Software function configuration method based on self-learning

Abstract

The present invention relates to the technical field of computer software application development, and in particular to a software function configuration method based on self-learning. The present invention uploads the historical data of the enterprise, processes the historical data, constructs the corresponding function module, calculates the degree of coordination, determines whether the construction of the function module meets the standard based on the degree of coordination, and determines whether the number of historical data used meets the standard or determines the reason for not meeting the standard when it is determined that the standard is not met, generates corresponding processing instructions based on the reason for not meeting the standard, and transmits the corresponding processing instructions to the corresponding components so that the components receiving the instructions re-determine the operating parameters to complete the construction of the function module. The present invention effectively realizes real-time monitoring of whether the system meets the standard after the software function configuration, effectively realizes precise adjustment of the system's operating parameters when the system after the software function configuration does not meet the standard, and effectively improves the operating efficiency of the system after the software function configuration.

Description

Technical Field

[0001] The present invention relates to the technical field of computer software application development, and in particular to a software function configuration method based on self-learning. Background Art

[0002] When existing software, especially enterprise-level software, is applied to enterprises, it is necessary to configure the software in combination with the information, processes, systems and other characteristics of the enterprise. This process is generally called software implementation. The implementation process includes project establishment, interviews with enterprises by implementation experts, implementation experts sorting out plans, and configuring and customizing the software. Since the configuration process of software requires a lot of manpower and material resources, it is of great research significance to combine the historical data of the enterprise and the technology of artificial intelligence to automatically discover the processes, systems, information, etc. of the enterprise, and then automatically configure the software. Implementation experts only need to make simple modifications to allow the software to be used in the enterprise.

[0003] Chinese patent publication number: CN110531964B, discloses a method, system and device for supporting flexible configuration of complex business processes within an enterprise. The method develops and implements business process template configuration functions and business process operation functions in a PC-side system, including query form maintenance functions, operation form maintenance functions and business process maintenance functions. Through the query form maintenance function, the query interface configuration information of each process node function of the business process is saved to the database persistence layer; through the operation form maintenance function, the operation interface configuration information of each process node function of the business process is saved to the database persistence layer; through the business process maintenance function, the number of nodes of the business process is configured, and the query form, operation form and operation organization level information of each process node function are set.

[0004] It can be seen that the above scheme can meet the personalized needs of the business processes within the enterprise through a small amount of implementation and development work, aiming at the current problems of inflexible business processes, different businesses but similar functions, low reusability and large development workload, and can be applied to the flexible configuration of complex business processes within the enterprise. However, the above scheme cannot achieve real-time monitoring of whether the system meets the standards after the software function configuration, nor can it accurately adjust the system's operating parameters when the system does not meet the standards after the software function configuration, thus failing to guarantee the operating efficiency of the system after the software function configuration. Summary of the invention

[0005] To this end, the present invention provides a software function configuration method based on self-learning, which is used to overcome the problems in the prior art that it is impossible to realize real-time monitoring of whether the system after the software function configuration meets the standards and it is impossible to accurately adjust the system's operating parameters when the system after the software function configuration does not meet the standards, resulting in low operating efficiency of the system after the software function configuration.

[0006] To achieve the above object, the present invention provides a software function configuration method based on self-learning, comprising:

[0007] Upload the company's historical data to the software function configuration system;

[0008] Extracting keywords from the historical data and processing the historical data after the keywords are extracted, including screening the historical data and normalizing the screened historical data;

[0009] Constructing corresponding functional modules according to the processed historical data;

[0010] Determine the functions of the functional modules and calculate the degree of fit based on the functions and actual requirements;

[0011] Determining whether the construction of the functional module meets the standard based on the degree of fit, and determining whether the amount of the historical data used meets the standard based on the degree of fit when it is determined that the construction of the functional module does not meet the standard, or determining the reason why the construction of the functional module does not meet the standard based on the historical data; generating a corresponding processing instruction based on the reason for not meeting the standard;

[0012] Transmitting the corresponding processing instructions to the corresponding components so that the components receiving the instructions re-determine the operating parameters to complete the construction of the functional modules;

[0013] When it is determined that the construction of the functional module meets the standard, the software function configuration is completed and a configuration success notification is issued;

[0014] After completing the software function configuration, the software function configuration system is analyzed, tried, adjusted and improved.

[0015] Furthermore, the process of extracting the keywords of the historical data includes:

[0016] Obtaining a corresponding demand keyword group including a plurality of demand keywords according to the content of the single actual demand;

[0017] Extracting keywords from the historical data based on the demand keyword group, and determining the demand matching degree between each historical data and each demand keyword group in turn; wherein the demand matching degree between a single historical data and the demand keyword group is the ratio of the number of matching keywords in the historical data to the total number of demand keywords, and the matching keyword is a keyword extracted from the historical data that matches the demand keyword;

[0018] Comparing the demand matching degree with a preset demand matching degree;

[0019] For a single piece of the historical data, when the demand matching degree between the historical data and the demand keyword is less than a preset demand matching degree, the historical data is screened out.

[0020] Furthermore, the process of determining the function of the functional module and calculating the degree of fit based on the function and the actual demand includes:

[0021] Record the functions of the constructed functional module as actual functions;

[0022] When the actual function can solve a single actual requirement, determining that the actual function matches the actual requirement;

[0023] The ratio of the number of the actual demands having a matching relationship to the total number of the actual demands is calculated, and the obtained ratio is recorded as the matching degree.

[0024] Furthermore, the process of determining whether the construction of the functional module meets the standard based on the degree of fit includes:

[0025] Comparing the degree of fit with a pre-stored preset degree of fit;

[0026] When the degree of fit is greater than or equal to a second preset degree of fit, it is determined that the construction of the functional module meets the standard, the software function configuration is completed, and a configuration success notification is issued;

[0027] When the degree of fit is less than the second preset degree of fit and greater than or equal to the first preset degree of fit, determining that the construction of the functional module does not meet the standard, and determining whether the amount of the historical data used meets the standard based on the degree of fit;

[0028] When the degree of fit is less than the first preset degree of fit, it is determined that the construction of the functional module does not meet the standard, and the reason why the construction of the functional module does not meet the standard is determined based on the historical data.

[0029] Furthermore, the process of determining whether the amount of the historical data used meets the standard based on the degree of cooperation includes:

[0030] Determining the matching relationship in the degree of fit;

[0031] Counting the number of the actual functions having the matching relationship;

[0032] Calculate the ratio of the number of the actual functions that have the matching relationship to the total number of actual functions, and record the obtained ratio as the overlap ratio;

[0033] Determining whether the amount of the historical data used meets the standard based on the overlap ratio;

[0034] When the overlap ratio is greater than the preset overlap ratio, it is determined that the amount of the historical data used does not meet the standard, the historical data needs to be supplemented, and the amount of the historical data is corrected based on the overlap ratio;

[0035] When the overlap ratio is less than or equal to the preset overlap ratio, it is determined that the quantity of the historical data used meets the standard and the construction of the functional module does not meet the standard, and the reason why the construction of the functional module does not meet the standard is determined based on the historical data.

[0036] Furthermore, the process of correcting the quantity of the historical data based on the overlap ratio includes:

[0037] Calculate the difference between the overlap ratio and a preset overlap ratio, and record the obtained difference as the overlap ratio difference;

[0038] Based on the overlap ratio difference, the amount of the historical data is increased and the increased amount of the historical data is recorded as the supplementary amount, and the supplementary amount is proportional to the overlap ratio difference.

[0039] Further, after the increase in the amount of the historical data is completed, the process of determining whether the screening process meets the standard based on the supplementary amount includes:

[0040] Determine the amount of replenishment actually used in the replenishment amount, and record the obtained amount of replenishment actually used as the actual replenishment amount;

[0041] Calculating the ratio of the replenishment amount to the actual replenishment amount, and recording the obtained ratio as the replenishment amount ratio;

[0042] Determining whether the screening process meets the standard based on the replenishment amount ratio;

[0043] comparing the replenishment amount ratio with a pre-stored preset replenishment amount ratio;

[0044] When the supplement amount ratio is greater than a preset supplement amount ratio, determining that the screening process does not meet the standard, and issuing a screening process non-compliant notification;

[0045] When the replenishment amount ratio is less than or equal to the preset replenishment amount ratio, it is determined that the screening process meets the standard, and the software function configuration is re-performed based on the historical data after the replenishment is completed.

[0046] Further, the process of determining the reason why the construction of the functional module does not meet the standard based on the historical data includes:

[0047] Determine the usage of the historical data in the process of constructing the corresponding functional module according to the processed historical data, and record the obtained usage as the historical data usage;

[0048] Calculating the ratio of the historical data usage to the total amount of the historical data, and recording the obtained ratio as the data usage rate;

[0049] Determining the reason why the construction of the functional module does not meet the standard based on the data usage rate;

[0050] comparing the data usage rate with a pre-stored preset data usage rate;

[0051] When the data usage rate is less than or equal to the preset data usage rate, it is determined that the reason why the construction of the functional module does not meet the standard is that invalid data exists, and the data transmission process needs to be optimized, and the bandwidth is increased based on the data usage rate;

[0052] When the data usage rate is greater than the preset data usage rate, it is determined that the reason why the construction of the functional module does not meet the standard is that the extraction of keywords from the historical data does not meet the standard, and the preset requirement matching degree is increased based on the matching degree.

[0053] Further, the process of increasing the bandwidth based on the data usage rate includes:

[0054] Calculating a difference between the preset data usage rate and the data usage rate, and recording the obtained difference as a usage rate difference;

[0055] The bandwidth is increased based on the usage rate difference, and the increase in bandwidth is proportional to the usage rate difference.

[0056] Furthermore, the process of increasing the matching degree of the preset requirement based on the matching degree includes:

[0057] Calculating the difference between the first preset matching degree and the matching degree, and recording the obtained difference as the matching degree difference;

[0058] The preset requirement matching degree is increased based on the matching degree difference, and the increase range of the preset requirement matching degree is proportional to the matching degree difference.

[0059] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention determines whether the construction of the functional module meets the standards based on the degree of fit, can timely and accurately complete the determination of whether the construction of the functional module meets the standards, and when it is determined that the construction of the functional module does not meet the standards, it determines whether the number of historical data used meets the standards based on the degree of fit or determines the reason why the construction of the functional module does not meet the standards based on the historical data, effectively realizing real-time monitoring of whether the system meets the standards after the software function configuration, generating corresponding processing instructions based on the reasons for not meeting the standards, and transmitting the corresponding processing instructions to the corresponding components so that the components receiving the instructions re-determine the operating parameters to complete the construction of the functional module, effectively realizing precise adjustment of the system's operating parameters when the system does not meet the standards after the software function configuration, and effectively improving the operating efficiency of the system after the software function configuration.

[0060] Furthermore, when extracting keywords from historical data, the historical data that needs to be screened out is determined based on the degree of matching with the requirements, and the historical data used to build the functional module is determined, which effectively ensures that the historical data used matches the requirements, and further improves the operating efficiency of the system after the software function is configured.

[0061] Furthermore, when determining the functions of the functional modules and calculating the degree of fit based on the functions and actual requirements, the degree of fit is calculated based on the ratio of the number of actual requirements with a matching relationship to the total number of actual requirements. This can accurately determine whether the constructed functional modules meet the actual requirements, further improving the operating efficiency of the system after the software function configuration.

[0062] Furthermore, whether the amount of historical data used meets the standards is determined based on the overlap ratio, so the matching between the actual functions of the constructed functional modules and the actual needs can be determined more accurately to avoid misjudgment. While further realizing real-time monitoring of whether the system meets the standards after the software function configuration, the operating efficiency of the system after the software function configuration is further improved.

[0063] Furthermore, when it is determined that the number of historical data used does not meet the standards, the number of historical data is increased based on the difference in the overlap ratio, so as to avoid the situation where the construction of functional modules does not meet the standards due to the number of historical data not meeting the standards. This further realizes the precise adjustment of the system's operating parameters when the system does not meet the standards after the software function configuration, and further improves the operating efficiency of the system after the software function configuration.

[0064] Furthermore, after the increase in the amount of historical data is completed, the screening process is determined based on the supplementary amount ratio to determine whether it meets the standards, thereby further realizing real-time monitoring of whether the system after the software function configuration meets the standards, effectively avoiding the occurrence of the screening of the supplementary data not meeting the standards, and ensuring the accuracy of the constructed functional modules. While further realizing the precise adjustment of the system's operating parameters when the system after the software function configuration does not meet the standards, the operating efficiency of the system after the software function configuration is further improved.

[0065] Furthermore, when it is determined that the construction of a functional module does not meet the standards, the reason why the construction of the functional module does not meet the standards is determined based on the data usage rate, and the reason why the constructed functional module does not meet the standards is determined in a timely and accurate manner, which further realizes real-time monitoring of whether the system after the software function configuration meets the standards, and further improves the operating efficiency of the system after the software function configuration.

[0066] Furthermore, when it is determined that the reason why the construction of the functional module does not meet the standards is the presence of invalid data, the bandwidth is increased based on the utilization rate difference. After the bandwidth is increased, the network strength is improved, thereby effectively avoiding the occurrence of incomplete data transmission caused by fluctuations in the network environment, thereby avoiding the reception of garbled data and the inability to complete the configuration of the software based on the data. While further realizing the precise adjustment of the system's operating parameters when the system does not meet the standards after the software function configuration, the operating efficiency of the system after the software function configuration is further improved.

[0067] Furthermore, when it is determined that the reason why the construction of the functional module does not meet the standards is that the extraction of keywords from the historical data does not meet the standards, the preset requirement matching degree is increased based on the matching degree difference. The increase in the preset requirement matching degree improves the accuracy of the keywords, and can make the historical data used more accurate. While further realizing the precise adjustment of the system's operating parameters when the system does not meet the standards after the software function configuration, the operating efficiency of the system after the software function configuration is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 It is a structural block diagram of the software function configuration system based on self-learning of the present invention;

[0069] Figure 2 It is a flow chart of the software function configuration method based on self-learning of the present invention;

[0070] Figure 3 A flowchart of the present invention for determining whether the construction of a functional module meets the standard and determining whether the amount of historical data used meets the standard;

[0071] Figure 4It is a flow chart of the present invention for determining the reason why the construction of a functional module does not meet the standards. DETAILED DESCRIPTION

[0072] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0073] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0074] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0075] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0076] See also Figure 1 As shown, it is a structural block diagram of the software function configuration system based on self-learning of the present invention. The structure of the embodiment of the present invention includes an upload layer, a processing layer, a construction layer, an analysis layer, a control layer and a feedback layer; wherein:

[0077] The upload layer is used to upload the historical data of the enterprise to the software function configuration system;

[0078] Extracting keywords from the historical data and processing the historical data after the keywords are extracted, including screening the historical data and normalizing the screened historical data;

[0079] The construction layer is connected to the processing layer, and is used to construct corresponding functional modules according to the processed historical data;

[0080] The construction layer performs exploratory analysis on the processed historical data to understand the distribution, characteristics and relationship between variables of the data, displays the data through visualization, discovers potential rules and trends, selects appropriate technical frameworks and tools according to the actual needs and characteristics of historical data, designs the architecture and process of the functional modules according to the actual needs and technical selection, divides the functional units and interfaces of the modules, and then writes code to realize functions such as data reading, processing, analysis and result output, such as building a financial analysis module, calculating financial indicators, generating financial statements, building a sales forecasting module, and using time series analysis and other methods to predict future sales data;

[0081] The analysis layer is connected to the construction layer to determine the functions of the functional modules and calculate the degree of fit based on the functions and actual requirements;

[0082] The analysis layer is further used to determine whether the construction of the functional module meets the standard based on the degree of fit, complete the software function configuration and issue a configuration success notification when it is determined that the construction of the functional module meets the standard, and determine whether the amount of the historical data used meets the standard based on the degree of fit when it is determined that the construction of the functional module does not meet the standard, or determine the reason why the construction of the functional module does not meet the standard based on the historical data; the analysis layer is further used to generate corresponding processing instructions based on the reason for not meeting the standard;

[0083] The control layer is connected to the analysis layer, and is used to transmit the corresponding processing instructions to the corresponding components so that the components receiving the instructions re-determine the operating parameters to complete the construction of the functional modules;

[0084] The feedback layer is connected to the control layer to analyze, try out, adjust and improve the software function configuration system after completing the software function configuration;

[0085] The feedback layer performs functional testing, performance testing, and security testing on the functional modules, and optimizes the performance of the functional modules and user experience based on the test results.

[0086] See also Figure 2 As shown, it is a flow chart of the software function configuration method based on self-learning of the present invention. The method of the embodiment of the present invention includes:

[0087] Upload the enterprise's historical data to the software function configuration system;

[0088] Extracting keywords from the historical data and processing the historical data after the keywords are extracted, including screening the historical data and normalizing the screened historical data;

[0089] Constructing the corresponding functional module according to the processed historical data;

[0090] Determine the function of the functional module and calculate the degree of fit based on the function and the actual demand;

[0091] Determining whether the construction of the functional module meets the standard based on the degree of fit, and determining whether the amount of the historical data used meets the standard based on the degree of fit when determining that the construction of the functional module does not meet the standard, or determining the reason why the construction of the functional module does not meet the standard based on the historical data; and generating a corresponding processing instruction based on the reason why the standard is not met;

[0092] Transmitting the corresponding processing instructions to the corresponding components so that the components receiving the instructions re-determine the operating parameters to complete the construction of the functional modules;

[0093] When it is determined that the construction of the functional module meets the standard, the software function configuration is completed and a configuration success notification is issued;

[0094] After completing the software function configuration, the software function configuration system is analyzed, tried, adjusted and improved.

[0095] Please continue reading Figure 2 As shown, the process of extracting keywords from the historical data in the embodiment of the present invention includes:

[0096] The process of extracting the keywords from the historical data includes:

[0097] Obtaining a corresponding demand keyword group including a plurality of demand keywords according to the content of the single actual demand;

[0098] Extracting keywords from the historical data based on the demand keyword group, and determining the demand matching degree between each historical data and each demand keyword group in turn; wherein the demand matching degree between a single historical data and the demand keyword group is the ratio of the number of matching keywords in the historical data to the total number of demand keywords, and the matching keyword is a keyword extracted from the historical data that matches the demand keyword;

[0099] Comparing the demand matching degree with a preset demand matching degree;

[0100] For a single piece of historical data, when the demand matching degree between the historical data and the demand keyword is less than a preset demand matching degree M, the historical data is screened out, wherein the preset demand matching degree M in this embodiment is 87.23%.

[0101] Please continue reading Figure 2 As shown, the process of determining the function of the functional module and calculating the degree of fit based on the function and the actual demand in the embodiment of the present invention includes:

[0102] Record the functions of the constructed functional module as actual functions;

[0103] When the actual function can solve a single actual requirement, determining that the actual function matches the actual requirement;

[0104] The ratio of the number of the actual demands having a matching relationship to the total number of the actual demands is calculated, and the obtained ratio is recorded as the matching degree.

[0105] See also Figure 3 As shown, it is a flowchart of the present invention for determining whether the construction of the functional module meets the standard and whether the amount of historical data used meets the standard. The process of determining the degree of coordination based on the function of the functional module and the actual demand in the embodiment of the present invention includes:

[0106] Comparing the degree of fit with a pre-stored preset degree of fit;

[0107] When the degree of fit is greater than or equal to the second preset degree of fit G2, it is determined that the construction of the functional module meets the standard, the software function configuration is completed, and a configuration success notification is issued, wherein the second preset degree of fit G2 in this embodiment is 98%;

[0108] When the degree of fit is less than the second preset degree of fit G2 and greater than or equal to the first preset degree of fit G1, it is determined that the construction of the functional module does not meet the standard, and based on the degree of fit, it is determined whether the amount of the historical data used meets the standard, wherein the first preset degree of fit G1 in this embodiment is 86%;

[0109] When the degree of fit is less than the first preset degree of fit G1, it is determined that the construction of the functional module does not meet the standard, and the reason why the construction of the functional module does not meet the standard is determined based on the historical data.

[0110] Please continue reading Figure 3 As shown, the process of determining whether the amount of the historical data used meets the standard based on the degree of cooperation in the embodiment of the present invention includes:

[0111] Determining the matching relationship in the degree of fit;

[0112] Counting the number of the actual functions having the matching relationship;

[0113] Calculate the ratio of the number of the actual functions that have the matching relationship to the total number of actual functions, and record the obtained ratio as the overlap ratio;

[0114] Determining whether the amount of the historical data used meets the standard based on the overlap ratio;

[0115] When the overlap ratio is greater than a preset overlap ratio P, it is determined that the amount of the historical data used does not meet the standard, and the historical data needs to be supplemented, and the amount of the historical data is corrected based on the overlap ratio, wherein the preset overlap ratio P in this embodiment is 91.2%;

[0116] When the overlap ratio is less than or equal to the preset overlap ratio P, it is determined that the quantity of the historical data used meets the standard and the construction of the functional module does not meet the standard, and the reason why the construction of the functional module does not meet the standard is determined based on the historical data.

[0117] Please continue reading Figure 3 As shown, the process of correcting the quantity of the historical data based on the overlap ratio in the embodiment of the present invention includes:

[0118] Calculate the difference between the overlap ratio and a preset overlap ratio, and record the obtained difference as the overlap ratio difference;

[0119] Increase the amount of the historical data based on the overlap ratio difference and record the increased amount of the historical data as a supplementary amount;

[0120] When the overlap ratio difference is greater than the second preset overlap ratio difference △D2, the supplement amount is 0.21 times the amount of the initial historical data, wherein the second preset overlap ratio difference △D2 in this embodiment is 6.3%;

[0121] When the overlap ratio difference is less than or equal to the second preset overlap ratio difference △D2 and greater than the first preset overlap ratio difference △D1, the supplement amount is 0.16 times the amount of the initial historical data, wherein the first preset overlap ratio difference △D1 in this embodiment is 2.9%;

[0122] When the overlap ratio difference is less than or equal to the first preset overlap ratio difference ΔD1, the supplement amount is 0.08 times the amount of initial historical data.

[0123] Please continue reading Figure 3 As shown, the process of determining whether the screening process meets the standard based on the supplementary amount after the increase in the amount of the historical data is completed in the embodiment of the present invention includes:

[0124] Determine the amount of replenishment actually used in the replenishment amount, and record the obtained amount of replenishment actually used as the actual replenishment amount;

[0125] Calculating the ratio of the replenishment amount to the actual replenishment amount, and recording the obtained ratio as the replenishment amount ratio;

[0126] Determining whether the screening process meets the standard based on the replenishment amount ratio;

[0127] comparing the replenishment amount ratio with a pre-stored preset replenishment amount ratio;

[0128] When the replenishment amount ratio is greater than a preset replenishment amount ratio S, it is determined that the screening process does not meet the standard, and a notification of the screening process not meeting the standard is issued, wherein the preset replenishment amount ratio S in this embodiment is 1.087;

[0129] When the replenishment amount ratio is less than or equal to the preset replenishment amount ratio S, it is determined that the screening process meets the standard, and the software function configuration is re-performed based on the historical data after the replenishment is completed.

[0130] See also Figure 4 As shown, it is a flow chart of the present invention for determining the reason why the construction of a functional module does not meet the standard. The process of determining the reason why the construction of the functional module does not meet the standard based on the historical data in the embodiment of the present invention includes:

[0131] Determine the usage of the historical data in the process of constructing the corresponding functional module according to the processed historical data, and record the obtained usage as the historical data usage;

[0132] Calculating the ratio of the historical data usage to the total amount of the historical data, and recording the obtained ratio as the data usage rate;

[0133] Determining the reason why the construction of the functional module does not meet the standard based on the data usage rate;

[0134] comparing the data usage rate with a pre-stored preset data usage rate;

[0135] When the data usage rate is less than or equal to the preset data usage rate E, it is determined that the reason why the construction of the functional module does not meet the standard is that invalid data exists, and the data transmission process needs to be optimized, and the bandwidth is increased based on the data usage rate. In this embodiment, the preset data usage rate E=95.2%;

[0136] When the data usage rate is greater than the preset data usage rate E, it is determined that the reason why the construction of the functional module does not meet the standard is that the extraction of keywords from the historical data does not meet the standard, and the preset requirement matching degree is increased based on the matching degree.

[0137] Please continue reading Figure 4 As shown, the process of increasing the bandwidth based on the data usage rate in the embodiment of the present invention includes:

[0138] Calculating a difference between the preset data usage rate and the data usage rate, and recording the obtained difference as a usage rate difference;

[0139] increasing bandwidth based on the utilization difference;

[0140] When the usage rate difference is greater than or equal to the second preset usage rate difference △V2, the bandwidth is increased to 1.53 times the initial bandwidth, wherein the second preset usage rate difference △V2 in this embodiment is 55.8%;

[0141] When the usage rate difference is less than the second preset usage rate difference △V2 and greater than or equal to the first preset usage rate difference △V1, the bandwidth is increased to 1.38 times the initial bandwidth, wherein the first preset usage rate difference △V1 in this embodiment is 32.7%;

[0142] When the usage rate difference is less than the first preset usage rate difference ΔV1, the bandwidth is increased to 1.21 times of the initial bandwidth.

[0143] Please continue reading Figure 4 As shown, the process of increasing the matching degree of the preset requirement based on the matching degree in the embodiment of the present invention includes:

[0144] Calculating the difference between the first preset matching degree and the matching degree, and recording the obtained difference as the matching degree difference;

[0145] Increasing the preset requirement matching degree based on the matching degree difference;

[0146] When the matching degree difference is greater than the second preset matching degree difference ΔA2, the preset requirement matching degree is increased to 1.039 times the initial preset requirement matching degree, wherein the second preset matching degree difference ΔA2 in this embodiment is 67.2%;

[0147] When the matching degree difference is less than or equal to the second preset matching degree difference △A2 and greater than the first preset matching degree difference △A1, the preset requirement matching degree is increased to 1.025 times of the initial preset requirement matching degree, wherein the first preset matching degree difference △A1 in this embodiment is 29.8%;

[0148] When the matching degree difference is less than or equal to the first preset matching degree difference ΔA1, the preset requirement matching degree is increased to 1.013 times the initial preset requirement matching degree. Example 1

[0149] Upload the company's historical data, the number of historical data is 30668, and obtain 8 demand keyword groups based on the company's single actual demand, extract keywords in the historical data based on the demand keyword group, calculate the ratio of the number of matching keywords in a single historical data 7 to the total number of demand keywords 8, obtain the demand matching degree between the single historical data and the demand keyword group, the obtained demand matching degree is 87.5%, which is greater than the preset demand matching degree of 87.23%, determine to use a single historical data to build a functional module, determine the demand matching degree between each historical data and each demand keyword group in turn, determine 25148 historical data used to build the functional module, screen the historical data, normalize the screened historical data, build the corresponding functional module according to the processed historical data, the number of functional modules is 8, after the functional module is built, determine the actual function of the functional module, and when the actual function can solve a single actual demand, determine that the actual function matches the actual demand.

[0150] The ratio of the number of actual requirements with matching relationships (19) to the total number of actual requirements (22) is calculated, and the obtained ratio is recorded as the degree of fit. After the degree of fit is calculated to be 86.4%, which is less than the second preset degree of fit (98%) and greater than or equal to the first preset degree of fit (86%), the analysis layer determines that the construction of the functional module does not meet the standard, and determines the matching relationship in the degree of fit. The number of actual functions with matching relationships is counted, and the ratio of the number of actual functions with matching relationships (23) to the total number of actual functions (24) is calculated. The overlap ratio is calculated to be 95.8%, which is greater than the preset overlap ratio of 91.2%. The analysis layer determines that the number of historical data used does not meet the standard and needs to be supplemented. The analysis layer calculates the difference between the overlap ratio of 95.8% and the preset overlap ratio of 91.2%, and the difference is 4.6%. Less than or equal to the second preset overlap ratio difference of 6.3% and greater than the first preset overlap ratio difference of 2.9%. The supplement amount is 0.16 times the number of initial historical data. The supplement amount of historical data is 4907. After the supplement amount for historical data is completed, the supplement amount actually used in the supplement amount is determined, and the obtained supplement amount actually used is recorded as the actual supplement amount. The actual supplement amount is 4736. The ratio of the supplement amount to the actual supplement amount is calculated, and the obtained ratio is recorded as the supplement amount ratio. The supplement amount ratio is 1.036, which is less than or equal to the preset supplement amount ratio of 1.087. The analysis layer determines that the screening process meets the standards, and reconfigures the software functions based on the historical data after the supplement amount is completed. After the software function configuration is completed, the degree of fit is calculated, and the constructed functional modules are determined to meet the standards based on the degree of fit. Example 2

[0151] The ratio of the number of actual demands with matching relationships (16) to the total number of actual demands (22) is calculated, and the obtained ratio is recorded as the degree of fit. After the degree of fit is calculated to be 72.7%, which is less than the first preset degree of fit (86%), the analysis layer determines that the construction of the functional module does not meet the standard. The ratio of the historical data usage (25148) to the total amount of historical data (30668) is calculated, and the obtained ratio is recorded as the data usage rate. When the data usage rate is 82%, which is less than or equal to the preset data usage rate (95.2%), the analysis layer determines that the reason why the construction of the functional module does not meet the standard is that invalid data exists, and the data transmission process needs to be optimized. The difference between the preset data usage rate (95.2%) and the data usage rate (82%) is calculated, and the obtained difference is recorded as the usage rate difference. The usage rate difference is 13.2%, which is less than the first preset usage rate difference (32.7%). The bandwidth is increased to 1.21 times the initial bandwidth. After the bandwidth is increased, the software function configuration is re-performed. After the software function configuration is completed, the degree of fit is calculated, and whether the constructed functional module meets the standard is determined based on the degree of fit.

[0152] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0153] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A software function configuration method based on self-learning, characterized in that: include: Upload the company's historical data to the software function configuration system; Extracting keywords from the historical data and processing the historical data after the keywords are extracted, including screening the historical data and normalizing the screened historical data; Constructing corresponding functional modules according to the processed historical data; Determine the functions of the functional modules and calculate the degree of fit based on the functions and actual requirements; Determine whether the construction of the functional module meets the standards based on the degree of fit, and determine whether the amount of the historical data used meets the standards based on the degree of fit when determining that the construction of the functional module does not meet the standards, or determine the reason why the construction of the functional module does not meet the standards based on the historical data; generate corresponding processing instructions based on the reason why the standards are not met; determine the usage of the historical data in the process of constructing the corresponding functional module according to the processed historical data, and record the obtained usage as the historical data usage; calculate the ratio of the historical data usage to the total amount of the historical data, and record the obtained ratio as the data usage rate; determine the reason why the construction of the functional module does not meet the standards based on the data usage rate; compare the data usage rate with the pre-stored preset data usage rate; When the data usage rate is less than or equal to the preset data usage rate, it is determined that the reason why the construction of the functional module does not meet the standard is that invalid data exists, and the data transmission process needs to be optimized, and the bandwidth is increased based on the data usage rate; When the data usage rate is greater than the preset data usage rate, determining that the reason why the construction of the functional module does not meet the standard is that the extraction of keywords from the historical data does not meet the standard, and increasing the preset requirement matching degree based on the matching degree; Transmitting the corresponding processing instructions to the corresponding components so that the components receiving the instructions re-determine the operating parameters to complete the construction of the functional modules; When it is determined that the construction of the functional module meets the standard, the software function configuration is completed and a configuration success notification is issued; After completing the software function configuration, the software function configuration system is analyzed, tried, adjusted and improved.

2. The method for configuring software functions based on self-learning according to claim 1, characterized in that: The process of extracting the keywords from the historical data includes: Obtaining a corresponding demand keyword group including a plurality of demand keywords according to the content of the single actual demand; Extracting keywords from the historical data based on the demand keyword group, and determining the demand matching degree between each historical data and each demand keyword group in turn; wherein the demand matching degree between a single historical data and the demand keyword group is the ratio of the number of matching keywords in the historical data to the total number of demand keywords, and the matching keyword is a keyword extracted from the historical data that matches the demand keyword; Comparing the demand matching degree with a preset demand matching degree; For a single piece of the historical data, when the demand matching degree between the historical data and the demand keyword is less than a preset demand matching degree, the historical data is screened out.

3. The method for configuring software functions based on self-learning according to claim 2, characterized in that: The process of determining the function of the functional module and calculating the degree of fit based on the function and the actual demand includes: Record the functions of the constructed functional module as actual functions; When the actual function can solve a single actual requirement, determining that the actual function matches the actual requirement; The ratio of the number of the actual demands having a matching relationship to the total number of the actual demands is calculated, and the obtained ratio is recorded as the matching degree.

4. The method for configuring software functions based on self-learning according to claim 3, characterized in that: The process of determining whether the construction of the functional module meets the standard based on the degree of fit includes: Comparing the degree of fit with a pre-stored preset degree of fit; When the degree of fit is greater than or equal to a second preset degree of fit, it is determined that the construction of the functional module meets the standard, the software function configuration is completed, and a configuration success notification is issued; When the degree of fit is less than the second preset degree of fit and greater than or equal to the first preset degree of fit, determining that the construction of the functional module does not meet the standard, and determining whether the amount of the historical data used meets the standard based on the degree of fit; When the degree of fit is less than the first preset degree of fit, it is determined that the construction of the functional module does not meet the standard, and the reason why the construction of the functional module does not meet the standard is determined based on the historical data.

5. The method for configuring software functions based on self-learning according to claim 4, characterized in that: The process of determining whether the amount of the historical data used meets the standard based on the degree of cooperation includes: Determining the matching relationship in the degree of fit; Counting the number of the actual functions having the matching relationship; Calculate the ratio of the number of the actual functions that have the matching relationship to the total number of actual functions, and record the obtained ratio as the overlap ratio; Determining whether the amount of the historical data used meets the standard based on the overlap ratio; When the overlap ratio is greater than the preset overlap ratio, it is determined that the amount of the historical data used does not meet the standard, the historical data needs to be supplemented, and the amount of the historical data is corrected based on the overlap ratio; When the overlap ratio is less than or equal to the preset overlap ratio, it is determined that the quantity of the historical data used meets the standard and the construction of the functional module does not meet the standard, and the reason why the construction of the functional module does not meet the standard is determined based on the historical data.

6. The method for configuring software functions based on self-learning according to claim 5, characterized in that: The process of correcting the quantity of the historical data based on the overlap ratio includes: Calculate the difference between the overlap ratio and a preset overlap ratio, and record the obtained difference as the overlap ratio difference; Based on the overlap ratio difference, the amount of the historical data is increased and the increased amount of the historical data is recorded as the supplementary amount, and the supplementary amount is proportional to the overlap ratio difference.

7. The method for configuring software functions based on self-learning according to claim 6, characterized in that: After the increase in the amount of historical data is completed, the process of determining whether the screening process meets the standard based on the supplementary amount includes: Determine the amount of replenishment actually used in the replenishment amount, and record the obtained amount of replenishment actually used as the actual replenishment amount; Calculating the ratio of the replenishment amount to the actual replenishment amount, and recording the obtained ratio as the replenishment amount ratio; Determining whether the screening process meets the standard based on the replenishment amount ratio; comparing the replenishment amount ratio with a pre-stored preset replenishment amount ratio; When the supplement amount ratio is greater than a preset supplement amount ratio, determining that the screening process does not meet the standard, and issuing a screening process non-compliant notification; When the replenishment amount ratio is less than or equal to the preset replenishment amount ratio, it is determined that the screening process meets the standard, and the software function configuration is re-performed based on the historical data after the replenishment is completed.

8. The method for configuring software functions based on self-learning according to claim 7, characterized in that: The process of increasing the bandwidth based on the data usage rate includes: Calculating a difference between the preset data usage rate and the data usage rate, and recording the obtained difference as a usage rate difference; The bandwidth is increased based on the usage rate difference, and the increase in bandwidth is proportional to the usage rate difference.

9. The method for configuring software functions based on self-learning according to claim 8, characterized in that: The process of increasing the matching degree of the preset requirement based on the matching degree includes: Calculating the difference between the first preset matching degree and the matching degree, and recording the obtained difference as the matching degree difference; The preset requirement matching degree is increased based on the matching degree difference, and the increase range of the preset requirement matching degree is proportional to the matching degree difference.

Images