Yacht industry full life cycle management system and method based on smart platform

Abstract

The present invention discloses a full life cycle management system and method for the yacht industry based on an intelligent platform, which relates to the field of platform data management. By constructing a yacht life cycle data packet in the database of the intelligent platform, a life cycle stage classification data packet is obtained. Combined with the service information characteristics of the new enterprise, the deviation value of the new enterprise service type proportion, the comprehensive service performance index and the service stage matching index are substituted into the logistic regression calculation to obtain a matching evaluation coefficient, and compared with the preset matching threshold. The probability of integrating the new enterprise data into a new data packet is obtained based on the strongly associated data packet and the matching data packet. Based on the number of enterprise cooperation times and the repetition of enterprise service content in the life cycle stage classification data packet, fuzzy logic is substituted for fuzzy reasoning to obtain the new data packet integration result, covering all stages of the yacht industry, realizing data connectivity while avoiding excessive data packet volume and reducing the probability of system freeze.

Description

Technical Field

[0001] The present invention relates to the field of platform data management, and more specifically, to a full life cycle management system and method for the yacht industry based on a smart platform. Background Art

[0002] With the rapid development of the yacht industry, the design, manufacturing, sales, operation, maintenance and scrapping and recycling of yachts are becoming increasingly complex. The development of existing technologies such as the Internet of Things, big data, artificial intelligence and blockchain has provided new possibilities for the intelligent management of the yacht industry. By building a full life cycle management system for the yacht industry based on an intelligent platform, we can effectively solve the complexity of data and improve the overall management efficiency and service level of the industry.

[0003] The existing technology has the following deficiencies:

[0004] At present, due to the relatively scattered data content, the information of upstream and downstream enterprises is relatively fragmented, and the efficiency of collaborative management is low, resulting in data sharing that is not timely and has a strong lag. In the data connection of upstream and downstream enterprise information, the data connection efficiency is low, the data connection time is long, and the corresponding enterprise needs to be searched for to obtain the corresponding data information. For the subsequent joining of new enterprises, the corresponding data matching cannot be quickly analyzed, resulting in low efficiency of data sharing for new enterprises. Therefore, a yacht industry full life cycle management system and method based on a smart platform is proposed.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a yacht industry full life cycle management system and method based on an intelligent platform, which solves the problems raised in the above-mentioned background technology by using different product inspection methods.

[0007] To achieve the above-mentioned objectives, the present invention provides the following technical solution: a yacht industry full life cycle management method based on a smart platform, comprising: S1: collecting enterprise service feature information and yacht full life cycle feature information, constructing yacht life cycle data packets corresponding to each enterprise in the smart platform database, and classifying the data packets according to yacht life cycle stages to obtain life cycle stage classification data packets;

[0008] S2: Obtain the lifecycle stage classification data package and the service information characteristics of the new enterprise, perform data analysis, and substitute the deviation value of the new enterprise service type proportion, comprehensive service performance index, and service stage matching index into the logistic regression calculation to obtain the matching evaluation coefficient;

[0009] S3: Obtain a matching evaluation coefficient and compare it with a preset matching threshold to obtain a matching result. Then, sort the matching evaluation coefficients marked as greater than or equal to the matching threshold, and use the data packet corresponding to the maximum matching evaluation coefficient as the data strongly associated data packet of the new enterprise. Then, use the data packets corresponding to the remaining matching evaluation coefficients as the data matching data packet of the new enterprise to obtain the new enterprise matching result.

[0010] S4: Obtain the new enterprise matching results, obtain the number of matching data packets and the total number of classified data packets in the life cycle stage, obtain the probability of integrating the new enterprise data into a new data packet, and compare it with the integration threshold to determine the new data packet generation result;

[0011] S5: Obtain the new data package generation result, collect the number of enterprise cooperation in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package, substitute fuzzy logic for fuzzy reasoning, and obtain the new data package integration result.

[0012] In a preferred embodiment, a request access link is sent to the enterprise information receiving terminal through the smart platform to determine the number of service contents of the enterprise;

[0013] By using text mining technology to analyze the report content provided by the enterprise, we can obtain the amount of resources available to the enterprise, the service coverage of the enterprise's affiliated enterprises, the enterprise's service efficiency and the number of historical services provided by the enterprise, and perform weighted calculations to obtain the enterprise service quality evaluation coefficient;

[0014] By querying the enterprise registration timestamp on the smart platform, you can get the length of time the enterprise has been on the smart platform.

[0015] By obtaining the start and end time of each yacht life cycle node data, subtracting the start and end time to get the time length of each life cycle, and calculating the ratio with the total life cycle length, the time distribution ratio of each stage of the life cycle is obtained;

[0016] By obtaining the number of companies in each stage of the yacht life cycle and calculating the ratio with the total number of services provided by all companies, we can obtain the service frequency of companies in each stage of the life cycle;

[0017] Construct the yacht life cycle data package corresponding to each enterprise, and classify the yachts according to their different life cycles to obtain the life cycle stage classification data package.

[0018] In a preferred embodiment, by counting the number of tasks of each service type, a distribution of the number of category tasks is formed, and the ratio of each to the total number of tasks of the new enterprise is calculated to obtain the proportion of the new enterprise service type, and then the ratio is subtracted from the proportion of the corresponding service type in the data packet to obtain the deviation value of the new enterprise service type proportion;

[0019] The comparison between the new enterprise service efficiency and quality assessment is calculated using the new enterprise service data recorded in the smart platform. The relative efficiency of the new enterprise service in different data packages is analyzed. The relative quality is then determined based on the ratio of the new enterprise's service efficiency to the efficiency of other enterprises in the corresponding data package. The relative efficiency and relative quality are weighted to obtain a comprehensive service performance index.

[0020] The service information features of new enterprises and data packets are extracted, converted into corresponding feature vectors, and substituted into the cosine similarity formula to obtain the service stage matching index.

[0021] In a preferred embodiment, the deviation value of the proportion of new enterprise service types, the comprehensive service performance index and the service stage matching index are substituted into the logistic regression formula to calculate the scheduling probability and obtain the matching evaluation coefficient.

[0022] In a preferred embodiment, if the matching evaluation coefficient is greater than or equal to the matching threshold, the current new enterprise service data is marked as matching the corresponding data packet, and a matching signal is generated;

[0023] If the matching evaluation coefficient is less than the matching threshold, the current new enterprise service data is marked as an opposing corresponding data packet and an end signal is generated;

[0024] Count the matching evaluation coefficients that are greater than or equal to the matching threshold, sort the corresponding matching evaluation coefficient values ​​from large to small, determine the maximum matching evaluation coefficient, and classify the new enterprise service data as new data into the life cycle stage classification data package corresponding to the maximum matching evaluation coefficient, and mark it as a new enterprise service data strongly associated data package;

[0025] The maximum value of the matching evaluation coefficient is screened out, and the data packets corresponding to the remaining matching evaluation coefficients are used as the data matching data packets of the new enterprise. The strongly associated data packets and the matching data packets are integrated to obtain the new enterprise matching results.

[0026] In a preferred embodiment, the new enterprise matching result includes a strongly associated data packet and a matching data packet; the strongly associated data packet is filtered out and the matching data packet is retained;

[0027] Count the number of matching data packets and calculate the ratio with the total number of classified data packets in the life cycle stage to obtain the probability of integrating new enterprise data into new data packets;

[0028] The probability of integrating new enterprise data into a new data packet is compared with the integration threshold. If the probability of integrating new enterprise data into a new data packet is greater than or equal to the integration threshold, a new data packet is generated as the data packet of the new enterprise. Otherwise, no new data packet is generated and the new enterprise service data matching is completed.

[0029] In a preferred embodiment, by recording and counting the cooperation behaviors between different enterprises in the same life cycle stage, the number of enterprise cooperation in the classified data package of the life cycle stage is obtained;

[0030] By comparing the service contents of different enterprises in the life cycle stage classification data package, the existence of the same quantity is detected. The number of enterprises with the same service content is added to the total number of enterprises in the data package to obtain the duplication of enterprise service content in the life cycle stage classification data package.

[0031] In a preferred embodiment, the number of enterprise collaborations in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package are defined as input variables, and they are divided into different fuzzy sets respectively;

[0032] The integration result of the new data package is defined as the output variable and divided into fuzzy sets;

[0033] Formulate fuzzy rules to describe the impact of the number of enterprise collaborations in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package on the integration results of the new data package;

[0034] Perform fuzzy reasoning based on fuzzy rules to determine the integration results of new data packets.

[0035] The yacht industry full life cycle management system based on the smart platform includes a platform construction module, a data processing module, a matching analysis module, and a generation and integration module;

[0036] The platform construction module is used to collect enterprise service feature information and yacht life cycle feature information, build each yacht life cycle data package corresponding to each enterprise in the smart platform database, classify the data package according to the yacht life cycle stage, obtain the life cycle stage classification data package, and send it to the data processing module;

[0037] The data processing module is used to obtain lifecycle stage classification data packages and service information characteristics of new enterprises, perform data analysis, and substitute the deviation value of the new enterprise service type proportion, comprehensive service performance index, and service stage matching index into the logistic regression calculation to obtain the matching evaluation coefficient, which is sent to the matching analysis module;

[0038] The matching analysis module is used to obtain the matching evaluation coefficient and compare it with the preset matching threshold to obtain the matching result. The matching evaluation coefficients marked as greater than or equal to the matching threshold are sorted, and the data packet corresponding to the maximum matching evaluation coefficient is used as the data strongly associated data packet of the new enterprise. The data packets corresponding to the remaining matching evaluation coefficients are then used as the data matching data packet of the new enterprise to obtain the new enterprise matching result and send it to the generation and integration module;

[0039] The generation and integration module is used to obtain the new enterprise matching results, the number of matching data packages and the total number of life cycle stage classification data packages, the probability of integrating new enterprise data into new data packages, and compare it with the integration threshold to determine the new data package generation results, and collect the number of enterprise cooperation times in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package, substitute fuzzy logic for fuzzy reasoning, and obtain the new data package integration results.

[0040] Technical effects and advantages of the present invention:

[0041] 1. The present invention collects enterprise service feature information and yacht life cycle feature information to construct a yacht life cycle data package in the database of the smart platform, classifies the data package according to the yacht life cycle stage, and obtains a life cycle stage classification data package. Combined with the service information characteristics of new enterprises, the deviation value of the proportion of new enterprise service types, the comprehensive service performance index, and the service stage matching index are substituted into the logistic regression calculation to obtain a matching evaluation coefficient, which is compared with the preset matching threshold to obtain a strongly associated data package and a matching data package. Accurate matching and efficient resource allocation are achieved, and corresponding data matching is quickly analyzed, covering all stages of the yacht industry from design to recycling, achieving seamless connection and data penetration.

[0042] 2. The present invention obtains the matching results of new enterprises, obtains the number of matching data packets and the total number of data packets classified in the life cycle stage, obtains the probability of integrating new enterprise data into a new data packet, and compares it with the integration threshold to determine the new data packet generation result, and collects the number of enterprise cooperation times of the data packets classified in the life cycle stage and the repetition of enterprise service content in the data packets classified in the life cycle stage, formulates a set of fuzzy rules for fuzzy reasoning, determines the new data packet integration result, avoids excessive data volume of the data packet, reduces the probability of system freeze, and improves user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of the method for managing the entire life cycle of the yacht industry based on a smart platform of the present invention.

[0044] Figure 2 This is a module diagram of the yacht industry full life cycle management system based on the smart platform of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] The present disclosure prioritizes building yacht lifecycle data packages corresponding to each enterprise in the database of the smart platform based on enterprise characteristic information and yacht lifecycle characteristics, and classifies the data packages by yacht lifecycle stage, so that different yacht lifecycle data packages have different corresponding upstream and downstream enterprises in the same lifecycle stage;

[0047] When a new enterprise joins the smart platform, the present invention prioritizes classifying data packets according to the lifecycle stage, combining the service information characteristics of the new enterprise, and analyzing the matching results of the new enterprise's service data based on the deviation value of the new enterprise's service type proportion, the comprehensive service performance index, and the service stage matching index;

[0048] Next, based on the number of matching data packets and the total number of data packets classified by lifecycle stage, the probability of integrating new enterprise data into a new data packet is obtained and compared with the integration threshold to analyze the possibility of integrating the new enterprise data into a new data packet. By formulating a set of fuzzy rules for fuzzy reasoning, the integration result of the new data packet is determined. In this way, this intelligent platform can cover all stages of the yacht industry from design to recycling, achieving seamless connection and data integration, and supporting collaborative management and data sharing among upstream and downstream enterprises in the industry chain. At the same time, as new enterprises join, the splitting and integration of data packets also have dynamic changes, allowing the data of new enterprises to complete data sharing and data integration more quickly.

[0049] Example 1

[0050] See also Figure 1 , a full life cycle management method for the yacht industry based on a smart platform. The specific operation process is as follows:

[0051] S1: Collect enterprise service feature information and yacht life cycle feature information, build yacht life cycle data packets corresponding to each enterprise in the database of the smart platform, classify the data packets according to the yacht life cycle stage, and obtain life cycle stage classification data packets;

[0052] Among them, enterprise service characteristic information includes the number of services provided by the enterprise, the enterprise service quality assessment coefficient, and the length of time the enterprise has been a member of the smart platform; yacht life cycle characteristic information includes the time distribution ratio of each stage of the life cycle and the frequency of enterprise services in each stage of the life cycle;

[0053] The logic for obtaining the number of service contents of an enterprise is that after the enterprise joins, the smart platform sends a request access link to the enterprise's information receiving terminal to determine the number of service contents of the enterprise;

[0054] Typically, the enterprise's information receiving terminal can be an enterprise service webpage or the contact email address of the enterprise's key technical personnel. After the enterprise confirms receipt of the request to access the link, the smart platform queries and records the enterprise's service content quantity. The method for collecting the enterprise's service content quantity is not limited and will not be elaborated here.

[0055] The logic for obtaining the enterprise service quality evaluation coefficient is to use text mining technology to analyze the report content provided by the enterprise and obtain the amount of resources available to the enterprise, the service coverage of the enterprise's affiliated enterprises, the enterprise's service efficiency and the number of historical services provided by the enterprise, and then perform weighted calculation to obtain the enterprise service quality evaluation coefficient;

[0056] Among them, regarding the service coverage of enterprise-affiliated enterprises, a service breadth index formula is established to express the service coverage of enterprise-affiliated enterprises in combination with the historical frequency of cooperation and service scope. The specific formula is as follows:

[0057]

[0058] Where, Service coverage for enterprise affiliates, is the cooperation frequency of the i-th affiliated enterprise, is the service area of ​​the affiliated enterprise, i is the i-th affiliated enterprise, is the total number of collaborations between enterprises;

[0059] It should be noted that the technology for analyzing and mining the report content provided by enterprises is not limited to text mining technology. It can also include network graph analysis, the task record module of the smart platform, and database query. Specifically, in the platform database, the number of completed service records can be directly queried by enterprise name, etc., which will not be elaborated here.

[0060] The logic for obtaining the length of time an enterprise has been on the smart platform is to query the enterprise registration timestamp on the smart platform to obtain the length of time the enterprise has been on the smart platform.

[0061] The logic for obtaining the time distribution ratio of each stage in the life cycle is to obtain the start and end time of each yacht life cycle node data, subtract the start and end time to obtain the time length of each life cycle, and calculate the ratio with the total life cycle length to obtain the time distribution ratio of each stage in the life cycle;

[0062] It should be noted that this embodiment uses one type of yacht as an example. In reality, the smart platform includes multiple types of yachts. The categories of yachts are not limited, but are derived based on the types of yachts provided by the platform enterprises. Detailed description is omitted here.

[0063] Specifically, the number and setting of the yacht life cycle can be divided into multiple stages, for example, the first stage is the drawing and design stage, the second stage is the manufacturing and production stage, the third stage is the digital delivery stage, the fourth stage is the operation monitoring stage, the fifth stage is the maintenance stage, the sixth stage is the recycling stage, etc. The number setting of the yacht life cycle will not be repeated here;

[0064] It is understandable that different types of yachts may also contain different life cycle stages. Therefore, yachts are integrated according to each life stage to construct a data package for each yacht life cycle.

[0065] The division of upstream and downstream enterprises can be based on specific scenarios or experimental data. Generally, upstream enterprises are defined as the manufacturing and production stage, and downstream enterprises are defined as the delivery, maintenance, and recycling stages. The specific division of upstream and downstream enterprises is not limited.

[0066] The logic for obtaining the service frequency of enterprises at each stage of the life cycle is to obtain the number of enterprises at each stage of the yacht life cycle and calculate the ratio with the total number of services of all enterprises to obtain the service frequency of enterprises at each stage of the life cycle;

[0067] The number of service contents, service quality evaluation coefficient, duration of the enterprise joining the smart platform, time distribution ratio of each life cycle stage, and service frequency of each life cycle stage are combined to construct a yacht life cycle data package corresponding to each enterprise. The yachts are then classified according to their different life cycles to obtain a life cycle stage classification data package.

[0068] Specifically, this data package can be used to obtain the corresponding yacht lifecycle data of each enterprise and the relevant service information of each enterprise at different lifecycle stages. Specifically, the content of each yacht lifecycle data package includes but is not limited to the start time, end time, service duration of each stage, the service capabilities, service efficiency and service quality of each enterprise at that stage, and also includes each enterprise's historical service data, etc.

[0069] Among them, the life cycle stage classification data package refers to the existence of different upstream and downstream enterprises in the same life cycle stage;

[0070] Then, by classifying data packages by life cycle stages, upstream and downstream companies can obtain companies they need to cooperate with or connect with based on the yacht life cycle, thus forming an intelligent platform for data integration and sharing.

[0071] S2: Obtain the lifecycle stage classification data package and the service information characteristics of the new enterprise, perform data analysis, and substitute the deviation value of the new enterprise service type proportion, comprehensive service performance index, and service stage matching index into the logistic regression calculation to obtain the matching evaluation coefficient;

[0072] Data analysis refers to the systematic processing, organization, and interpretation of service information characteristics and lifecycle stage classification data packages of new enterprises to explore potential patterns and characteristics in the data and provide a basis for subsequent logistic regression calculations and matching evaluations. Specific analysis techniques include but are not limited to data cleaning and preprocessing, differential analysis, etc. These specific analysis techniques are existing technologies and will not be elaborated here.

[0073] The logic for obtaining the deviation value of the proportion of new enterprise service types is to count the number of tasks of each service type to form the distribution of the number of category tasks, and then calculate the ratio of each to the total number of tasks of the new enterprise to obtain the proportion of new enterprise service types, and then subtract the ratio from the proportion of the corresponding service type in the data packet to obtain the deviation value of the proportion of new enterprise service types. ; Wherein, i is the i-th comparison data packet;

[0074] The service types of the specific new enterprise are related to the various stages of the yacht life cycle, that is, the multiple stages set corresponding to the number of yacht life cycles in the above content;

[0075] The logic for obtaining the comprehensive service performance index is to calculate the comparison value of the new enterprise service efficiency and quality evaluation through the new enterprise service data recorded in the smart platform, analyze the relative efficiency of the new enterprise service efficiency in different data packages, and then determine the relative quality based on the efficiency ratio of the new enterprise's service efficiency relative to the efficiency of other enterprises in the corresponding data package. The relative efficiency and relative quality are weighted to calculate the comprehensive service performance index. ;

[0076] The logic for obtaining the service stage matching index is to extract the service information features of the new enterprise and data packet, convert them into corresponding feature vectors, and substitute them into the cosine similarity formula to calculate the service stage matching index. ;

[0077] Substitute the deviation value of the proportion of new enterprise service types, the comprehensive service performance index, and the service stage matching index into the logistic regression formula to calculate the scheduling probability. The specific formula is expressed as follows:

[0078] ;

[0079] Where, is the result of logistic regression calculation, that is, the matching evaluation coefficient, e is the natural base, and y is the linear combination term of the logistic regression model. Specifically, y can be set as:

[0080] ;

[0081] Where, is the bias term, 、 as well as They are the regression coefficients of the deviation value of the proportion of new enterprise service types, the comprehensive service performance index, and the service stage matching index;

[0082] S3: Obtain a matching evaluation coefficient and compare it with a preset matching threshold to obtain a matching result. Then, sort the matching evaluation coefficients marked as greater than or equal to the matching threshold, and use the data packet corresponding to the maximum matching evaluation coefficient as the data strongly associated data packet of the new enterprise. Then, use the data packets corresponding to the remaining matching evaluation coefficients as the data matching data packet of the new enterprise to obtain the new enterprise matching result.

[0083] The logic for obtaining the matching threshold is to collect a set of historical new enterprise matching data package results, then divide the data set into training and test sets, set evaluation indicators and clustering algorithms, and in each round of cross-validation, train the model on the training set and evaluate the model performance on the test set. The matching threshold is then adjusted based on the performance of the validation set. Therefore, the matching threshold is continuously updated.

[0084] In the present invention, clustering algorithm is a type of unsupervised learning algorithm used to divide matching data in a dataset into labeled groups or clusters. A common example is K-means clustering, which divides matching data in a dataset into K clusters so that the distance between each matching data and the center point (center of mass) of the cluster to which it belongs is minimized. Finally, the similarity of the matching data is measured by Euclidean distance, thereby setting a matching threshold.

[0085] After obtaining the matching evaluation coefficient, the matching evaluation coefficient is compared and analyzed with the continuously iterated matching threshold;

[0086] If the matching evaluation coefficient is greater than or equal to the matching threshold, the current new enterprise service data is marked as matching the corresponding data packet, and a matching signal is generated;

[0087] If the matching evaluation coefficient is less than the matching threshold, the current new enterprise service data is marked as an opposing corresponding data packet and an end signal is generated;

[0088] Count the matching evaluation coefficients that are greater than or equal to the matching threshold, sort the corresponding matching evaluation coefficient values ​​from large to small, determine the maximum matching evaluation coefficient, and classify the new enterprise service data as new data into the life cycle stage classification data package corresponding to the maximum matching evaluation coefficient, and mark it as a new enterprise service data strongly associated data package;

[0089] It should be noted that the maximum matching evaluation coefficient represents the lifecycle stage classification data package that best matches the new enterprise service data. Specifically, the service characteristics of this lifecycle stage classification data package are closest to those of the new enterprise. Therefore, the new enterprise service data and the corresponding lifecycle stage classification data package are strongly correlated.

[0090] Strong correlation refers to a high degree of consistency between the service data of the new enterprise and the characteristics of the lifecycle stage classification data package. Specifically, it is manifested as follows: a high match in service type (yacht lifecycle services), service efficiency, and service quality. In other words, the new enterprise's service data plays a significant role in this data package, forming a good data synergy effect.

[0091] Eliminate the maximum value of the matching evaluation coefficient, use the data packets corresponding to the remaining matching evaluation coefficients as the data matching data packets of the new enterprise, integrate the strongly associated data packets and the matching data packets, and obtain the new enterprise matching results;

[0092] The present invention collects enterprise service feature information and yacht life cycle feature information, constructs a yacht life cycle data packet in the database of the smart platform, classifies the data packet according to the yacht life cycle stage, and obtains a life cycle stage classification data packet. Combined with the service information characteristics of the new enterprise, according to the deviation value of the new enterprise service type proportion, the comprehensive service performance index and the service stage matching index, the data are substituted into the logistic regression calculation to obtain the matching evaluation coefficient, and compared with the preset matching threshold to obtain a strongly associated data packet and a matching data packet, accurately match and efficiently allocate resources, and quickly analyze the corresponding data matching, covering all stages of the yacht industry from design to recycling, and realizing seamless connection and data penetration.

[0093] Example 2

[0094] In the first embodiment of the present invention, an example is given of collecting enterprise service feature information and yacht life cycle feature information, constructing a yacht life cycle data packet in the database of the smart platform, classifying the data packet according to the yacht life cycle stage, obtaining a life cycle stage classification data packet, combining the service information characteristics of the new enterprise, substituting the new enterprise service type proportion deviation value, the comprehensive service performance index and the service stage matching index into the logistic regression calculation to obtain a matching evaluation coefficient, and comparing it with the preset matching threshold to obtain a strongly associated data packet and an operation strategy for the matching data packet; however, in the first embodiment, the operation method of the new enterprise service data is determined only based on the matching result of the new enterprise. However, as time changes, this will cause the data of each data packet of the smart platform to be relatively large, resulting in slow system operation, reduced data call efficiency, and reduced user experience; in response to the above problems, the second embodiment of the present invention is further refined;

[0095] S4: Obtain the new enterprise matching results, obtain the number of matching data packets and the total number of classified data packets in the life cycle stage, obtain the probability of integrating the new enterprise data into a new data packet, and compare it with the integration threshold to determine the new data packet generation result;

[0096] Specifically, the new enterprise matching results include strongly associated data packets and matching data packets;

[0097] Filter out strongly correlated data packets and retain matching data packets;

[0098] It should be noted that the strongly associated data packets express that the service data of the new enterprise is highly correlated with the corresponding data packets, and therefore are not recorded as integrated data packets;

[0099] Count the number of matching data packets and calculate the ratio with the total number of classified data packets in the life cycle stage to obtain the probability of integrating new enterprise data into new data packets;

[0100] The probability of integrating the new enterprise data into a new data package is compared with the integration threshold. If the probability of integrating the new enterprise data into a new data package is greater than or equal to the integration threshold, a new data package is generated as the data package of the new enterprise. Otherwise, no new data package is generated, and the new enterprise service data matching is completed.

[0101] It should be noted that the integration threshold is obtained through the integration results of historical new enterprise data and the new enterprise matching results, which will not be elaborated here;

[0102] S5: Obtain the new data package generation result, collect the number of enterprise collaborations in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package, substitute them into fuzzy logic for fuzzy reasoning, and obtain the new data package integration result;

[0103] Among them, the life cycle stage classification data package in the number of enterprise cooperation in the life cycle stage classification data package is the life cycle stage classification data package corresponding to the above-mentioned matching data package; the enterprise data contained in the data package includes the number of service contents of the enterprise, the enterprise service quality evaluation coefficient, the length of time the enterprise has joined the smart platform, the time distribution ratio of each stage of the life cycle, and the frequency of enterprise services in each stage of the life cycle. Specifically, the relevant enterprise data has been described in Example 1 and will not be repeated here;

[0104] The logic for obtaining the number of enterprise collaborations in the data package classified by life cycle stages is to record and count the collaboration behaviors between different enterprises in the same life cycle stage, and then obtain the number of enterprise collaborations in the data package classified by life cycle stages;

[0105] The logic for obtaining the duplication of enterprise service content within the life cycle stage classification data package is to compare the service content of different enterprises within the life cycle stage classification data package, detect the existence of the same quantity, and then add the number of enterprises with the same service content to the total number of enterprises in the data package to obtain the duplication of enterprise service content within the life cycle stage classification data package;

[0106] For example, "High", "Low", and "Medium" refer to the number of enterprise collaborations in the life cycle stage classification data package, and "Repetition", "Unique", and "Moderate" refer to the duplication of enterprise service content in the life cycle stage classification data package;

[0107] Formulate a set of fuzzy rules to describe the impact of different input variables on the output variable. The definition of rules can be based on professional knowledge or obtained through data analysis and experiments. For example:

[0108] The number of enterprise collaborations in the life cycle stage classification data package is marked as X, the duplication of enterprise service content in the life cycle stage classification data package is marked as U, and the new data package integration result is marked as C_Public;

[0109] Then we can define:

[0110] Rule 1: IF (X is High) AND (Uis Repetition) THEN (C_Public isHigh)

[0111] Rule 2: IF (U is Low) AND (U is Unique) THEN (C_Public is Low) ...

[0112] Perform fuzzy reasoning based on fuzzy rules to determine the integration result of new data packets;

[0113] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although this embodiment takes three fuzzy sets as an example, in fact, the number of enterprise collaborations in the life cycle stage classification data package and the repetition of enterprise service content in the life cycle stage classification data package can be divided into more than three sets to facilitate better precise adjustment according to different life cycle stage classification data packages.

[0114] Furthermore, for judging the number of enterprise collaborations in the lifecycle stage classification data package and the degree of duplication of enterprise service content in the lifecycle stage classification data package, thresholds can be set according to actual conditions for judgment. For example, when the number of enterprise collaborations in the lifecycle stage classification data package exceeds 80%, it is marked as "High", and when the degree of duplication of enterprise service content in the lifecycle stage classification data package exceeds 75%, it is marked as "Repetition", etc., which will not be elaborated here.

[0115] The present invention obtains the new enterprise matching results, obtains the number of matching data packets and the total number of data packets classified in the life cycle stage, obtains the probability of integrating new enterprise data into a new data packet, and compares it with the integration threshold to determine the new data packet generation result, and collects the number of enterprise cooperation times of the data packets classified in the life cycle stage and the repetition of enterprise service content in the data packets classified in the life cycle stage, formulates a set of fuzzy rules for fuzzy reasoning, determines the new data packet integration result, avoids excessive data volume of the data packet, reduces the probability of system freeze, and improves user experience.

[0116] Example 3

[0117] See also Figure 2 , a yacht industry full life cycle management system based on a smart platform, including building platform modules, data processing modules, matching analysis modules, and generation and integration modules;

[0118] The platform construction module is used to collect enterprise service feature information and yacht life cycle feature information, build each yacht life cycle data package corresponding to each enterprise in the smart platform database, classify the data package according to the yacht life cycle stage, obtain the life cycle stage classification data package, and send it to the data processing module;

[0119] The data processing module is used to obtain lifecycle stage classification data packages and service information characteristics of new enterprises, perform data analysis, and substitute the deviation value of the new enterprise service type proportion, comprehensive service performance index, and service stage matching index into the logistic regression calculation to obtain the matching evaluation coefficient, which is sent to the matching analysis module;

[0120] The matching analysis module is used to obtain the matching evaluation coefficient and compare it with the preset matching threshold to obtain the matching result. The matching evaluation coefficients marked as greater than or equal to the matching threshold are sorted, and the data packet corresponding to the maximum matching evaluation coefficient is used as the data strongly associated data packet of the new enterprise. The data packets corresponding to the remaining matching evaluation coefficients are then used as the data matching data packet of the new enterprise to obtain the new enterprise matching result and send it to the generation and integration module;

[0121] The generation and integration module is used to obtain the new enterprise matching results, the number of matching data packages and the total number of life cycle stage classification data packages, the probability of integrating new enterprise data into new data packages, and compare it with the integration threshold to determine the new data package generation results, and collect the number of enterprise cooperation times in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package, substitute fuzzy logic for fuzzy reasoning, and obtain the new data package integration results.

[0122] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0123] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0124] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0125] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0126] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0129] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0130] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0131] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A full life cycle management method for the yacht industry based on a smart platform, characterized by: S1 includes: collecting enterprise service feature information and yacht life cycle feature information, building yacht life cycle data packets corresponding to each enterprise in the database of the smart platform, classifying the data packets according to the yacht life cycle stage, and obtaining life cycle stage classification data packets; S2: Obtain the lifecycle stage classification data package and the service information characteristics of the new enterprise, perform data analysis, and substitute the deviation value of the new enterprise service type proportion, comprehensive service performance index, and service stage matching index into the logistic regression calculation to obtain the matching evaluation coefficient; S3: Obtain a matching evaluation coefficient and compare it with a preset matching threshold to obtain a matching result. Then, sort the matching evaluation coefficients marked as greater than or equal to the matching threshold, and use the data packet corresponding to the maximum matching evaluation coefficient as the data strongly associated data packet of the new enterprise. Then, use the data packets corresponding to the remaining matching evaluation coefficients as the data matching data packet of the new enterprise to obtain the new enterprise matching result. S4: Obtain the new enterprise matching results, obtain the number of matching data packets and the total number of classified data packets in the life cycle stage, obtain the probability of integrating the new enterprise data into a new data packet, and compare it with the integration threshold to determine the new data packet generation result; S5: Obtain the new data package generation result, collect the number of enterprise cooperation in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package, substitute fuzzy logic for fuzzy reasoning, and obtain the new data package integration result.

2. The yacht industry full life cycle management method based on the smart platform according to claim 1 is characterized by: Send a request access link to the enterprise receiving information terminal through the smart platform to determine the number of service contents of the enterprise; By using text mining technology to analyze the report content provided by the enterprise, we can obtain the amount of resources available to the enterprise, the service coverage of the enterprise's affiliated enterprises, the enterprise's service efficiency and the number of historical services provided by the enterprise, and perform weighted calculations to obtain the enterprise service quality evaluation coefficient; By querying the enterprise registration timestamp on the smart platform, you can get the length of time the enterprise has been on the smart platform. By obtaining the start and end time of each yacht life cycle node data, subtracting the start and end time to get the time length of each life cycle, and calculating the ratio with the total life cycle length, the time distribution ratio of each stage of the life cycle is obtained; By obtaining the total number of services provided by all enterprises in each stage of the yacht life cycle and calculating the ratio with the total number of services provided by all enterprises, the service frequency of enterprises in each stage of the life cycle is obtained; Construct the yacht life cycle data package corresponding to each enterprise, and classify the yachts according to their different life cycles to obtain the life cycle stage classification data package.

3. The yacht industry full life cycle management method based on the smart platform according to claim 2 is characterized by: By counting the number of tasks of each service type, we can form a distribution of the number of category tasks, and then calculate the ratio of each to the total number of tasks of the new enterprise to obtain the proportion of the new enterprise service type. Then, we subtract the ratio from the proportion of the corresponding service type in the data packet to obtain the deviation value of the new enterprise service type proportion. The comparison between the new enterprise service efficiency and quality assessment is calculated using the new enterprise service data recorded in the smart platform. The relative efficiency of the new enterprise service in different data packages is analyzed. The relative quality is then determined based on the ratio of the new enterprise's service efficiency to the efficiency of other enterprises in the corresponding data package. The relative efficiency and relative quality are weighted to obtain a comprehensive service performance index. The service information features of new enterprises and data packets are extracted, converted into corresponding feature vectors, and substituted into the cosine similarity formula to obtain the service stage matching index.

4. The yacht industry full life cycle management method based on a smart platform according to claim 3 is characterized by: Substitute the deviation value of the proportion of new enterprise service types, the comprehensive service performance index and the service stage matching index into the logistic regression formula to calculate the scheduling probability and obtain the matching evaluation coefficient.

5. The yacht industry full life cycle management method based on the smart platform according to claim 4 is characterized by: If the matching evaluation coefficient is greater than or equal to the matching threshold, the current new enterprise service data is marked as matching the corresponding data packet, and a matching signal is generated; If the matching evaluation coefficient is less than the matching threshold, the current new enterprise service data is marked as an opposing corresponding data packet and an end signal is generated; Count the matching evaluation coefficients that are greater than or equal to the matching threshold, sort the corresponding matching evaluation coefficient values ​​from large to small, determine the maximum matching evaluation coefficient, and classify the new enterprise service data as new data into the life cycle stage classification data package corresponding to the maximum matching evaluation coefficient, and mark it as a new enterprise service data strongly associated data package; The maximum value of the matching evaluation coefficient is screened out, and the data packets corresponding to the remaining matching evaluation coefficients are used as the data matching data packets of the new enterprise. The strongly associated data packets and the matching data packets are integrated to obtain the new enterprise matching results.

6. The yacht industry full life cycle management method based on the smart platform according to claim 5 is characterized by: The new enterprise matching results include strongly associated data packets and matching data packets; the strongly associated data packets are filtered out and the matching data packets are retained; Count the number of matching data packets and calculate the ratio with the total number of classified data packets in the life cycle stage to obtain the probability of integrating new enterprise data into new data packets; The probability of integrating new enterprise data into a new data packet is compared with the integration threshold. If the probability of integrating new enterprise data into a new data packet is greater than or equal to the integration threshold, a new data packet is generated as the data packet of the new enterprise. Otherwise, no new data packet is generated and the new enterprise service data matching is completed.

7. The yacht industry full life cycle management method based on the smart platform according to claim 6 is characterized by: By recording and counting the cooperation behaviors between different enterprises in the same life cycle stage, the number of enterprise cooperation in the classified data package of the life cycle stage is obtained; By comparing the service contents of different enterprises in the life cycle stage classification data package, the existence of the same quantity is detected. The duplication of enterprise service content in the life cycle stage classification data package is obtained based on the number of enterprises with the same service content and the total number of enterprises in the data package.

8. The yacht industry full life cycle management method based on a smart platform according to claim 7 is characterized by: The number of enterprise collaborations in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package are defined as input variables, and they are divided into different fuzzy sets respectively; The integration result of the new data package is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the impact of the number of enterprise collaborations in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package on the integration results of the new data package; Perform fuzzy reasoning based on fuzzy rules to determine the integration results of new data packets.

9. A yacht industry full life cycle management system based on a smart platform, used to implement the yacht industry full life cycle management method based on a smart platform as described in any one of claims 1 to 8, characterized in that: Including building platform module, data processing module, matching analysis module and generation integration module; The platform construction module is used to collect enterprise service feature information and yacht life cycle feature information, build each yacht life cycle data package corresponding to each enterprise in the smart platform database, classify the data package according to the yacht life cycle stage, obtain the life cycle stage classification data package, and send it to the data processing module; The data processing module is used to obtain lifecycle stage classification data packages and service information characteristics of new enterprises, perform data analysis, and substitute the deviation value of the new enterprise service type proportion, comprehensive service performance index, and service stage matching index into the logistic regression calculation to obtain the matching evaluation coefficient, which is sent to the matching analysis module; The matching analysis module is used to obtain the matching evaluation coefficient and compare it with the preset matching threshold to obtain the matching result. The matching evaluation coefficients marked as greater than or equal to the matching threshold are sorted, and the data packet corresponding to the maximum matching evaluation coefficient is used as the data strongly associated data packet of the new enterprise. The data packets corresponding to the remaining matching evaluation coefficients are then used as the data matching data packet of the new enterprise to obtain the new enterprise matching result and send it to the generation and integration module; The generation and integration module is used to obtain the new enterprise matching results, the number of matching data packages and the total number of life cycle stage classification data packages, the probability of integrating new enterprise data into new data packages, and compare it with the integration threshold to determine the new data package generation results, and collect the number of enterprise cooperation times in the life cycle stage classification data package and the duplication of enterprise service content in the life cycle stage classification data package, substitute fuzzy logic for fuzzy reasoning, and obtain the new data package integration results.

Images