing on the demand text and the problem text of each historical production issue; marking the parts of speech of the demand text and each problem text to filter out irrelevant words; matching the demand text with a preset keyword set to obtain multiple first keywords of the demand text; matching each historical production issue with the keyword set to obtain multiple second keywords of each problem text.

[0009] According to an embodiment of the present disclosure, multiple first keywords are vectorized to obtain a first feature vector, and multiple second keywords of each historical production problem are respectively vectorized to obtain multiple second feature vectors, including: obtaining custom parameter values ​​of each first keyword and each second keyword; calculating weight values ​​of each first keyword and each second keyword according to the TF-IDF algorithm and the custom parameter values; forming a first feature vector with the weight values ​​of multiple first keywords, and forming multiple second feature vectors with the weight values ​​of multiple second keywords of each question text.

[0010] According to an embodiment of the present disclosure, obtaining the custom parameter value of each first keyword and each second keyword includes: determining whether the first keyword or the second keyword belongs to a preset professional vocabulary set; when the first keyword or the second keyword belongs to the professional vocabulary set, setting the custom parameter value to a specific value; when the first keyword or the second keyword does not belong to the professional vocabulary set, setting the custom parameter value to 1.

[0011] According to an embodiment of the present disclosure, frequent item calculation is performed based on a historical production problem set to obtain at least one risky product application associated with a product application, including: obtaining the product application involved in each historical production problem from each problem text to obtain a product application set; performing frequent item calculation on the product application set to obtain multiple frequent item sets, wherein each frequent item set includes multiple product applications in the product application set whose correlation is higher than a predetermined threshold; matching the product application involved in the requirement text with the frequent item set to obtain at least one risky product application.

[0012] According to an embodiment of the present disclosure, frequent item calculation is performed based on a historical production problem set to obtain at least one risky product application associated with a product application, and the method further includes: obtaining the business type of each historical production problem from each problem text; and dividing the historical production problem set into multiple business problem sets according to the business type to narrow the scope of the product application set for frequent item calculation.

[0013] According to an embodiment of the present disclosure, it also includes: standardizing the demand text and each question text respectively to obtain texts that meet preset rules.

[0014] A second aspect of the present disclosure provides a project risk prediction device, including: an acquisition module, used to acquire a demand text of a risk to be predicted in a project and a product application involved in the demand text; a similarity calculation module, used to calculate the similarity between the demand text and a historical production problem set, and obtain at least one historical production problem whose similarity to the demand text is higher than a predetermined threshold, wherein the historical production problem set includes problem texts corresponding to each historical production problem; a frequent item calculation module, used to perform frequent item calculation based on the historical production problem set, and obtain at least one risky product application associated with the product application; and an output module, used to output at least one historical production problem and at least one risky product application to indicate the project risk associated with the demand text.

[0015] The third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned project risk prediction method.

[0016] The fourth aspect of the present disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned project risk prediction method.

[0017] The fifth aspect of the present disclosure also provides a computer program product, including a computer program, which implements the above-mentioned project risk prediction method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above contents and other purposes, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0019] Figure 1 A diagram schematically illustrates an application scenario of a project risk prediction method, apparatus, device, medium, and program product according to an embodiment of the present disclosure;

[0020] Figure 2 A flowchart of a project risk prediction method according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 3 The specific flow chart of S220 of the project risk prediction method according to the embodiment of the present disclosure is schematically shown;

[0022] Figure 4 The specific flow chart of S230 of the project risk prediction method according to the embodiment of the present disclosure is schematically shown;

[0023] Figure 5 A schematic diagram of a structure of a project risk prediction device according to an embodiment of the present disclosure is shown; and

[0024] Figure 6 A block diagram of an electronic device suitable for implementing a project risk prediction method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0025] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0026] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0027] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0028] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0029] The embodiments of the present disclosure provide a project risk prediction method, which is applied to the field of artificial intelligence, including: obtaining the demand text of the risk to be predicted in the project and the product application involved in the demand text; calculating the similarity between the demand text and the historical production problem set, and obtaining at least one historical production problem whose similarity with the demand text is higher than a predetermined threshold, wherein the historical production problem set includes the problem text corresponding to each historical production problem; performing frequent item calculation based on the historical production problem set, and obtaining at least one risk product application associated with the product application; outputting at least one historical production problem and at least one risk product application to indicate the project risk associated with the demand text. The project risk prediction method can comprehensively predict the potential project risks of the demand item in production based on the existing historical production problem set, and no longer completely rely on human judgment, so as to greatly improve the operational stability of the project after it goes online.

[0030] Figure 1 The application scenario diagram of the project risk prediction method according to the embodiment of the present disclosure is schematically shown.

[0031] like Figure 1 As shown, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0032] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0033] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0034] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0035] It should be noted that the project risk prediction method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the project risk prediction device provided in the embodiment of the present disclosure can generally be set in the server 105. The project risk prediction method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the project risk prediction device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0036] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0037] The following will be based on Figure 1 The scene described by Figure 2 to Figure 4 The project risk prediction method of the disclosed embodiment is described in detail.

[0038] Figure 2 The flowchart of the project risk prediction method according to the embodiment of the present disclosure is schematically shown.

[0039] like Figure 2 As shown, the project risk prediction method of this embodiment includes operations S210 to S240, and the project risk prediction method can be executed by the server 105.

[0040] In operation S210, a demand text of a risk to be predicted in a project and a product application involved in the demand text are obtained.

[0041] In software project management / development, each project consists of multiple requirement items. The requirement items include the requirement text written by project developers based on project requirements and requirement rules. The requirement text describes the project name, business type, business scenario, requirement description, and product applications involved.

[0042] In the embodiments of the present disclosure, the demand items for which risks are to be predicted are all valid demand items, and valid demand items refer to demand items whose project approval status is approved by joint approval. The demand texts of the valid demand items are obtained to perform risk prediction.

[0043] In operation S220, the similarity between the demand text and the historical production problem set is calculated to obtain at least one historical production problem having a similarity with the demand text higher than a predetermined threshold, wherein the historical production problem set includes problem texts corresponding to each historical production problem.

[0044] The historical production problem set is a collection of historical production problems that have been solved in historical projects. The root cause analysis of these historical production problems has been completed during the development of the historical projects. Each historical production problem has a corresponding problem text, which describes the problem classification, problem description, product applications involved, problem root cause analysis, problem generation time, etc. of the historical production problem.

[0045] According to an embodiment of the present disclosure, it also includes: standardizing the demand text and each question text respectively to obtain texts that meet preset rules.

[0046] According to preset rules, the demand text and each question text are parsed and attributed to form text data in a standardized format. The standardized text data is output in a regularized manner and transformed into a modeling data source that is easy to identify for modeling. By standardizing the demand text and each question text, subsequent data calculations are facilitated, which helps to improve the efficiency and accuracy of risk prediction.

[0047] Figure 3 The specific flow chart of S220 of the project risk prediction method according to the embodiment of the present disclosure is schematically shown.

[0048] like Figure 3 As shown, operation S220 of the project risk prediction method of this embodiment specifically includes the following operations S221 to S223.

[0049] In operation S221, a plurality of first keywords of the demand text are extracted, and a plurality of second keywords of the problem text of each historical production problem are extracted.

[0050] According to an embodiment of the present disclosure, extracting multiple first keywords of a demand text and extracting multiple second keywords of a problem text of each historical production issue include: separately performing word segmentation processing on the demand text and the problem text of each historical production issue; marking the parts of speech of the demand text and each problem text to filter out irrelevant words; matching the demand text with a preset keyword set to obtain multiple first keywords of the demand text; matching each historical production issue with the keyword set to obtain multiple second keywords of each problem text.

[0051] In the embodiment of the present disclosure, the CRF algorithm (conditional random field algorithm) is used to perform basic Chinese word segmentation on the modeling data sources of the demand text and each question text, and a value set is established to calculate the labeling probability between words, and the parts of speech are marked to help perform Chinese word segmentation. For example, the FudanNLP toolkit can be used to mark nouns, verbs and other parts of speech, and filter out special symbols, adjectives, auxiliary words and other useless words, so as to reduce the dimensionality of the subsequent word vector model and improve the efficiency of project risk prediction. The demand text and each question text are screened using the existing keyword set, and then the first keyword and the second keyword are determined.

[0052] In operation S222, the plurality of first keywords are vectorized to obtain first feature vectors, and the plurality of second keywords of each historical production problem are respectively vectorized to obtain plurality of second feature vectors.

[0053] According to an embodiment of the present disclosure, multiple first keywords are vectorized to obtain a first feature vector, and multiple second keywords of each historical production problem are respectively vectorized to obtain multiple second feature vectors, including: obtaining custom parameter values ​​of each first keyword and each second keyword; calculating weight values ​​of each first keyword and each second keyword according to a TF-IDF (term frequency-inverse document frequency) algorithm and custom parameter values; forming a first feature vector with the weight values ​​of multiple first keywords, and forming multiple second feature vectors with the weight values ​​of multiple second keywords of each question text.

[0054] The word frequency TF is the proportion of each keyword to all keywords, and the inverse text frequency index IDF reflects the frequency of the number of times the text containing the keyword appears in all texts. For example, the first feature vector is composed of the weight values ​​of M first keywords, and the i-th first keyword in the first feature vector is t i , 1≤i≤M, the frequency of the first keyword in the keyword set is f i , there are n question texts containing the first keyword i The total number of question texts is N, then the first keyword t i The inverse document frequency index IDF i =log(N / n i ).

[0055] According to an embodiment of the present disclosure, obtaining the custom parameter value of each first keyword and each second keyword includes: determining whether the first keyword or the second keyword belongs to a preset professional vocabulary set; when the first keyword or the second keyword belongs to the professional vocabulary set, setting the custom parameter value to a specific value; when the first keyword or the second keyword does not belong to the professional vocabulary set, setting the custom parameter value to 1.

[0056] For example, in the banking industry, the custom parameter value is set to k to determine whether the extracted keyword belongs to the banking professional vocabulary set. If the keyword belongs to the banking professional vocabulary set, the k value is 100, otherwise the k value is 1. Combine the TF-IDF algorithm and the custom parameter value k to calculate the weight value of each keyword. For example, set the first keyword t i The weight value is w i , w i =k*f i *IDF i Similarly, the weight value w of each second keyword in the second feature vector i 'This method is also used for calculation.

[0057] In operation S223, the similarities between the first feature vector and each second feature vector are calculated respectively to obtain the similarities between the requirement text and each problem text, so as to determine at least one historical production problem whose similarity with the requirement text is higher than a predetermined threshold.

[0058] For example, the first feature vector corresponding to a certain requirement text S1 is set to S1(w1, w2, ..., w n ), a question text T1 = T1(w1', w2', ..., w n '), let the similarity between the requirement text S1 and the question text T1 be Sim(S1, T1), and use the cosine theorem to calculate the similarity,

[0059]

[0060] Due to the subjective habits in writing demand texts and problem texts, the threshold is used to adjust the similarity judgment requirements, and the similarity threshold is set to p. The size between Sim(S1, T1) and p is compared. When Sim(S1, T1) is greater than p, it is considered that there is a correlation between the demand item corresponding to the demand text S1 and the historical production problem corresponding to the problem text T1, otherwise it is assumed that there is no correlation. Using the above method, all historical production problems with a similarity to the demand text higher than the predetermined threshold are calculated. Based on the original data of production problems, the most concerned risk hazards of the project can be truly reflected through the existing historical production problem set, no longer relying entirely on the human judgment of experienced experts or test managers, and getting rid of human dependence in the project risk prediction process.

[0061] In operation S230 , frequent item calculation is performed based on the historical production problem set to obtain at least one risky product application associated with the product application.

[0062] Figure 4 The specific flow chart of S230 of the project risk prediction method according to the embodiment of the present disclosure is schematically shown.

[0063] like Figure 4 As shown, operation S230 of the project risk prediction method of this embodiment specifically includes the following operations S231 to S233.

[0064] In operation S231, the product application involved in each historical production problem is obtained from each problem text to obtain a product application set.

[0065] According to an embodiment of the present disclosure, frequent item calculation is performed based on a historical production problem set to obtain at least one risky product application associated with a product application, and the method further includes: obtaining the business type of each historical production problem from each problem text; and dividing the historical production problem set into multiple business problem sets according to the business type to narrow the scope of the product application set for frequent item calculation.

[0066] In an embodiment of the present disclosure, question texts are classified according to business types to obtain multiple business question sets, and then product applications involved in historical production problems are obtained from each question text in the business question set, thereby obtaining a product application set for each business question set.

[0067] In operation S232, frequent item calculation is performed on the product application set to obtain a plurality of frequent item sets, wherein each frequent item set includes a plurality of product applications in the product application set whose correlation degree is higher than a predetermined threshold.

[0068] Next, frequent items are calculated for the product application set of each business problem set.

[0069] Based on the FP-growth (Frequent Pattern-growth) algorithm, the support parameter and confidence parameter are set independently to control the number of frequent items and the accuracy of association rules that can be generated by the current application set. The support parameter is set to 0.5, that is, the number of records containing the item set in the data set accounts for a proportion of greater than or equal to 0.5 of the entire data set; the confidence parameter is set to 0.75, that is, the number of records in the item set accounts for a proportion of greater than or equal to 0.75 of the number of records in each item.

[0070] Calculate the frequent item sets in the current data set, that is, the frequent item sets of the product application set of each business problem set. It can be generally considered that if an item set is a non-frequent item set, then all its supersets are also non-frequent. Therefore, when the number of items in the set is greater than 0, a list of item sets consisting of k items is constructed in a loop, and the item sets with support greater than or equal to n are retained and a list of item sets consisting of k+1 items is generated until the number of items is equal to 0, and the initial value k=1. Output the frequent item sets of product applications of the current data set. Table 1 is an example table of frequent item sets of associated applications, showing the generation results of frequent items with support of 0.5 and 0.7 respectively.

[0071] The obtained frequent item set is further calculated to account for the number of records in the item set and the number of records in each item, and compared with the set confidence parameter value. If it is greater than or equal to the confidence parameter, it is assumed to be an association rule that meets the conditions. Table 2 is an example table of frequent item sets under association rules, showing the rule generation results of confidence 0.7 and 0.6 respectively. For example, {Fa}->{Fc} means that when {Fa} appears, {Fc} may also appear. This method can be used to select when there is a demand item involving the application {Fa}, then the demand item may also have the risk of applying {Fc}.

[0072] Table 1:

[0073] Support Frequent Itemsets 0.5 {Fb, Fc, Fe}, {Fa, Fc}, {Fb, Fe}, {Fb, Fc}, {Fc, Fe}, {Fa}, {Fb}, {Fc}, {Fe} 0.7 {Fb, Fe}, {Fb}, {Fc}, {Fe}

[0074] Table 2:

[0075]

[0076] In operation S233, the product applications involved in the requirement text are matched with the frequent item sets to obtain at least one risky product application.

[0077] By matching the product applications involved in the requirement text with the frequent item sets obtained in the above operation, the risk product applications associated with the product applications can be obtained, and the associated application sets can be automatically mined. Thresholds are set for frequent item rules to control the accuracy of the association rules, avoiding the risk of missing associated applications in the project risk prediction process, greatly improving the comprehensiveness of risk prediction, having forward-looking prediction capabilities, and greatly saving the time cost of communicating with all parties involved in application development.

[0078] In operation S240 , at least one historical production problem and at least one risky product application are output to indicate project risks associated with the requirement text.

[0079] Table III schematically shows the project risk prediction results.

[0080] In addition, it is also possible to manually intervene in the project risk prediction results by manually entering association rules and associating one or more production issues that are definitely involved with the demand text of the risk to be predicted, thereby reducing the calculation cost. By manually adjusting or re-associating the production issues, a more realistic project risk prediction result can be ultimately generated.

[0081] Table 3:

[0082]

[0083] The project risk prediction method provided by the present disclosure truly reflects the most concerned risk hazards of the project based on the existing historical production problem set, and no longer relies entirely on manual judgment, liberating manpower and improving the efficiency of risk prediction. The project risk prediction method can also automatically mine the application set with associations through frequent item calculation, set thresholds for frequent item rules to control the accuracy of association rules, avoid missing the risk of associated applications in the process of project risk identification, and greatly improve the comprehensiveness of risk prediction.

[0084] Based on the above project risk prediction method, the present disclosure also provides a project risk prediction device. Figure 5 The device is described in detail.

[0085] Figure 5 The structural block diagram of the project risk prediction device according to an embodiment of the present disclosure is schematically shown.

[0086] like Figure 5 As shown, the project risk prediction device 500 of this embodiment includes an acquisition module 510 , a similarity calculation module 520 , a frequent item calculation module 530 and an output module 540 .

[0087] The acquisition module 510 is used to acquire the demand text of the risk to be predicted in the project and the product application involved in the demand text. In one embodiment, the acquisition module 510 can be used to perform the operation S210 described above, which will not be repeated here.

[0088] The similarity calculation module 520 is used to calculate the similarity between the demand text and the historical production problem set, and obtain at least one historical production problem whose similarity to the demand text is higher than a predetermined threshold, wherein the historical production problem set includes the problem text corresponding to each historical production problem. In one embodiment, the similarity calculation module 520 can be used to perform the operation S220 described above, which will not be repeated here.

[0089] The frequent item calculation module 530 is used to calculate frequent items based on the historical production problem set to obtain at least one risky product application associated with the product application. In one embodiment, the frequent item calculation module 530 can be used to perform the operation S230 described above, which will not be described in detail here.

[0090] The output module 540 is used to output at least one historical production problem and at least one risky product application to indicate the project risk associated with the requirement text. In one embodiment, the output module 540 can be used to perform the operation S240 described above, which will not be described in detail here.

[0091] According to an embodiment of the present disclosure, any multiple modules among the acquisition module 510, the similarity calculation module 520, the frequent item calculation module 530 and the output module 540 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 510, the similarity calculation module 520, the frequent item calculation module 530 and the output module 540 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware and firmware or in a proper combination of any of them. Alternatively, at least one of the acquisition module 510, the similarity calculation module 520, the frequent item calculation module 530 and the output module 540 may be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function may be executed.

[0092] Figure 6 A block diagram of an electronic device suitable for implementing a project risk prediction method according to an embodiment of the present disclosure is schematically shown.

[0093] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0094] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0095] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the I / O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0096] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the project risk prediction method according to the embodiment of the present disclosure is implemented.

[0097] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0098] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the project risk prediction method provided by the embodiment of the present disclosure.

[0099] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 601. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0100] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0101] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, apparatus, module, unit, etc. described above can be implemented by a computer program module.

[0102] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0103] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0104] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0105] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A project risk prediction method, comprising: Obtain the demand text of the risks to be predicted in the project and the product applications involved in the demand text; Calculate the similarity between the demand text and the set of historical production problems, and obtain at least one historical production problem whose similarity to the demand text is higher than a predetermined threshold, wherein the set of historical production problems includes the problem texts corresponding to the various historical production problems; specifically comprising: extracting a plurality of first keywords from the demand text, and extracting a plurality of second keywords from the problem text of each historical production problem; vectorizing the plurality of first keywords to obtain a first feature vector, and respectively vectorizing a plurality of second keywords of each historical production problem to obtain a plurality of second feature vectors; respectively calculating the similarity between the first feature vector and each second feature vector to obtain the similarity between the demand text and each problem text, so as to determine at least one historical production problem whose similarity to the demand text is higher than a predetermined threshold; Frequent item calculation is performed based on the historical production problem set to obtain at least one risk product application associated with the product application; specifically comprising: obtaining the product application involved in each historical production problem from each problem text to obtain a product application set; performing frequent item calculation on the product application set to obtain multiple frequent item sets, wherein each frequent item set includes multiple product applications in the product application set whose correlation is higher than a predetermined threshold; matching the product application involved in the demand text with the frequent item set to obtain the at least one risk product application; The at least one historical production problem and the at least one risky product application are output to indicate the project risk associated with the requirement text.

2. The project risk prediction method according to claim 1, wherein the extracting of the plurality of first keywords of the demand text and the extracting of the plurality of second keywords of the problem text of each historical production problem comprises: Performing word segmentation processing on the demand text and the problem text of each historical production problem respectively; Marking the demand text and each question text with parts of speech to filter out irrelevant words; Matching the demand text with a preset keyword set to obtain a plurality of first keywords of the demand text; The historical production questions are matched with the keyword set to obtain a plurality of second keywords for each question text.

3. The project risk prediction method according to claim 1, wherein the first keywords are vectorized to obtain a first feature vector, and The multiple second keywords of each historical production problem are vectorized respectively, and the multiple second feature vectors obtained include: Get the custom parameter value of each first keyword and each second keyword; Calculate the weight value of each first keyword and each second keyword according to the TF-IDF algorithm and the custom parameter value; The first feature vector is composed of the weight values ​​of the plurality of first keywords, and the plurality of second feature vectors are composed of the weight values ​​of the plurality of second keywords of each question text.

4. According to the project risk prediction method of claim 3, the step of obtaining the custom parameter value of each first keyword and each second keyword comprises: Determining whether the first keyword or the second keyword belongs to a preset professional vocabulary set; When the first keyword or the second keyword belongs to the professional vocabulary set, setting the custom parameter value to a specific value; When the first keyword or the second keyword does not belong to the professional vocabulary set, the custom parameter value is set to 1.

5. The project risk prediction method according to claim 1, wherein the frequent item calculation based on the historical production problem set to obtain at least one risky product application associated with the product application further comprises: Get the business type of each historical production problem from each problem text; The historical production problem set is divided into a plurality of business problem sets according to business types, so as to narrow the scope of the product application set for frequent item calculation.

6. The project risk prediction method according to claim 1, further comprising: The requirement text and each question text are standardized respectively to obtain texts that meet preset rules.

7. A project risk prediction device, comprising: An acquisition module, used to acquire the demand text of the risk to be predicted in the project and the product application involved in the demand text; A similarity calculation module is used to calculate the similarity between the demand text and the historical production problem set, and obtain at least one historical production problem whose similarity with the demand text is higher than a predetermined threshold, wherein the historical production problem set includes the problem texts corresponding to the various historical production problems; specifically comprising: extracting a plurality of first keywords from the demand text, and extracting a plurality of second keywords from the problem text of each historical production problem; vectorizing the plurality of first keywords to obtain a first feature vector, and respectively vectorizing a plurality of second keywords of each historical production problem to obtain a plurality of second feature vectors; respectively calculating the similarity between the first feature vector and each second feature vector to obtain the similarity between the demand text and each problem text, so as to determine at least one historical production problem whose similarity with the demand text is higher than a predetermined threshold; A frequent item calculation module is used to perform frequent item calculation based on the historical production problem set to obtain at least one risky product application associated with the product application; specifically comprising: obtaining the product application involved in each historical production problem from each problem text to obtain a product application set; performing frequent item calculation on the product application set to obtain multiple frequent item sets, wherein each frequent item set includes multiple product applications in the product application set whose correlation is higher than a predetermined threshold; matching the product application involved in the demand text with the frequent item set to obtain the at least one risky product application; and An output module is used to output the at least one historical production problem and the at least one risky product application to prompt the project risk associated with the requirement text.

8. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images