Enterprise service data intelligent processing method and system

Abstract

The invention discloses an enterprise service data intelligent processing method and system, and the method comprises the steps: obtaining an initial data set corresponding to a data collection instruction if an enterprise user side detects the data collection instruction, carrying out the data compression of the initial data set, so as to update the initial data set, and transmitting the updated initial data set to a first server; the first server performs data decompression on the initial data set to update the initial data set, and sends the initial data set to a second server; the second server receives the initial data set and performs data cleaning on the initial data set to obtain a cleaned data set; and the second server performs data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set. According to the embodiment of the invention, the initial data set comprising a large amount of data can be quickly and automatically obtained from the enterprise user side, and multi-dimensional data processing application is carried out after data cleaning is carried out.

Description

Technical Field

[0001] The present invention relates to the technical field of network communication and data processing, and particularly to an intelligent processing method and system for enterprise service data. Background Art

[0002] Currently, the system application functions of enterprise service institutions mainly lie in daily business handling and operation management, lacking the function of intelligent analysis to find problems, and the system functions vary greatly due to different requirements in their respective business fields, resulting in inconsistent data sources. Specifically, that is, the current systems of enterprise service institutions are in a manual operation mode for some analysis data required by enterprise users, resulting in low data acquisition efficiency and a low amount of acquired data. Summary of the Invention

[0003] Embodiments of the present invention provide an intelligent processing method and system for enterprise service data, aiming to solve the problem that in the prior art, the systems of enterprise service institutions are in a manual operation mode for some analysis data required by enterprise users, resulting in low data acquisition efficiency and a low amount of acquired data.

[0004] In a first aspect, embodiments of the present invention provide an intelligent processing method for enterprise service data, which is applied to an intelligent processing system for enterprise service data. The intelligent processing system for enterprise service data includes an enterprise user terminal, a first server, and a second server. The enterprise user terminal is communicatively connected to the first server, and the first server is communicatively connected to the second server. The intelligent processing method for enterprise service data includes:

[0005] If the enterprise user terminal detects a data collection instruction, it obtains an initial data set corresponding to the data collection instruction, compresses the initial data set to update the initial data set, and sends the updated initial data set to the first server. Wherein, a data collection script is pre-deployed in the enterprise user terminal, and the data collection script is executed when the enterprise user terminal detects the data collection instruction to collect the initial data set;

[0006] The first server decompresses the initial data set to update the initial data set, and sends the initial data set to the second server;

[0007] The second server receives the initial data set, and performs data cleaning on the initial data set to obtain a cleaned data set;

[0008] The second server performs data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set.

[0009] Second aspect, an embodiment of the present invention further provides an intelligent enterprise service data processing system, which includes an enterprise user terminal, a first server, and a second server. The enterprise user terminal is communicatively connected to the first server, and the first server is communicatively connected to the second server;

[0010] The enterprise user terminal is configured to, if a data collection instruction is detected, obtain an initial data set corresponding to the data collection instruction, and perform data compression on the initial data set to update the initial data set and send it to the first server; wherein, a data collection script is pre-deployed in the enterprise user terminal, and the data collection script is executed when the enterprise user terminal detects the data collection instruction to collect the initial data set;

[0011] The first server is configured to decompress the initial data set to update the initial data set, and send the initial data set to the second server;

[0012] The second server is configured to receive the initial data set, and perform data cleaning on the initial data set to obtain a cleaned data set;

[0013] The second server is further configured to perform data processing on the cleaned data set based on a preset data processing policy to obtain a data processing result corresponding to the cleaned data set.

[0014] Third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor. A computer program is stored on the memory, and when the processor executes the computer program, the method described in the first aspect above is implemented.

[0015] Fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium. The computer storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the method described in the first aspect above can be implemented.

[0016] The embodiments of the present invention provide an enterprise service data intelligent processing method and system. The method includes: if an enterprise user terminal detects a data collection instruction, it obtains an initial data set corresponding to the data collection instruction, compresses the initial data set to update the initial data set, and sends it to a first server; the first server decompresses the initial data set to update the initial data set and sends the initial data set to a second server; the second server receives the initial data set and performs data cleaning on the initial data set to obtain a cleaned data set; the second server performs data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set. The embodiments of the present invention can quickly and automatically obtain an initial data set including a large amount of data from the enterprise user terminal, perform data cleaning, and then perform multi-dimensional data processing applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic diagram of the application scenario of the enterprise service data intelligent processing method provided by the embodiments of the present invention;

[0019] Figure 2 It is a schematic flowchart of the enterprise service data intelligent processing method provided by the embodiments of the present invention;

[0020] Figure 3 It is a schematic block diagram of the enterprise service data intelligent processing device provided by the embodiments of the present invention;

[0021] Figure 4 It is a schematic block diagram of the computer device provided by the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0023] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0024] It should also be understood that the terminology used in this specification of the present invention is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in this specification of the present invention and the appended claims, unless the context clearly dictates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0025] It should be further understood that the term "and / or" used in this specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0026] Please refer simultaneously to Figure 1 and Figure 2 where Figure 1 is a schematic diagram of the scenario of the enterprise service data intelligent processing method according to an embodiment of the present invention, Figure 2 is a schematic flowchart of the enterprise service data intelligent processing method provided by an embodiment of the present invention. As Figure 1 shown, the enterprise service data intelligent processing method provided by an embodiment of the present invention is applied to an enterprise service data intelligent processing system. The enterprise service data intelligent processing includes an enterprise user terminal 10, a first server 20, and a second server 30; the enterprise user terminal 10 is communicatively connected to the first server 20, and the first server 20 is communicatively connected to the second server 30.

[0027] As Figure 2 shown, the method includes the following steps S110 - S140.

[0028] S110. If the enterprise user terminal detects a data collection instruction, obtain an initial data set corresponding to the data collection instruction, and compress the initial data set to update the initial data set and send it to the first server.

[0029] Wherein, a data collection script is pre - deployed in the enterprise user terminal, and the data collection script is executed when the enterprise user terminal detects the data collection instruction to collect the initial data set.

[0030] In this embodiment, the enterprise client can communicate with the enterprise server. When the enterprise client detects a data collection instruction, it can obtain the initial data set corresponding to the data collection instruction from the enterprise server or the local of the enterprise client, and directly send the initial data set from the enterprise client or indirectly send it to the first server through the enterprise server. It should be noted that the data transmission scenario of the initial data set directly sent from the enterprise client or indirectly sent to the first server through the enterprise server in this application can specifically be a data transmission scenario of continuous transmission of a large amount of data for a long time. The data collection instruction includes at least information such as a data collection time interval and a data collection target object. By parsing the data collection instruction including information such as a data collection time interval and a data collection target object, the initial data set corresponding to the data collection time interval and the data collection target object can be obtained from the local database of the enterprise client first, and then the initial data set is compressed to update the initial data set and sent to the first server. Through the above data compression process, the data volume of the initial data set can be effectively reduced, so that the initial data set does not occupy a large amount of bandwidth during the data transmission process between the enterprise client and the first server, and the data transmission efficiency is improved.

[0031] Specifically, the enterprise client can perform corresponding processing on the initial data set through a data preprocessing strategy. The data preprocessing strategy includes a data classification sub-strategy and a data compression sub-strategy. After the initial data set is divided into multiple data groups through the data classification sub-strategy, each data group is subjected to data compression processing based on the data compression sub-strategy to obtain multiple compressed data groups, and the multiple compressed data groups together form the updated initial data set.

[0032] More specifically, a data collection script can be pre-deployed in the enterprise client. Once the enterprise client detects a data collection instruction, the data collection script can be executed to obtain the initial data set corresponding to the data collection instruction from the enterprise server or the local of the enterprise client. The database in which the initial data set is stored in the enterprise server or the local of the enterprise client can be the production database of the enterprise server or the enterprise client, or the mirror database of the enterprise server or the enterprise client.

[0033] In one embodiment, step S110 includes:

[0034] If it is determined that the data collection instruction corresponds to a timed data collection instruction, obtain the data collection effective time and the timed data collection script corresponding to the timed data collection instruction, and collect the initial data set based on the timed data collection script;

[0035] If it is determined that the data collection instruction corresponds to an immediate data collection instruction, obtain the immediate data collection script corresponding to the immediate data collection instruction, and collect the initial data set based on the immediate data collection script;

[0036] If it is determined that the data collection instruction corresponds to an abnormal data collection instruction, obtain the abnormal data collection script corresponding to the abnormal data collection instruction, and collect the initial data set based on the abnormal data collection script.

[0037] In this embodiment, the data collection instruction is one of the following three types: a timed data collection instruction, an immediate data collection instruction, and an abnormal data collection instruction. In the timed data collection scenario, first obtain the data collection effective time and the timed data collection script corresponding to the timed data collection instruction, and based on the timed data collection script, execute and collect the initial data set at the time point corresponding to the data collection effective time. In the immediate data collection instruction scenario, once the immediate data collection instruction is obtained, the corresponding timed data collection script can be immediately executed to collect the initial data set. In the abnormal data collection scenario, similar to the immediate data collection instruction scenario, in the immediate data collection instruction scenario, normal data collection can be restricted, so in the abnormal data collection scenario, only abnormal data collection can be restricted, that is, immediately execute the corresponding abnormal data collection script to collect the initial data set. However, regardless of which scenario the initial data set is collected in, it can be subjected to data compression processing and then uploaded to the first server for subsequent data processing.

[0038] S120. The first server decompresses the initial data set to update the initial data set, and sends the initial data set to the second server.

[0039] In this embodiment, the first server can be regarded as a server cluster for data transfer caching and data decompression in a private network. When the first server receives the initial data set, before the initial data set is transmitted to the second server, it can also be decompressed to update the initial data set (the initial data set obtained at this time is the same as the initial data set collected by the enterprise user terminal according to the data collection instruction), and then the initial data set in the decompressed state is transmitted to the second server, and the second server then performs subsequent processing on it.

[0040] In one embodiment, before step S120, the method further includes:

[0041] The first server performs a security check on the enterprise user terminal identity information corresponding to the initial data set based on a preset firewall policy, and releases the initial data set when it is determined that the enterprise user terminal identity information passes the security check;

[0042] If the first server determines that the initial data set is an encrypted data set or a signed data set, it acquires the encryption model type for data encryption or data signing of the initial data set, and decrypts the initial data set or verifies the digital signature based on the decryption model corresponding to the encryption model type, so as to update the initial data set.

[0043] In this embodiment, in order to ensure that the first server securely receives the initial data set, the identity information of the enterprise client corresponding to the initial data set may first be securely verified based on a preset firewall policy. Only when the identity information of the enterprise client is in the enterprise client white list corresponding to the firewall policy can it be determined that the identity information of the enterprise client passes the security verification, and the firewall of the first server allows the initial data set to pass. Moreover, a load balancing component may further be deployed in the firewall, so that the load balancing component distributes the initial data set to one of the first target servers in the server cluster corresponding to the first server by using load balancing technology. Then, the first target server in the first server decompresses the initial data set to obtain the decompressed initial data set. It can be seen that based on the above method, the data transmission security is improved.

[0044] In the above process, when the first server determines that the initial data set is an encrypted data set or a signed data set, it may first acquire the encryption model type for data encryption or data signing of the initial data set (such as a combination of a message digest algorithm and an asymmetric encryption algorithm), then acquire the decryption model corresponding to the encryption model type (such as also a combination of a message digest algorithm and an asymmetric encryption algorithm), and finally decrypt the initial data set or verify the digital signature based on the decryption model to update the initial data set.

[0045] S130. The second server receives the initial data set and performs data cleaning on the initial data set to obtain a cleaned data set.

[0046] In this embodiment, after the second server receives the initial data set sent by the first server, it may specifically perform data cleaning on the initial data set in combination with the data cleaning policy deployed locally to obtain a cleaned data set, and the obtained cleaned data set may be further processed by the data processing sub-application local to the second server.

[0047] In one embodiment, performing data cleaning on the initial data set to obtain a cleaned data set includes:

[0048] Performing integrity verification on the initial data set based on the integrity verification sub-policy in the data cleaning policy to obtain an integrity verification result;

[0049] If it is determined that the integrity verification result is a passed verification result, the initial data set is subjected to missing value deletion or completion based on the missing value processing sub-strategy in the data cleaning strategy to obtain a first processed data set;

[0050] Duplicate values in the first processed data set are deleted based on the duplicate value processing sub-strategy in the data cleaning strategy to obtain a second processed data set;

[0051] Outliers in the second processed data set are deleted or corrected based on the outlier processing sub-strategy in the data cleaning strategy to obtain a third processed data set;

[0052] The third processed data set is subjected to data standardization conversion based on the data conversion processing sub-strategy in the data cleaning strategy to obtain the cleaned data set.

[0053] In this embodiment, when the second server performs data cleaning on the initial data set, after sequentially performing integrity verification, missing value deletion or completion, duplicate value deletion, constant value deletion or correction, and data standardization conversion on the initial data set, the cleaned data set can be obtained.

[0054] Of course, when performing integrity verification on the initial data set based on the integrity verification sub-strategy in the data cleaning strategy to obtain an integrity verification result, specifically, it can be determined whether each piece of initial data in the initial data set includes all specified core fields, and whether the data generation time point and data belonging object corresponding to each piece of initial data match the data collection time interval and data collection target object in the data collection instruction. For example, if each piece of initial data in the initial data set includes all specified core fields, and the data generation time point and data belonging object corresponding to each piece of initial data match the data collection time interval and data collection target object in the data collection instruction, it indicates that the integrity verification result of the initial data set is a passed verification result; if at least one piece of initial data in the initial data set does not include all specified core fields, or there is at least one piece of initial data whose data generation time point and data belonging object do not match the data collection time interval and data collection target object in the data collection instruction, it indicates that the integrity verification result of the initial data set is a failed verification result.

[0055] Duplicate values in the first processed data set are deleted based on the duplicate value processing sub-strategy in the data cleaning strategy, specifically, data deduplication is performed to avoid the impact of duplicate data on subsequent data processing processes.

[0056] Based on the outlier handling sub-strategy in the data cleaning strategy, outliers in the second processed data set are deleted or corrected. Specifically, outlier detection is first performed, and then outliers are deleted or corrected. For example, when the outlier handling sub-strategy performs outlier detection on the second processed data set, a statistics-based method can be specifically adopted. Specifically, by calculating the mean and standard deviation of the corresponding values of each field in the second processed data set, a reasonable interval is determined to identify whether the corresponding values of each field in the second processed data set are outliers. For example, for data with a normal distribution, data exceeding the mean ± 3 times the standard deviation is usually considered an outlier.

[0057] Based on the data transformation processing sub-strategy in the data cleaning strategy, data standardization transformation is performed on the third processed data set. Specifically, normalization processing can be performed on the third processed data set to obtain the cleaned data set.

[0058] It can be seen that by sequentially performing integrity verification, missing value deletion or completion, duplicate value deletion, constant value deletion or correction, and data standardization transformation on the initial data set, the data cleaning process can be quickly completed. Moreover, after completing the data cleaning of the initial data set, the data authenticity of the initial data set uploaded by the enterprise user side can be ensured.

[0059] In one embodiment, as the first embodiment of the missing value handling sub-strategy, the missing value handling sub-strategy in the data cleaning strategy is used to delete or complete missing values in the initial data set to obtain the first processed data set, including:

[0060] If it is determined that there are missing values in the initial data in the initial data set and the initial data in the initial data set is randomly distributed, then based on the missing value handling sub-strategy, the initial data corresponding to the missing values is deleted to update the initial data set and obtain the first processed data set.

[0061] In this embodiment, if it is determined that there are missing values in the initial data in the initial data set and it is further determined that the ratio of the total number of initial data with missing values to the total number of initial data in the initial data set is lower than the first preset ratio threshold (such as 0.1%, 0.5%, 1%, etc.), it means that the proportion of the initial data with missing values in the initial data set is relatively small. Under the condition that the initial data in the initial data set satisfies the random distribution, the initial data corresponding to the missing values can be deleted based on the missing value handling sub-strategy to update the initial data set and obtain the first processed data set. It can be seen that the missing value processing of the initial data set can be quickly realized based on the above method.

[0062] In one embodiment, as the second embodiment of the missing value processing sub-strategy, deleting or filling in missing values from the initial data set based on the missing value processing sub-strategy in the data cleaning strategy to obtain a first processed data set includes:

[0063] If it is determined that there are missing values in the initial data in the initial data set and the initial data in the initial data set is not randomly distributed, then determine the predicted value corresponding to the initial data with missing values based on the K-nearest neighbor model corresponding to the missing value processing sub-strategy, and fill in the initial data with corresponding missing values with the predicted value to update the initial data set and obtain the first processed data set.

[0064] In this embodiment, if it is determined that there are missing values in the initial data in the initial data set and it is further determined that the initial data in the initial data set is not randomly distributed, the predicted value corresponding to the initial data with missing values can be determined based on the K-nearest neighbor model corresponding to the missing value processing sub-strategy, that is, predict and fill based on the values of other initial data that are most similar to the initial data where the missing value is located. To update the initial data set and obtain the first processed data set. It can be seen that the missing value processing of the initial data set can also be quickly realized based on the above method.

[0065] S140. The second server processes the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set.

[0066] In this embodiment, the second server can be regarded as a server cluster for data processing applications in a private network. When the second server receives the cleaned data set, it can specifically process the cleaned data set based on the locally deployed data processing strategy to obtain a data processing result. The obtained data processing result can be visually displayed locally or sent to a specified receiving terminal for visual viewing.

[0067] In one embodiment, as the first embodiment of the data processing strategy, processing the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set includes:

[0068] If it is determined that the data processing strategy is a data analysis and statistics strategy, then obtain the core data analysis and statistics indicators and the data analysis target time period corresponding to the data analysis and statistics strategy;

[0069] Screen a target screened data set from the cleaned data set based on the core data analysis and statistics indicators and the data analysis target time period, and use it as the data processing result.

[0070] In this embodiment, if it is determined that the data processing strategy is a data analysis and statistics strategy, it means that a target screening dataset can be obtained by screening from the cleaned dataset based on the core indicators of data analysis and statistics corresponding to the data analysis and statistics strategy and the data analysis target time period, and the obtained target screening dataset can be directly used as the data processing result. Of course, if the data display in the form of the target screening dataset as the source data is not intuitive enough, the data processing result can be processed based on a preset visual data processing strategy to update the data processing result, and the obtained data processing result can be displayed in visual display methods such as the visual data processing strategy data table and curve graph.

[0071] In one embodiment, as the second embodiment of the data processing strategy, the data processing of the cleaned dataset based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned dataset includes:

[0072] If it is determined that the data processing strategy is a data trend prediction strategy, obtain a prediction model corresponding to the data trend prediction strategy;

[0073] Input the cleaned dataset into the prediction model to obtain a prediction result, which is used as the data processing result.

[0074] In this embodiment, if it is determined that the data processing strategy is a data trend prediction strategy, the cleaned dataset can also be first converted into a time series, and then the time series corresponding to the cleaned dataset is input into the prediction model corresponding to the data trend prediction strategy, so as to obtain a prediction result, which is used as the data processing result. This prediction result can be visually displayed and processed locally by the second server or sent to a specified receiving terminal for visual viewing.

[0075] After the data processing result is obtained in the second server, it can be regarded as a predicted processing workload of the target enterprise corresponding to the enterprise user terminal in a specified future time period (for example, taking the generation time of the data collection instruction as the current initial time point, the specified future time period can be the next complete natural day, the next complete natural week, the next complete natural month, etc. compared with the current initial time point). The service interface of other servers can be called to send the data processing result to the service interface. Based on the relationship function between the preset processing workload and the number of human resources in the service interface (such as W = p * n, where W is the processing workload, p is the per capita processing volume and is regarded as a constant, and n is the number of human resources), the number of human resources corresponding to the data processing result (which can be understood as the number of processing personnel) can be determined. After the service interface determines the number of human resources corresponding to the data processing result, it can be sent to the second server for viewing. It should be noted that the obtained number of human resources is a reference index that can be intuitively viewed and referenced by users processed by the second server by calling the service interface of other servers, rather than a decisive index specifically used for participating in transaction decisions.

[0076] In one embodiment, as the third embodiment of the data processing strategy, the data processing of the cleaned data set based on the preset data processing strategy to obtain a data processing result corresponding to the cleaned data set includes:

[0077] If it is determined that the data processing strategy is a data matching strategy, obtain the local target storage data set corresponding to the cleaned data set and stored locally, and perform data matching comparison between the cleaned data set and the local target storage data set, and obtain the data matching comparison result as the data processing result.

[0078] In this embodiment, if it is determined that the data processing strategy is a data matching strategy, a local target storage data set for the same enterprise object as the cleaned data set can also be obtained locally on the second server. Then, each piece of data in the cleaned data set is compared with the data in the local target storage data set one by one for data matching. When it is determined that the data similarity between the two data sets (for example, if the total number of data in the cleaned data set is N1, and the total number of data in the local target storage data set is N2, and N3 pieces of data in the cleaned data set match successfully with the data in the local target storage data set, then the similarity between the two data sets is N3 / N2, where N1, N2, and N3 are all positive integers) is greater than or equal to the preset data similarity threshold, it indicates that the data matching comparison result of the cleaned data set is a successful match result and is used as the data processing result; when it is determined that the data similarity between the two data sets is less than the data similarity threshold, it indicates that the data matching comparison result of the cleaned data set is a failed match result and is used as the data processing result. Moreover, when the match fails, the second server can also generate an abnormal data prompt message corresponding to the cleaned data set and send the abnormal data prompt message to the enterprise user terminal. Through the above matching process of the data sets, the validity of the data in the cleaned data set can be ensured.

[0079] It can be seen that the embodiments implementing this method can quickly automatically obtain an initial data set including a large amount of data from the enterprise user terminal, perform data cleaning, and then perform multi-dimensional data processing applications.

[0080] Figure 3 It is a schematic block diagram of an enterprise service data intelligent processing system provided by an embodiment of the present invention. As Figure 3 shown, corresponding to the above enterprise service data intelligent processing method, the present invention also provides an enterprise service data intelligent processing system 100. The enterprise service data intelligent processing system includes an enterprise user terminal 10, a first server 20, and a second server 30; the enterprise user terminal 10 is communicatively connected to the first server 20, and the first server 20 is communicatively connected to the second server 30.

[0081] The enterprise user terminal 10 is configured to, if a data collection instruction is detected, obtain an initial data set corresponding to the data collection instruction, compress the initial data set to update the initial data set, and send it to the first server.

[0082] Among them, a data collection script is pre-deployed in the enterprise user terminal, and the data collection script is executed when the enterprise user terminal detects the data collection instruction to collect the initial data set.

[0083] In this embodiment, the enterprise client can communicate with the enterprise server. When the enterprise client detects a data collection instruction, it can obtain the initial data set corresponding to the data collection instruction from the enterprise server or the local of the enterprise client, and directly send the initial data set from the enterprise client or indirectly send it to the first server through the enterprise server. It should be noted that the data transmission scenario of the initial data set directly sent from the enterprise client or indirectly sent to the first server through the enterprise server in this application can specifically be a data transmission scenario where a large amount of data is continuously transmitted for a long time. The data collection instruction at least includes information such as a data collection time interval and a data collection target object. By parsing the data collection instruction including information such as a data collection time interval and a data collection target object, the initial data set corresponding to the data collection time interval and the data collection target object can be obtained from the local database of the enterprise client first, and then the initial data set is compressed to update the initial data set and sent to the first server. Through the above data compression process, the data volume of the initial data set can be effectively reduced, so that the initial data set does not occupy a large amount of bandwidth during the data transmission process between the enterprise client and the first server, and the data transmission efficiency is improved.

[0084] Specifically, the enterprise client can perform corresponding processing on the initial data set through a data preprocessing strategy. The data preprocessing strategy includes a data classification sub-strategy and a data compression sub-strategy. After the initial data set is divided into multiple data groups through the data classification sub-strategy, each data group is compressed based on the data compression sub-strategy to obtain multiple compressed data groups, and the multiple compressed data groups together form the updated initial data set.

[0085] More specifically, a data collection script can be pre-deployed in the enterprise client. Once the enterprise client detects a data collection instruction, the data collection script can be executed to obtain the initial data set corresponding to the data collection instruction from the enterprise server or the local of the enterprise client. The database in which the initial data set is stored in the enterprise server or the local of the enterprise client can be the production library of the enterprise server or the enterprise client, or the mirror library of the enterprise server or the enterprise client.

[0086] In one embodiment, the enterprise client 10 is further configured to:

[0087] If it is determined that the data collection instruction corresponds to a timed data collection instruction, obtain the data collection effective time and the timed data collection script corresponding to the timed data collection instruction, and collect the initial data set based on the timed data collection script;

[0088] If it is determined that the data collection instruction corresponds to an immediate data collection instruction, obtain the immediate data collection script corresponding to the immediate data collection instruction, and collect the initial data set based on the immediate data collection script;

[0089] If it is determined that the data collection instruction corresponds to an abnormal data collection instruction, obtain the abnormal data collection script corresponding to the abnormal data collection instruction, and collect the initial data set based on the abnormal data collection script.

[0090] In this embodiment, the data collection instruction is one of the following three types: a timed data collection instruction, an immediate data collection instruction, and an abnormal data collection instruction. In the timed data collection scenario, first obtain the data collection effective time and the timed data collection script corresponding to the timed data collection instruction, and based on the timed data collection script, execute and collect the initial data set at the time point corresponding to the data collection effective time. In the immediate data collection instruction scenario, once the immediate data collection instruction is obtained, the corresponding timed data collection script can be immediately executed to collect the initial data set. In the abnormal data collection scenario, similar to the immediate data collection instruction scenario, in the immediate data collection instruction scenario, normal data collection can be limited, so in the abnormal data collection scenario, only abnormal data collection can be limited, that is, immediately execute the corresponding abnormal data collection script to collect the initial data set. However, regardless of which scenario the initial data set is collected in, it can be compressed and then uploaded to the first server for subsequent data processing.

[0091] The first server 20 is used to decompress the initial data set to update the initial data set and send the initial data set to the second server.

[0092] In this embodiment, the first server can be regarded as a server cluster for data transfer caching and data decompression in a private network. When the first server receives the initial data set, before the initial data set is transmitted to the second server, it can also be decompressed to update the initial data set (at this time, the obtained initial data set is the same as the initial data set collected by the enterprise user terminal according to the data collection instruction), and then the initial data set in the decompressed state is transmitted to the second server, and the second server then performs subsequent processing on it.

[0093] Specifically, in the data preprocessing strategy, there are a data classification sub-strategy and a data compression sub-strategy. Through the data classification sub-strategy, the initial data set can be divided into multiple data groups, and then each data group is subjected to data compression processing based on the data compression sub-strategy to obtain multiple compressed data groups, which form the updated initial data set.

[0094] In one embodiment, before the first server decompresses the initial data set to update the initial data set and sends the initial data set to the second server, the following steps are further included:

[0095] The first server performs a security check on the enterprise client identity information corresponding to the initial data set based on a preset firewall policy, and releases the initial data set when it is determined that the enterprise client identity information passes the security check;

[0096] If the first server determines that the initial data set is an encrypted data set or a signed data set, it obtains the encryption model type for data encryption or data signing of the initial data set, and decrypts the initial data set or verifies the digital signature based on the decryption model corresponding to the encryption model type to update the initial data set.

[0097] In this embodiment, in order to ensure that the first server securely receives the initial data set, the security check on the enterprise client identity information corresponding to the initial data set can be first performed based on a preset firewall policy. Only when the enterprise client identity information is in the enterprise user white list corresponding to the firewall policy, it can be determined that the enterprise client identity information passes the security check, and the firewall of the first server releases the initial data set. Moreover, a load balancing component can be further deployed in the firewall, so that the load balancing component distributes the initial data set to one of the first target servers in the server cluster corresponding to the first server by using load balancing technology. Then, the first target server in the first server decompresses the initial data set to obtain the decompressed initial data set. It can be seen that based on the above method, the data transmission security is improved.

[0098] In the above process, when the first server determines that the initial data set is an encrypted data set or a signed data set, it can first obtain the encryption model type for data encryption or data signing of the initial data set (such as a combination of a message digest algorithm and an asymmetric encryption algorithm), then obtain the decryption model corresponding to the encryption model type (such as also a combination of a message digest algorithm and an asymmetric encryption algorithm), and finally decrypt the initial data set or verify the digital signature based on the decryption model to update the initial data set. The above functions support national cryptographic algorithms.

[0099] The first server 20 is configured to receive the initial data set and perform data cleaning on the initial data set to obtain a cleaned data set.

[0100] In this embodiment, after receiving the initial data set sent by the first server, the second server may specifically perform data cleaning on the initial data set in combination with the data cleaning policy deployed locally to obtain a cleaned data set, and the obtained cleaned data set may be further processed by the data processing sub-application local to the second server.

[0101] In one embodiment, the process of performing data cleaning on the initial data set to obtain a cleaned data set includes:

[0102] Performing integrity verification on the initial data set based on the integrity verification sub-policy in the data cleaning policy to obtain an integrity verification result;

[0103] If it is determined that the integrity verification result is a passed verification result, then perform missing value deletion or filling on the initial data set based on the missing value processing sub-policy in the data cleaning policy to obtain a first processed data set;

[0104] Performing duplicate value deletion on the first processed data set based on the duplicate value processing sub-policy in the data cleaning policy to obtain a second processed data set;

[0105] Performing outlier deletion or correction on the second processed data set based on the outlier processing sub-policy in the data cleaning policy to obtain a third processed data set;

[0106] Performing data standardization conversion on the third processed data set based on the data conversion processing sub-policy in the data cleaning policy to obtain the cleaned data set.

[0107] In this embodiment, when the second server performs data cleaning on the initial data set, after sequentially performing integrity verification, missing value deletion or filling, duplicate value deletion, constant value deletion or correction, and data standardization conversion on the initial data set, the cleaned data set can be obtained.

[0108] Of course, when performing integrity verification on the initial dataset based on the integrity verification sub-strategy in the data cleaning strategy to obtain the integrity verification result, specifically, it can be determined whether each piece of initial data in the initial dataset includes all specified core fields, and whether the data generation time point and the data ownership object corresponding to each piece of initial data match the data collection time interval and the data collection target object in the data collection instruction. For example, if each piece of initial data in the initial dataset includes all specified core fields, and the data generation time point and the data ownership object corresponding to each piece of initial data match the data collection time interval and the data collection target object in the data collection instruction, it indicates that the integrity verification result of the initial dataset is a verification passed result; if at least one piece of initial data in the initial dataset does not include all specified core fields, or there is at least one piece of initial data whose corresponding data generation time point and data ownership object do not match the data collection time interval and the data collection target object in the data collection instruction, it indicates that the integrity verification result of the initial dataset is a verification failed result.

[0109] Based on the duplicate value processing sub-strategy in the data cleaning strategy, duplicate values are deleted from the first processed dataset. Specifically, data deduplication is performed to avoid the impact of duplicate data on subsequent data processing.

[0110] Based on the outlier processing sub-strategy in the data cleaning strategy, outliers are deleted or corrected from the second processed dataset. Specifically, outlier detection is first performed, and then outliers are deleted or corrected. For example, when the outlier processing sub-strategy performs outlier detection on the second processed dataset, a statistical-based method can be specifically used. Specifically, by calculating the mean and standard deviation of the values corresponding to each field in the second processed dataset, a reasonable interval is determined to identify whether the values corresponding to each field in the second processed dataset are outliers. For example, for data with a normal distribution, data exceeding the mean ± 3 times the standard deviation is usually considered an outlier.

[0111] Based on the data transformation processing sub-strategy in the data cleaning strategy, data standardization transformation is performed on the third processed dataset. Specifically, normalization processing can be performed on the third processed dataset to obtain the cleaned dataset.

[0112] It can be seen that by sequentially performing integrity verification, missing value deletion or completion, duplicate value deletion, constant value deletion or correction, and data standardization transformation on the initial dataset, the data cleaning process can be quickly completed. Moreover, after completing the data cleaning of the initial dataset, the data authenticity of the initial dataset uploaded by the enterprise user side can be ensured.

[0113] In one embodiment, as the first embodiment of the missing value processing sub-strategy, deleting or filling in missing values from the initial data set based on the missing value processing sub-strategy in the data cleaning strategy to obtain a first processed data set includes:

[0114] If it is determined that there are missing values in the initial data in the initial data set and the initial data in the initial data set is randomly distributed, then based on the missing value processing sub-strategy, the initial data with corresponding missing values is deleted to update the initial data set and obtain the first processed data set.

[0115] In this embodiment, if it is determined that there are missing values in the initial data in the initial data set and it is further determined that the ratio of the total number of initial data with missing values to the total number of initial data in the initial data set is lower than a first preset ratio threshold (such as 0.1%, 0.5%, 1%, etc.), it means that the proportion of the initial data with missing values in the initial data set is relatively small. Under the condition that the initial data in the initial data set satisfies the random distribution, the initial data with corresponding missing values can be deleted based on the missing value processing sub-strategy to update the initial data set and obtain the first processed data set. It can be seen that the missing value processing of the initial data set can be quickly realized based on the above method.

[0116] In one embodiment, as the second embodiment of the missing value processing sub-strategy, deleting or filling in missing values from the initial data set based on the missing value processing sub-strategy in the data cleaning strategy to obtain a first processed data set includes:

[0117] If it is determined that there are missing values in the initial data in the initial data set and the initial data in the initial data set is not randomly distributed, then based on the K-nearest neighbor model corresponding to the missing value processing sub-strategy, the predicted value corresponding to the initial data with missing values is determined, and the initial data with corresponding missing values is filled in with the predicted value to update the initial data set and obtain the first processed data set.

[0118] In this embodiment, if it is determined that there are missing values in the initial data in the initial data set and it is further determined that the initial data in the initial data set is not randomly distributed, the predicted value corresponding to the initial data with missing values can be determined based on the K-nearest neighbor model corresponding to the missing value processing sub-strategy, that is, predicted and filled according to the values of other initial data most similar to the initial data where the missing value is located. To update the initial data set and obtain the first processed data set. It can be seen that the missing value processing of the initial data set can also be quickly realized based on the above method.

[0119] The second server 30 is further configured to perform data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set.

[0120] In this embodiment, the second server can be regarded as a server cluster for data processing applications in a private network. When the second server receives the cleaned data set, it can specifically perform data processing on the cleaned data set in combination with the locally deployed data processing strategy to obtain a data processing result. The obtained data processing result can be visually displayed locally or sent to a specified receiving terminal for visual viewing.

[0121] In one embodiment, as a first embodiment of the data processing strategy, performing data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set includes:

[0122] If it is determined that the data processing strategy is a data analysis and statistics strategy, obtain the core data analysis and statistics indicators and the data analysis target time period corresponding to the data analysis and statistics strategy;

[0123] Screen a target screened data set from the cleaned data set based on the core data analysis and statistics indicators and the data analysis target time period, and use it as the data processing result.

[0124] In this embodiment, if it is determined that the data processing strategy is a data analysis and statistics strategy, it means that a target screened data set can be screened from the cleaned data set based on the core data analysis and statistics indicators and the data analysis target time period corresponding to the data analysis and statistics strategy, and the obtained target screened data set can be directly used as the data processing result. Of course, if the data display in the form of the target screened data set as the source data is not intuitive enough, the data processing result can be processed based on a preset visual data processing strategy to update the data processing result, and the obtained data processing result can be displayed in visual display methods such as the visual data processing strategy data table and curve graph.

[0125] In one embodiment, as a second embodiment of the data processing strategy, performing data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set includes:

[0126] If it is determined that the data processing strategy is a data trend prediction strategy, obtain the prediction model corresponding to the data trend prediction strategy;

[0127] Input the cleaned data set into the prediction model to obtain a prediction result, and use it as the data processing result.

[0128] In this embodiment, if it is determined that the data processing strategy is a data trend prediction strategy, the cleaned data set can also be first converted into a time series, and then the time series corresponding to the cleaned data set is input into the prediction model corresponding to the data trend prediction strategy, so as to obtain a prediction result, which is used as the data processing result. This prediction result can be visually displayed and processed locally by the second server, or sent to a specified receiving terminal for visual inspection.

[0129] Among them, after the data processing result is obtained in the second server, it can be regarded as a predicted processing workload of the target enterprise corresponding to the enterprise user terminal in a specified future time period (for example, taking the generation time of the data collection instruction as the current initial time point, the specified future time period can be the next complete natural day, the next complete natural week, the next complete natural month, etc. after the current initial time point). The service interface of other servers can be called to send the data processing result to the service interface. Based on the relationship function between the preset processing workload and the number of human resources in the service interface (such as W = p * n, where W is the processing workload, p is the per capita processing volume and is regarded as a constant, and n is the number of human resources), the number of human resources corresponding to the data processing result (which can be understood as the number of processing personnel) is determined. After the service interface determines the number of human resources corresponding to the data processing result, it can be sent to the second server for viewing. It should be noted that the obtained number of human resources is a reference index that can be intuitively viewed and referenced by users processed by the second server by calling the service interface of other servers, rather than a decisive index specifically used for participating in transaction decision-making.

[0130] In one embodiment, as the third embodiment of the data processing strategy, the data processing of the cleaned data set based on the preset data processing strategy to obtain a data processing result corresponding to the cleaned data set includes:

[0131] If it is determined that the data processing strategy is a data matching strategy, the local target storage data set corresponding to the cleaned data set and stored locally is obtained, and the cleaned data set is compared with the local target storage data set for data matching to obtain a data matching comparison result as the data processing result.

[0132] In this embodiment, if it is determined that the data processing policy is a data matching policy, a local target storage data set for the same enterprise object as the cleaned data set can also be obtained locally on the second server. Then, each piece of data in the cleaned data set is compared with the data in the local target storage data set one by one for data matching. When it is determined that the data similarity between the two data sets (for example, if the total number of data in the cleaned data set is N1, and the total number of data in the local target storage data set is N2, and N3 pieces of data in the cleaned data set match successfully with the data in the local target storage data set, then the similarity between the two data sets is N3 / N2, where N1, N2, and N3 are all positive integers) is greater than or equal to the preset data similarity threshold, it indicates that the data matching comparison result of the cleaned data set is a successful matching result and is used as the data processing result; when it is determined that the data similarity between the two data sets is less than the data similarity threshold, it indicates that the data matching comparison result of the cleaned data set is a failed matching result and is used as the data processing result. Moreover, when the matching fails, the second server can also generate an abnormal data prompt message corresponding to the cleaned data set and send this abnormal data prompt message to the enterprise user terminal. Through the above matching process of the data sets, the validity of the data in the cleaned data set can be ensured.

[0133] It can be seen that implementing the embodiment of this system can quickly automatically obtain an initial data set including a large amount of data from the enterprise user terminal, perform data cleaning, and then perform multi-dimensional data processing applications.

[0134] The above enterprise service data intelligent processing system can be implemented in the form of a computer program, and this computer program can run on a computer device as shown in Figure 4 shown.

[0135] Please refer to Figure 4 , Figure 4 which is a schematic block diagram of a computer device provided by an embodiment of the present invention. This computer device integrates any enterprise service data intelligent processing system provided by the embodiment of the present invention.

[0136] Refer to Figure 4 . This computer device 400 includes a processor 402, a memory, and a network interface 405 connected through a system bus 401. Among them, the memory may include a storage medium 403 and an internal memory 404.

[0137] The storage medium 403 can store an operating system 4031 and a computer program 4032. This computer program 4032 includes program instructions. When these program instructions are executed, the processor 402 can be made to execute the above enterprise service data intelligent processing method.

[0138] The processor 402 is used to provide computing and control capabilities to support the operation of the entire computer device.

[0139] The internal memory 404 provides an environment for the operation of the computer program 4032 in the storage medium 403. When the computer program 4032 is executed by the processor 402, the processor 402 can be caused to execute the above-mentioned intelligent processing method for enterprise service data.

[0140] The network interface 405 is used for network communication with other devices. Those skilled in the art can understand that Figure 4 the structure shown in is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0141] Among them, the processor 402 is used to run the computer program 4032 stored in the memory to implement the intelligent processing method for enterprise service data as described above.

[0142] It should be understood that in the embodiment of the present invention, the processor 402 may be a central processing unit (CPU), and the processor 402 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0143] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, and the storage medium is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0144] Therefore, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, where the computer program includes program instructions. When the program instructions are executed by the processor, the processor is caused to execute the intelligent processing method for enterprise service data as described above.

[0145] The computer-readable storage medium may be a U disk, a mobile hard disk, a read-only memory (ROM), a magnetic disk, an optical disk, or other various computer-readable storage media that can store program codes.

[0146] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0147] In several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0148] The steps in the method embodiments of the present invention can be adjusted, combined, and deleted according to actual needs. The units in the system embodiments of the present invention can be combined, divided, and deleted according to actual needs. In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0149] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0150] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An enterprise service data intelligent processing method, applied to an enterprise service data intelligent processing system, characterized in that, The enterprise service data intelligent processing system includes an enterprise user terminal, a first server, and a second server. The enterprise user terminal is communicatively connected to the first server, and the first server is communicatively connected to the second server; The enterprise service data intelligent processing method includes: If the enterprise user terminal detects a data collection instruction, it obtains an initial data set corresponding to the data collection instruction, compresses the initial data set to update the initial data set, and sends it to the first server; wherein, a data collection script is pre-deployed in the enterprise user terminal, and the data collection script is executed when the enterprise user terminal detects the data collection instruction to collect the initial data set; The first server decompresses the initial data set to update the initial data set, and sends the initial data set to the second server; The second server receives the initial data set, and performs data cleaning on the initial data set to obtain a cleaned data set; The second server performs data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set.

2. The method according to claim 1, characterized in that, Before the first server decompresses the initial data set to update the initial data set and sends the initial data set to the second server, the method further includes: The first server performs a security check on the enterprise user terminal identity information corresponding to the initial data set based on a preset firewall policy, and releases the initial data set when it is determined that the enterprise user terminal identity information passes the security check; If the first server determines that the initial data set is an encrypted data set or a signed data set, it obtains the encryption model type for data encryption or data signing of the initial data set, and decrypts the initial data set or verifies the digital signature based on the decryption model corresponding to the encryption model type to update the initial data set.

3. The method according to claim 1, wherein The obtaining of the initial data set corresponding to the data collection instruction includes: If it is determined that the data collection instruction corresponds to a timed data collection instruction, obtain the data collection effective time and the timed data collection script corresponding to the timed data collection instruction, and collect the initial data set based on the timed data collection script; If it is determined that the data collection instruction corresponds to an immediate data collection instruction, obtain the immediate data collection script corresponding to the immediate data collection instruction, and collect the initial data set based on the immediate data collection script; If it is determined that the data collection instruction corresponds to an abnormal data collection instruction, obtain the abnormal data collection script corresponding to the abnormal data collection instruction, and collect the initial data set based on the abnormal data collection script.

4. The method according to claim 1, wherein The performing of data cleaning on the initial data set to obtain a cleaned data set includes: Performing integrity verification on the initial data set based on the integrity verification sub-strategy in the data cleaning strategy to obtain an integrity verification result; If it is determined that the integrity verification result is a verification passed result, then based on the missing value processing sub-strategy in the data cleaning strategy, the initial data set is subjected to missing value deletion or completion to obtain a first processed data set; Based on the duplicate value processing sub-strategy in the data cleaning strategy, the first processed data set is subjected to duplicate value deletion to obtain a second processed data set; Based on the outlier processing sub-strategy in the data cleaning strategy, the second processed data set is subjected to outlier deletion or correction to obtain a third processed data set; Based on the data transformation processing sub-strategy in the data cleaning strategy, the third processed data set is subjected to data standardization transformation to obtain the cleaned data set.

5. The method according to claim 1, characterized in that Performing data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set, including: If it is determined that the data processing strategy is a data matching strategy, then a local target storage data set corresponding to the cleaned data set and stored locally is obtained, and the cleaned data set is compared with the local target storage data set for data matching to obtain a data matching comparison result as the data processing result.

6. The method according to claim 1, wherein Performing data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set, including: If it is determined that the data processing strategy is a data analysis and statistics strategy, then the core data analysis and statistics indicators and the data analysis target time period corresponding to the data analysis and statistics strategy are obtained; Based on the core data analysis and statistics indicators and the data analysis target time period, a target screening data set is screened from the cleaned data set and used as the data processing result.

7. The method according to claim 1, characterized in that Performing data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set, including: If it is determined that the data processing strategy is a data trend prediction strategy, then a prediction model corresponding to the data trend prediction strategy is obtained; The cleaned data set is input into the prediction model to obtain a prediction result, which is used as the data processing result.

8. An enterprise service data intelligent processing system, characterized in that, Including an enterprise user terminal, a first server, and a second server, the enterprise user terminal is communicatively connected to the first server, and the first server is communicatively connected to the second server; The enterprise user terminal is configured to, if a data collection instruction is detected, obtain an initial data set corresponding to the data collection instruction, and perform data compression on the initial data set to update the initial data set and send it to the first server; wherein, a data collection script is pre-deployed in the enterprise user terminal, and the data collection script is executed when the enterprise user terminal detects the data collection instruction to collect the initial data set; The first server is configured to decompress the initial data set to update the initial data set, and send the initial data set to the second server; The second server is configured to receive the initial data set, and perform data cleaning on the initial data set to obtain a cleaned data set; The second server is further configured to perform data processing on the cleaned data set based on a preset data processing strategy to obtain a data processing result corresponding to the cleaned data set.

9. A computer device, characterized in that, The computer device includes a memory and a processor. A computer program is stored on the memory. When the processor executes the computer program, the intelligent enterprise service data processing method according to any one of claims 1-7 is implemented.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, the intelligent enterprise service data processing method according to any one of claims 1-7 can be implemented.

Images