Method, device and equipment for executing business operation and computer readable medium

Abstract

The invention discloses a method, a device and equipment for executing business operation and a computer readable medium, and relates to the technical field of automatic programming. A specific embodiment of the method comprises the steps of traversing a historical business operation document, cleaning job scripts in the historical business operation document, and cutting the cleaned job scripts into cut job scripts; marking and cutting the job script, and training to obtain a table name entity extraction model in combination with the job dependence in the historical business operation document, so as to input the job script for executing the current business operation into the table name entity extraction model and output the job dependence of the current business operation; and obtaining a job name mapping table according to the job script of the current service operation, mapping the job table to a corresponding job scheduling name by using the job name mapping table, and filling the dependency table of the current service operation based on the job scheduling name to execute the current service operation. The embodiment can improve the correctness of the scheduling dependency parameter of the service and improve the success rate of job execution.

Description

Technical Field

[0001] The present invention relates to the field of automatic program design technology, and in particular to a method, device, equipment and computer-readable medium for executing business operations. Background Art

[0002] In the process of scheduling and managing jobs, it is necessary to manually identify the scheduling dependency parameters of the business. The manual identification process is prone to the following problems: missing the job dependency of the related table, resulting in the current job being executed, the data of the previous table may not be generated or the job name of the related table may be filled in incorrectly, resulting in job scheduling dependency execution errors.

[0003] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art: the scheduling dependency parameter error rate of the manual identification service is high, resulting in a low success rate of job execution. Summary of the invention

[0004] In view of this, the embodiments of the present invention provide a method, apparatus, device and computer-readable medium for executing business operations, which can improve the correctness of business scheduling dependency parameters and improve the success rate of job execution.

[0005] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for performing a service operation is provided, comprising:

[0006] Traversing the historical business operation documents to clean the job scripts in the historical business operation documents, and cutting the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents;

[0007] The cutting job script is marked, and combined with the job dependency of the job script in the historical business operation document, a table name entity extraction model is trained to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script of the current business operation;

[0008] Obtain a job name mapping table according to the job script of the current business operation, use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name, and fill in the dependency table of the current business operation based on the job scheduling name to execute the current business operation.

[0009] The traversing of the historical business operation documents to clean the job scripts in the historical business operation documents, and cutting the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents, includes:

[0010] Traversing historical business operation documents, cleaning job scripts in the historical business operation documents based on escape characters, and obtaining cleaned job scripts;

[0011] The business operation parameters of the historical business operation document are obtained according to the historical business operation document, so as to cut the cleaned job script into cut job scripts according to the business operation parameters of the historical business operation document.

[0012] The acquiring the business operation parameters of the historical business operation document according to the historical business operation document, so as to cut the cleaned job script into cut job scripts according to the business operation parameters of the historical business operation document, includes:

[0013] Acquire the business logic of the historical business operation document based on the historical business operation document, and acquire the business operation parameters of the historical business operation document according to the business logic;

[0014] The cleaned job script is cut into a pre-cut job script according to the business operation parameters of the historical business operation document, and the availability of the pre-cut job script is tested, and the pre-cut job script with availability is used as the cut job script.

[0015] The marking of the cutting job script and the job dependency of the job script in the historical business operation document are combined to train a table name entity extraction model, so as to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script of the current business operation, including:

[0016] The cutting job script is annotated by using a preset annotation method, and a table name entity extraction model is obtained by training in combination with the job dependency of the job script in the historical business operation document;

[0017] The job script for executing the current business operation is input into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script for the current business operation.

[0018] The method of annotating the cutting job script by a preset annotation method and training a table name entity extraction model in combination with the job dependency of the job script in the historical business operation document includes:

[0019] The cutting job script is annotated by using the BIO annotation method, wherein the label B identifies the starting end of the job dependency in the cutting job script, the label I identifies the inside of the job dependency in the cutting job script, and the label O identifies that the current word does not belong to any entity;

[0020] The cutting job script is combined with the table name in the job dependency of the job script in the historical business operation document to train a table name entity extraction model.

[0021] The step of obtaining a job name mapping table according to the job script of the current business operation, mapping a job table in a job dependency of the job script of the current business operation to a corresponding job scheduling name using the job name mapping table, and filling the dependency table of the current business operation based on the job scheduling name to execute the current business operation includes:

[0022] Search the database to obtain a job name mapping table according to the job script of the current business operation, and use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name;

[0023] The dependency table of the current business operation is filled based on the job scheduling name, and the current business operation is executed according to the dependency table.

[0024] The table name entity extraction model outputs the job dependencies of the job script of the current business operation, including:

[0025] The table name entity extraction model outputs the logical relationship between the job table in the job dependency of the job script of the current business operation and the job table;

[0026] The filling of the dependency table of the current business operation based on the job scheduling name and executing the current business operation according to the dependency table includes:

[0027] The dependency table of the current business operation is filled based on the job scheduling name, and the current business operation is executed according to the logical relationship between the job table in the dependency table and the job table.

[0028] According to a second aspect of an embodiment of the present invention, there is provided an apparatus for performing a service operation, including:

[0029] A processing module, configured to traverse the historical business operation documents to clean the job scripts in the historical business operation documents, and cut the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents;

[0030] A model module is used to annotate the cutting job script, and train a table name entity extraction model in combination with the job dependency of the job script in the historical business operation document, so as to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script of the current business operation;

[0031] An operation module is used to obtain a job name mapping table according to the job script of the current business operation, use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name, and fill in the dependency table of the current business operation based on the job scheduling name to execute the current business operation.

[0032] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for performing a service operation, including:

[0033] one or more processors;

[0034] a storage device for storing one or more programs,

[0035] When the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0036] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method as described above is implemented.

[0037] According to a fifth aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, and when the program is executed by a processor, the method as described above provided by an embodiment of the present invention is implemented.

[0038] One embodiment of the above invention has the following advantages or beneficial effects: traversing historical business operation documents to clean the job scripts in the historical business operation documents, and cutting the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents; marking the cut job scripts, and combining the job dependencies of the job scripts in the historical business operation documents, training to obtain a table name entity extraction model, so that the job script for executing the current business operation is input into the table name entity extraction model, and the table name entity extraction model outputs the job dependencies of the job script of the current business operation; obtaining a job name mapping table according to the job script of the current business operation, using the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name, and filling the dependency table of the current business operation based on the job scheduling name to execute the current business operation. Training data is constructed by cleaning and cutting the job scripts of the historical business operation documents, and then the table name entity extraction model is trained. The use of the table name entity extraction model can improve the correctness of the scheduling dependency parameters of the business and improve the success rate of job execution.

[0039] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0041] Figure 1 is a schematic diagram of the main flow of a method for performing a business operation according to an embodiment of the present invention;

[0042] Figure 2 is a flowchart of processing a job script in a historical business operation document according to an embodiment of the present invention;

[0043] Figure 3 is a flow chart of a job script after cutting and cleaning according to an embodiment of the present invention;

[0044] Figure 4 is a schematic diagram of a process of training and using a table name entity extraction model according to an embodiment of the present invention;

[0045] Figure 5 It is a flow chart of obtaining a table name entity extraction model through training of a labeling and cutting job script according to an embodiment of the present invention;

[0046] Figure 6 is a schematic diagram of a process of filling a dependency table of a current business operation to execute the current business operation according to an embodiment of the present invention;

[0047] Figure 7 is a schematic diagram of the main structure of an apparatus for performing a service operation according to an embodiment of the present invention;

[0048] Figure 8 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0049] Fig. 9 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description. The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0051] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0052] When configuring job scheduling, you need to identify the scheduling dependency parameters of the job. For example, the precondition for script execution is the table in the script. You need to know all the tables contained in the script in the job, and then find the job names corresponding to these tables. The scheduling of the current job requires configuring the job name. Subsequent job scheduling can only be performed after the above-mentioned pre-dependent jobs are completed.

[0053] However, the scheduling dependency parameters of manual identification services have a high error rate, resulting in a low success rate of job execution.

[0054] In order to solve the problem of high error rate of scheduling dependent parameters, which leads to low success rate of job execution, the following technical solution in the embodiment of the present invention can be adopted.

[0055] See also Figure 1 , Figure 1 1 is a schematic diagram of the main flow of the method for executing a business operation according to an embodiment of the present invention, and constructs training data to train a table name entity extraction model to fill the job scheduling name into the dependency table. Figure 1 As shown in 100, the following steps are specifically included:

[0056] S101, traversing historical business operation documents to clean job scripts in the historical business operation documents, and cutting the cleaned job scripts into cut job scripts according to business operation parameters of the historical business operation documents.

[0057] In an embodiment of the present invention, for a historical business operation document, a job script of the historical business operation document and a job dependency of the job script of the historical business operation document are exported. As an example, each job script corresponds to multiple job dependencies. Job script 1 involves job dependency 1, job dependency 2, and job dependency 3. Among them, job dependency 1 includes table name 1, job dependency 2 includes table name 2, and job dependency 3 includes table name 3.

[0058] In order to establish training data, historical business operation documents may be traversed to clean the job scripts in the historical business operation documents, and then the cleaned job scripts may be cut into cut job scripts according to the business operation parameters of the historical business operation documents.

[0059] See also Figure 2 That is 200, Figure 2 This is a flow chart of processing a job script in a historical business operation document according to an embodiment of the present invention. Specifically, it includes the following steps:

[0060] S201, traversing historical business operation documents, cleaning job scripts in the historical business operation documents based on escape characters, and obtaining cleaned job scripts.

[0061] In business operation documents, escape characters are used to represent special characters. To avoid parsing errors and improve data quality, it is necessary to traverse historical business operation documents and clean the job scripts in the historical business operation documents based on escape characters. As an example, delete the escape characters of the job scripts in the historical business operation documents to obtain the cleaned job scripts. For example, escape characters include: tab, \r (carriage return), and \n (line feed).

[0062] In one embodiment of the present invention, the following steps can be used to clean the job scripts in the historical business operation documents based on escape characters: Identify the escape characters in the job scripts in the historical business operation documents, and replace the escape characters with spaces or directly delete them to maintain the consistency of the job scripts.

[0063] S202: Obtain business operation parameters of the historical business operation document according to the historical business operation document, so as to cut the cleaned job script into cut job scripts according to the business operation parameters of the historical business operation document.

[0064] The number of characters in the cleaned job script is large, and it involves multiple job tables that the jobs depend on. In order to improve the accuracy of obtaining the job table, the cleaned job script needs to be divided into multiple parts.

[0065] The business operation parameters of the historical business operation document may be obtained according to the historical business operation document, so that the cleaned job script may be cut into cut job scripts according to the business operation parameters of the historical business operation document.

[0066] See also Figure 3 That is 300, Figure 3 This is a flow chart of the operation script after cutting and cleaning according to an embodiment of the present invention. Specifically, it includes the following steps:

[0067] S301. Acquire the business logic of the historical business operation document based on the historical business operation document, and acquire the business operation parameters of the historical business operation document according to the business logic.

[0068] In the embodiment of the present invention, considering that the business logic has a high correlation with the job dependency, the business logic of the historical business operation document can be obtained based on the historical business operation document, and the business operation parameters of the historical business operation document can be obtained according to the business logic.

[0069] As an example, the business logic of the historical business operation document is obtained based on the historical business operation document. For example, the business logic includes the business operation branch corresponding to operation: yes, and the business operation branch corresponding to operation: no.

[0070] Based on the historical business operation document, the business logic of the historical business operation document is obtained, and the business operation parameters of the historical business operation document can be determined. The business operation parameters include the cutting point.

[0071] As an example, based on the historical business operation document, four parts of business logic of the historical business operation document are obtained, and then it is determined that the business operation parameters of the historical business operation document include three cutting points. That is, the cleaned job script of the historical business operation document can be cut into four parts corresponding to the business logic according to the three cutting points in the business parameters.

[0072] S302: Cut the cleaned job script into pre-cut job scripts according to the business operation parameters of the historical business operation document, test the availability of the pre-cut job scripts, and use the pre-cut job scripts with availability as the cut job scripts.

[0073] In the embodiment of the present invention, after the cleaned job script is cut into a pre-cut job script according to the business operation parameters of the historical business operation document, in order to ensure the validity of the script after the cutting job script, it is necessary to test the pre-cut job script. If the test is successful, it means that the pre-cut job script is available; if the test fails, it means that the pre-cut job script is not available and the business operation parameters need to be re-determined.

[0074] The pre-cutting job script is tested to see if it is available, and the available pre-cutting job script is used as the cutting job script.

[0075] exist Figure 3 In the embodiment, in order to improve the quality of the job script as training data, cleaning is performed first and then cutting to obtain a high-quality cutting job script.

[0076] S102. Label and cut the job script, and combine the job dependencies of the job script in the historical business operation document to train a table name entity extraction model, so that the job script that executes the current business operation is input into the table name entity extraction model, and the table name entity extraction model outputs the job dependencies of the job script of the current business operation.

[0077] In an embodiment of the present invention, the job dependencies of the job scripts in the cut job scripts and the historical business operation documents are used as training data to train a table name entity extraction model. Then, the job script for executing the current business operation is input into the table name entity extraction model, and the table name entity extraction model outputs the job dependencies of the job script for the current business operation. The entity extraction model is used to process the current business operation.

[0078] See also Figure 4 That is 400, Figure 4 The flowchart of training and using the table name entity extraction model according to an embodiment of the present invention is shown in FIG. The flowchart specifically includes the following steps:

[0079] S401. Annotate the cutting job script using a preset annotation method, and train a table name entity extraction model based on the job dependencies of the job script in the historical business operation document.

[0080] In an embodiment of the present invention, the job scripts in the historical business operation documents are used as training data, and the job scripts can be annotated and cut using a preset annotation method to train a table name entity extraction model. As an example, the preset annotation method includes one or more of BIO annotation, BIOES annotation, named entity recognition (NER), and semantic segmentation.

[0081] See also Figure 5 That is 500, Figure 5 This is a flow chart of obtaining a table name entity extraction model by training a labeling and cutting job script according to an embodiment of the present invention. Specifically, it includes the following steps:

[0082] S501. Use BIO annotation to annotate the cutting job script. Label B identifies the starting end of the job dependency in the cutting job script. Label I identifies the inside of the job dependency in the cutting job script. Label O identifies that the current word does not belong to any entity.

[0083] In the embodiment of the present invention, the BIO annotation method is used in practice for training the table name entity extraction model. Among them, label B identifies the starting end of the job dependency in the cutting job script, label I identifies the inside of the job dependency in the cutting job script, and label O identifies that the current word does not belong to any entity.

[0084] S502: Cut the job script and combine it with the table name in the job dependency of the job script in the historical business operation document to train a table name entity extraction model.

[0085] The table name entity extraction model is trained by combining the table name in the job dependency of the job script in the historical business operation document. The table name entity extraction model is trained on the basis of Bi-LSTM + Attention + CRF. The following briefly introduces the Bi-LSTM + Attention + CRF model.

[0086] The Bi-LSTM + Attention + CRF model adds an Attention layer and a CRF loss layer to the Bi-LSTM model. In the Bi-LSTM model, the output vector of the last time series is used as the feature vector, and then softmax classification is performed. At this time, if the prediction is made directly without considering the information of the previous and next labels, the prediction result will be inaccurate. Therefore, in order to consider the information of adjacent labels, a CRF layer is usually added to the last layer.

[0087] Attention first calculates the weight of each time series, and then takes the weighted sum of all time series vectors as the feature vector. Adding Attention does improve the results. The entire Bilstm+attention+CRF consists of the following six parts.

[0088] Input layer: Serialize and input the training data organized by S501.

[0089] Embedding layer: maps each word in the sentence into a vector of fixed length, converts the serialized text of the input layer into the corresponding embedding layer, learns the overall features, automatically adjusts the vector parameters according to the model, and then performs a bidirectional recurrent neural network and attention mechanism layer.

[0090] LSTM layer: The embedding vector is calculated using a bidirectional LSTM. In fact, the bidirectional LSTM calculates the word vector to obtain a higher-level sentence vector. The formula is as follows;

[0091]

[0092]

[0093]

[0094]

[0095]

[0096]

[0097] Formula 1

[0098] The LSTM model is composed of Input word of time , cell status , temporary cell state , hidden layer state , the Forget Gate , Memory Gate , output gate The calculation process of LSTM is briefly described as follows: by forgetting the information in the cell state and remembering new information, the information useful for subsequent moment calculations can be transmitted, while the useless information is discarded, and the hidden state is output at each time node. Among them, forgetting, memory and output are determined by the hidden state of the previous moment and the current input Calculated forget gate , Memory Gate , output gate To control. Bilstm is a combination of forward LSTM and backward LSTM. Compared with LSTM, the bidirectional loop LSTM can better capture the problem of bidirectional semantic dependency.

[0099] Attention layer: Use Attention weighting on the results of bidirectional LSTM;

[0100]

[0101]

[0102]

[0103] Formula 2

[0104] Logically speaking, attention includes two processes: decoder and encoder. Its function is to encode a vector sequence X into another vector sequence Z. Each original vector X is just a digital block representing a word. After encoding and transformation, the vector Z not only contains the original word information, but also includes its relationship with other surrounding words. The calculation process is that the input Input undergoes linear changes to obtain Q, K, and V in the above formula, where q is used to match other units; k is used to be matched by other units; k represents the information to be extracted, and then Q and K are dot-producted to obtain the dependency relationship between the input words. Then, after scale change, mask, and softmax operations, the final attention matrix is ​​obtained. Among them, the scale change is to prevent the input value from being too large and causing unstable training, and the mask is to ensure the order of time.

[0105]

[0106] Formula 3

[0107] in, It is the number of columns of Q, K matrix, that is, the vector dimension.

[0108] CRF layer: As mentioned above, directly calculating the sequence with the highest probability at each moment through the bilstm output layer is to regard the labels as independent individuals, which leads to the failure to obtain the optimal training effect. Therefore, the output vector of the Bilstm+attention layer is input to the CRF layer, and the introduction of the transfer matrix parameters can make the final sequence have a constraint relationship. Define the matrix is the output of the Bilstm+attention layer, represents the probability that the i-th character in the script is the j-th label. Define the state transition matrix A, where represents the probability of the i-th label being transferred to the j-th label. The formula for the output sequence y is as follows:

[0109]

[0110] Formula 4

[0111] Softmax layer: Finally, the softmax layer is used to calculate the probabilities of all category labels, obtain the BIO label corresponding to each character, extract the BI label in the script, and obtain the table name corresponding to the script.

[0112] S402: Input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script for the current business operation.

[0113] After the table name entity extraction model is obtained by training the training data, the job script for executing the current business operation is input into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script for the current business operation, wherein the job dependency includes the table name of the job table.

[0114] exist Figure 4 In the embodiment, a table name entity extraction model is obtained by training with training data, and then the table name entity extraction model is used to determine the table name that the job depends on in the job script of the current business operation.

[0115] In one embodiment of the present invention, since the business operation parameters of the historical business operation document can be obtained according to the business logic of the historical business operation document, the logical relationship between the job tables in the job dependency of the job tag can be used in the training table name entity extraction model.

[0116] In this way, the table name entity extraction model outputs the logical relationship between the job table and the job table in the job dependency of the job script of the current business operation.

[0117] S103. Obtain a job name mapping table according to the job script of the current business operation, use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name, and fill in the dependency table of the current business operation based on the job scheduling name to execute the current business operation.

[0118] In an embodiment of the present invention, a job name mapping table can be obtained according to the job script of the current business operation, and then the job table in the job dependency of the job script of the current business operation can be mapped to the corresponding job scheduling name, and the dependency table of the current business operation can be filled based on the job scheduling name to execute the current business operation.

[0119] See also Figure 6 That is 600, Figure 6 This is a flow chart of filling the dependency table of the current business operation to execute the current business operation according to an embodiment of the present invention. Specifically, it includes the following steps:

[0120] S601 , searching a database for a job name mapping table according to a job script of a current business operation, and using the job name mapping table to map a job table in a job dependency of the job script of the current business operation to a corresponding job scheduling name.

[0121] In an embodiment of the present invention, a job name mapping table is stored in a database, and the database can be searched based on the job script of the current business operation to obtain the job name mapping table. The job name mapping table includes the corresponding relationship between the job table and the job scheduling name.

[0122] Then, the job table in the job dependency of the job script of the current business operation is mapped to the corresponding job scheduling name using the job name mapping table. As an example, job table TablenameA is mapped to job 1; job table TablenameB is mapped to job 2; job table TablenameC is mapped to job 3; and job table TablenameD is mapped to job 4.

[0123] S602: Fill in a dependency table of the current business operation based on the job scheduling name, and execute the current business operation according to the dependency table.

[0124] The dependency table of the current business operation is filled based on the job scheduling name. When all job scheduling names are filled in the dependency table of the current business operation, the dependency table is searched to see whether the current business operation meets the execution conditions corresponding to the job scheduling name, and then the current business operation is executed according to the dependency table.

[0125] exist Figure 6In an embodiment, the job table in the job dependency of the job script of the current business operation is filled into the dependency table to implement the current business operation.

[0126] In one embodiment of the present invention, there is a logical relationship between the business tables, and the dependency table of the current business operation can be filled based on the job scheduling name, and the current business operation is executed according to the logical relationship between the job table and the job table in the dependency table.

[0127] The logical relationship between the job tables represents the order of executing the current business operation. Executing the current business operation according to the logical relationship between the job tables in the dependency table can improve the efficiency of executing the business operation and avoid repeated operations and missed operations.

[0128] In the above-mentioned embodiment of the present invention, the job scripts in the historical business operation documents are traversed to clean the job scripts in the historical business operation documents, and the cleaned job scripts are cut into cut job scripts according to the business operation parameters of the historical business operation documents; the cut job scripts are marked, and combined with the job dependencies of the job scripts in the historical business operation documents, a table name entity extraction model is trained to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependencies of the job script of the current business operation; the job name mapping table is obtained according to the job script of the current business operation, and the job name mapping table is used to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name, and the dependency table of the current business operation is filled based on the job scheduling name to execute the current business operation. Training data is constructed by cleaning and cutting the job scripts of the historical business operation documents, and then the table name entity extraction model is trained. The use of the table name entity extraction model can improve the correctness of the scheduling dependency parameters of the business and improve the success rate of job execution.

[0129] The table name entity extraction model is used to extract the job table in the job dependency of the job script of the current business operation to ensure accurate improvement of the job book and avoid missing tables.

[0130] See also Figure 7 , Figure 7 is a schematic diagram of the main structure of an apparatus for performing a business operation according to an embodiment of the present invention. The apparatus for performing a business operation can implement a method for performing a business operation, such as Figure 7 As shown in 700, the device for performing the service operation specifically includes:

[0131] Processing module 701, used for traversing historical business operation documents to clean the job scripts in the historical business operation documents, and cutting the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents;

[0132] Model module 702, used to annotate the cutting job script, and train a table name entity extraction model in combination with the job dependency of the job script in the historical business operation document, so as to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script of the current business operation;

[0133] Operation module 703 is used to obtain a job name mapping table according to the job script of the current business operation, use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name, and fill in the dependency table of the current business operation based on the job scheduling name to execute the current business operation.

[0134] In one embodiment of the present invention, the processing module 701 is specifically used to traverse the historical business operation documents, clean the job scripts in the historical business operation documents based on the escape characters, and obtain the cleaned job scripts;

[0135] The business operation parameters of the historical business operation document are obtained according to the historical business operation document, so as to cut the cleaned job script into cut job scripts according to the business operation parameters of the historical business operation document.

[0136] In one embodiment of the present invention, the processing module 701 is specifically configured to obtain the business logic of the historical business operation document based on the historical business operation document, and obtain the business operation parameters of the historical business operation document according to the business logic;

[0137] The cleaned job script is cut into a pre-cut job script according to the business operation parameters of the historical business operation document, and the availability of the pre-cut job script is tested, and the pre-cut job script with availability is used as the cut job script.

[0138] In one embodiment of the present invention, the model module 702 is specifically used to annotate the cutting operation script using a preset annotation method, and train a table name entity extraction model in combination with the operation dependency of the operation script in the historical business operation document;

[0139] The job script for executing the current business operation is input into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script for the current business operation.

[0140] In one embodiment of the present invention, the model module 702 is specifically used to annotate the cutting job script using the BIO annotation method, where the label B identifies the starting end of the job dependency in the cutting job script, the label I identifies the inside of the job dependency in the cutting job script, and the label O identifies that the current word does not belong to any entity;

[0141] The cutting job script is combined with the table name in the job dependency of the job script in the historical business operation document to train a table name entity extraction model.

[0142] In one embodiment of the present invention, the operation module 703 is specifically used to search the database according to the job script of the current business operation to obtain a job name mapping table, and use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name;

[0143] The dependency table of the current business operation is filled based on the job scheduling name, and the current business operation is executed according to the dependency table.

[0144] In one embodiment of the present invention, the model module 702 is specifically used for the table name entity extraction model to output the logical relationship between the job table in the job dependency of the job script of the current business operation and the job table;

[0145] The operation module 703 is specifically used to fill the dependency table of the current business operation based on the job scheduling name, and execute the current business operation according to the logical relationship between the job table in the dependency table and the job table.

[0146] Figure 8 An exemplary system architecture 800 is shown to which the method for executing a business operation or the apparatus for executing a business operation according to the embodiments of the present invention can be applied.

[0147] like Figure 8 As shown, system architecture 800 may include terminal devices 801, 802, 803, a network 804, and a server 805. Network 804 is used to provide a medium for communication links between terminal devices 801, 802, 803 and server 805. Network 804 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0148] Users can use terminal devices 801, 802, and 803 to interact with server 805 through network 804 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 801, 802, and 803, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0149] The terminal devices 801 , 802 , and 803 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0150] The server 805 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 801, 802, and 803. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0151] It should be noted that the method for executing a business operation provided in the embodiment of the present invention is generally executed by the server 805 , and accordingly, the device for executing the business operation is generally disposed in the server 805 .

[0152] It should be understood that Figure 8 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0153] A computer program product according to an embodiment of the present invention includes a computer program, and when the program is executed by a processor, the method for executing a business operation provided by an embodiment of the present invention is implemented.

[0154] Reference below Fig. 9 , which shows a schematic diagram of the structure of a computer system 900 of a terminal device suitable for implementing an embodiment of the present invention. Fig. 9 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0155] like Fig. 9 As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the system 900 are also stored. The CPU 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0156] The following components are connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage section 908 as needed.

[0157] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the central processing unit (CPU) 901, the above-mentioned functions defined in the system of the present invention are executed.

[0158] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0159] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0160] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be arranged in a processor, for example, they may be described as: a processor including a processing module, a model module and an operation module. The names of these modules do not constitute limitations on the modules themselves in certain cases, for example, the processing module may also be described as "used to traverse historical business operation documents to clean the job scripts in the historical business operation documents, and cut the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents".

[0161] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:

[0162] Traversing the historical business operation documents to clean the job scripts in the historical business operation documents, and cutting the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents;

[0163] The cutting job script is marked, and combined with the job dependency of the job script in the historical business operation document, a table name entity extraction model is trained to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script of the current business operation;

[0164] Obtain a job name mapping table according to the job script of the current business operation, use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name, and fill in the dependency table of the current business operation based on the job scheduling name to execute the current business operation.

[0165] According to the technical solution of the embodiment of the present invention, the historical business operation documents are traversed to clean the job scripts in the historical business operation documents, and the cleaned job scripts are cut into cut job scripts according to the business operation parameters of the historical business operation documents; the cut job scripts are marked, and combined with the job dependencies of the job scripts in the historical business operation documents, a table name entity extraction model is trained to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependencies of the job script of the current business operation; the job name mapping table is obtained according to the job script of the current business operation, and the job table in the job dependency of the job script of the current business operation is mapped to the corresponding job scheduling name using the job name mapping table, and the dependency table of the current business operation is filled based on the job scheduling name to execute the current business operation. Training data is constructed by cleaning and cutting the job scripts of the historical business operation documents, and then the table name entity extraction model is trained. The use of the table name entity extraction model can improve the correctness of the scheduling dependency parameters of the business and improve the success rate of job execution.

[0166] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0167] It should be noted that in the technical solution of the present invention, the collection, analysis, use, transmission, storage and other aspects of user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside of these legal uses, and are subject to supervision and management by regulatory authorities. Necessary measures should be taken for user personal information to prevent illegal access to such personal information data, ensure that persons who have access to personal information data comply with the provisions of relevant laws and regulations, and ensure the security of user personal information. Once these user personal information data are no longer needed, the risks should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0168] When applicable, including in certain relevant applications, protect user privacy by de-identifying data, such as by removing specific identifiers (e.g., date of birth, etc.) when applicable, controlling the amount or specificity of data stored (e.g., collecting location data at a city level rather than at a specific address level), controlling how data is stored, and / or other de-identification methods.

Claims

1. A method for performing a business operation, characterized in that: include: Traversing the historical business operation documents to clean the job scripts in the historical business operation documents, and cutting the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents; The cutting job script is marked, and combined with the job dependency of the job script in the historical business operation document, a table name entity extraction model is trained to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script of the current business operation; Obtain a job name mapping table according to the job script of the current business operation, use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name, and fill in the dependency table of the current business operation based on the job scheduling name to execute the current business operation.

2. The method for performing business operations according to claim 1, characterized in that: The traversing of the historical business operation documents to clean the job scripts in the historical business operation documents, and cutting the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents, includes: Traversing historical business operation documents, cleaning job scripts in the historical business operation documents based on escape characters, and obtaining cleaned job scripts; The business operation parameters of the historical business operation document are obtained according to the historical business operation document, so as to cut the cleaned job script into cut job scripts according to the business operation parameters of the historical business operation document.

3. The method for performing business operations according to claim 2, characterized in that: The acquiring the business operation parameters of the historical business operation document according to the historical business operation document, so as to cut the cleaned job script into cut job scripts according to the business operation parameters of the historical business operation document, includes: Acquire the business logic of the historical business operation document based on the historical business operation document, and acquire the business operation parameters of the historical business operation document according to the business logic; The cleaned job script is cut into a pre-cut job script according to the business operation parameters of the historical business operation document, and the availability of the pre-cut job script is tested, and the pre-cut job script with availability is used as the cut job script.

4. The method for performing business operations according to claim 1, characterized in that: The marking of the cutting job script and the job dependency of the job script in the historical business operation document are combined to train a table name entity extraction model, so as to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script of the current business operation, including: The cutting job script is annotated by using a preset annotation method, and a table name entity extraction model is obtained by training in combination with the job dependency of the job script in the historical business operation document; The job script for executing the current business operation is input into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script for the current business operation.

5. The method for performing business operations according to claim 4, characterized in that: The method of annotating the cutting job script by a preset annotation method and training a table name entity extraction model in combination with the job dependency of the job script in the historical business operation document includes: The cutting job script is annotated by using the BIO annotation method, wherein the label B identifies the starting end of the job dependency in the cutting job script, the label I identifies the inside of the job dependency in the cutting job script, and the label O identifies that the current word does not belong to any entity; The cutting job script is combined with the table name in the job dependency of the job script in the historical business operation document to train a table name entity extraction model.

6. The method for performing business operations according to claim 1, characterized in that: The step of obtaining a job name mapping table according to the job script of the current business operation, mapping a job table in a job dependency of the job script of the current business operation to a corresponding job scheduling name using the job name mapping table, and filling the dependency table of the current business operation based on the job scheduling name to execute the current business operation includes: Search the database to obtain a job name mapping table according to the job script of the current business operation, and use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name; The dependency table of the current business operation is filled based on the job scheduling name, and the current business operation is executed according to the dependency table.

7. The method for performing business operations according to claim 6, characterized in that: The table name entity extraction model outputs the job dependencies of the job script of the current business operation, including: The table name entity extraction model outputs the logical relationship between the job table in the job dependency of the job script of the current business operation and the job table; The filling of the dependency table of the current business operation based on the job scheduling name and executing the current business operation according to the dependency table includes: The dependency table of the current business operation is filled based on the job scheduling name, and the current business operation is executed according to the logical relationship between the job table in the dependency table and the job table.

8. A device for performing a business operation, characterized in that: include: A processing module, configured to traverse the historical business operation documents to clean the job scripts in the historical business operation documents, and cut the cleaned job scripts into cut job scripts according to the business operation parameters of the historical business operation documents; A model module is used to annotate the cutting job script, and train a table name entity extraction model in combination with the job dependency of the job script in the historical business operation document, so as to input the job script for executing the current business operation into the table name entity extraction model, and the table name entity extraction model outputs the job dependency of the job script of the current business operation; An operation module is used to obtain a job name mapping table according to the job script of the current business operation, use the job name mapping table to map the job table in the job dependency of the job script of the current business operation to the corresponding job scheduling name, and fill in the dependency table of the current business operation based on the job scheduling name to execute the current business operation.

9. An electronic device for performing business operations, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images