CN113283222A - Automatic report generation method and device, computer equipment and storage medium - Google Patents
Automatic report generation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113283222A CN113283222A CN202110650664.2A CN202110650664A CN113283222A CN 113283222 A CN113283222 A CN 113283222A CN 202110650664 A CN202110650664 A CN 202110650664A CN 113283222 A CN113283222 A CN 113283222A
- Authority
- CN
- China
- Prior art keywords
- report
- model
- data
- target
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/174—Form filling; Merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Algebra (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application belongs to the field of artificial intelligence and relates to an automatic report generation method which comprises the steps of obtaining a report type of a target report and all stored report types, converting the report type into a label vector through characteristic engineering, and converting the report type into a characteristic vector; acquiring a preset target prediction model, inputting a label vector and a feature vector into the target prediction model, and calculating by a gradient lifting decision tree and a logistic regression model in the target prediction model to obtain the prediction connection probability between reports; and predicting and sequencing the report forms of the target report according to the predicted connection probability to obtain a sequencing result, and matching the report content in the target report with the report forms according to the sequencing result to obtain an optimal report form. The application also provides an automatic report generation device, computer equipment and a storage medium. In addition, the application also relates to a block chain technology, and the sequencing result can be stored in the block chain. The method and the device improve the automatic generation efficiency of the report.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to an automated report generation method and apparatus, a computer device, and a storage medium.
Background
At present, the monitoring and application of data indexes are often lacked in daily management, the trend of data cannot be checked through the existing index report, namely, the operation trend represented by the digital indexes is difficult to identify, and the operation scheme planning and target tracking work cannot be effectively carried out aiming at the data indexes. When the data is tracked through the report, the report is often drawn manually, and particularly when a large amount of data needs to be generated, manual repeated screening and determination are needed, so that the technical problem of low report generation efficiency is finally caused.
Disclosure of Invention
An object of the embodiments of the present application is to provide an automated report generation method, an automated report generation device, a computer device, and a storage medium, so as to solve the technical problem of low report generation efficiency.
In order to solve the above technical problem, an embodiment of the present application provides an automated report generation method, which adopts the following technical solutions:
acquiring a report type of a target report and all stored report types, converting the report type into a label vector through a feature engineering, and converting the report type into a feature vector;
acquiring a preset target prediction model, inputting the label vector and the feature vector into the target prediction model, and calculating by a gradient lifting decision tree and a logistic regression model in the target prediction model to obtain the prediction connection probability between reports;
and predicting and sequencing the report forms of the target report according to the predicted connection probability to obtain a sequencing result, and matching the report content in the target report with the report forms according to the sequencing result to obtain an optimal report form of the target report.
Further, the step of inputting the label vector and the feature vector into the target prediction model, and obtaining the prediction join probability between each report through calculation of a gradient boosting decision tree and a logistic regression model in the target prediction model specifically includes:
inputting the label vector and the feature vector into a gradient lifting decision tree in the target prediction model, outputting through leaf nodes of the gradient lifting decision tree to obtain discrete features, and coding the discrete features to obtain coding features;
and carrying out weighted summation on the coding features to obtain a summation result, inputting the summation result to the logistic regression model, and calculating to obtain the prediction connection probability.
Further, the step of obtaining the preset target prediction model specifically includes:
acquiring a preset basic prediction model, historical label data, historical characteristic data and historical interaction data;
and training the basic prediction model according to the historical label data, the historical characteristic data and the historical interaction data to obtain the target prediction model.
Further, the step of training the basic prediction model according to the historical label data, the historical feature data and the historical interaction data to obtain the target prediction model specifically includes:
selecting a first preset number of the historical label data, the historical characteristic data and the historical interaction data as training data, and selecting a second preset number of the historical label data, the historical characteristic data and the historical interaction data as verification data;
training the basic prediction model according to the training data to obtain a model to be optimized, verifying the model to be optimized according to the verification data, and determining the model to be optimized as the target prediction model when the verification passing rate of the model to be optimized on the verification data is greater than or equal to a preset threshold value.
Further, after the step of verifying the model to be optimized according to the verification data, the method further includes:
when the verification passing rate of the model to be optimized on the verification data is smaller than the preset threshold value, acquiring a preset loss function, adjusting the parameter size of the model to be optimized according to the loss function, and when the loss function is converged, determining that the parameter adjustment of the model to be optimized is completed, so as to obtain the model to be optimized with the parameter adjustment completed;
and verifying the model to be optimized after the parameter adjustment according to the verification data, and determining the model to be optimized after the parameter adjustment as the target prediction model when the verification passing rate of the model to be optimized after the parameter adjustment on the verification data is greater than or equal to the preset threshold value.
Further, the step of adjusting the parameter size of the model to be optimized according to the loss function specifically includes:
obtaining a prediction result obtained by calculating historical label data and historical characteristic data in the training data by the model to be optimized;
calculating a loss value of the prediction result and the historical interaction data according to the loss function, obtaining a preset parameter adjusting instruction corresponding to the loss value, and adjusting the parameter of the model to be optimized according to the preset parameter adjusting instruction.
Further, after the step of obtaining the preferred report form of the target report, the method further includes:
and storing the preferred report in a block chain.
In order to solve the above technical problem, an embodiment of the present application further provides an automatic report generating device, which adopts the following technical solution:
the acquisition module is used for acquiring the report type of a target report and all the stored report types, converting the report type into a label vector through a feature engineering, and converting the report type into a feature vector;
the prediction module is used for acquiring a preset target prediction model, inputting the label vector and the feature vector into the target prediction model, and calculating through a gradient lifting decision tree and a logistic regression model in the target prediction model to obtain the prediction connection probability between reports;
and the sequencing module is used for predicting and sequencing the report of the target report according to the predicted connection probability to obtain a sequencing result, and matching the report content in the target report with the report according to the sequencing result to obtain an optimal report of the target report.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which includes a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, where the processor implements the steps of the above automated report generation method when executing the computer readable instructions.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, where computer-readable instructions are stored, and when executed by a processor, the computer-readable instructions implement the steps of the above automated report generation method.
According to the automatic report generation method, the report type of the target report and all the stored report types are obtained, the report type is converted into the label vector through the characteristic engineering, the report type is converted into the characteristic vector, and the prediction connection probability of the report can be accurately calculated according to the characteristic vector and the label vector; then, a preset target prediction model is obtained, a label vector and a feature vector are input into the target prediction model, and the prediction connection probability between reports is obtained through calculation of a gradient promotion decision tree and a logistic regression model in the target prediction model, so that the reports of the target report are accurately recommended through the prediction connection probability, and automatic generation of the reports is further realized; and then, forecasting and sequencing the report forms of the target report according to the forecasting connection probability to obtain a sequencing result, matching the report content in the target report with the report forms according to the sequencing result to obtain an optimal report form of the target report, realizing automatic generation of the data report form, improving the report form generation efficiency and further realizing intelligent visualization of data.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of an automated report generation method according to the present application;
FIG. 3 is a schematic diagram of an embodiment of an automated report generation apparatus according to the present application;
FIG. 4 is a schematic block diagram of one embodiment of a computer device according to the present application.
Reference numerals: the system comprises an automatic report generation device 300, an acquisition module 301, a prediction module 302 and a sorting module 303.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the automated report generation method provided in the embodiment of the present application is generally executed by a server/terminal device, and accordingly, the automated report generation apparatus is generally disposed in the server/terminal device.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow diagram of one embodiment of a method of automated report generation in accordance with the present application is shown. The automatic report generation method comprises the following steps:
step S201, obtaining the report type of the target report and all the stored report types, converting the report type into a label vector through a feature engineering, and converting the report type into a feature vector.
In this embodiment, the target report is a data report that needs to be subjected to chart conversion, and when the target report is received, the report type of the target report, such as the categories of the financial category and the business category, is obtained. The report type is converted into a label vector through feature engineering. Specifically, the feature engineering is a data conversion mode for converting original data into initial parameter data which can be input by a model, and the feature engineering comprises feature data conversion modes such as linear normalization, category coding and a plurality of feature combinations. When the report type is a character string, the report type can be converted into a label vector through category coding, wherein the category coding comprises serial number coding, one-hot coding and binary coding, and the report type can be converted into the label vector through any one mode of sequence coding, one-hot coding and binary coding. Taking the one-hot coding as an example, the one-hot coding is to encode N states by using N-bit state registers using parameters expressed by 0, 1, and when a report type or a report type is obtained, the report type or the report type can be directly converted into a corresponding tag vector or a corresponding feature vector through the one-hot coding.
The report types comprise chart types and digital report types, and all the stored chart types and digital report types are obtained. The chart type and the digital report type can be converted into corresponding feature vectors by the conversion mode of the feature engineering, and the description is omitted here.
Step S202, a preset target prediction model is obtained, the label vector and the feature vector are input into the target prediction model, and the prediction connection probability between reports is obtained through calculation of a gradient lifting decision tree and a logistic regression model in the target prediction model.
In this embodiment, a preset target prediction model is obtained, where the target prediction model includes a feature input layer, a decision tree processing layer and a classification layer, the decision tree processing layer is a gradient lifting decision tree structure, the classification layer is a logistic regression model structure, and an output result of a previous layer is input data of a next layer. When the label vector and the feature vector are obtained, the label vector and the feature vector are used as input data of the target prediction model and are input into the target prediction model. The target prediction model is obtained by training a basic prediction model, and the basic prediction model and the target prediction model adopt the same structure but have different parameters. Pre-collecting a plurality of groups of historical label data, historical characteristic data and historical interaction data to train a basic prediction model; and adjusting parameters of the basic prediction model according to each training result, wherein each parameter adjustment can be specifically determined according to the training result and the corresponding preset parameter adjustment instruction, and different training results correspond to different preset parameter adjustment instructions. The training result can be represented by a loss value of a prediction result and historical interactive data calculated by a basic prediction model, the historical label data is a historical stored report type label, the historical characteristic data is historical stored report type data, and the historical interactive data is joint data of reports in each report type and the report type. And when the verification passing rate of the model after the parameter adjustment on the preset verification data is greater than or equal to a preset threshold value, determining the model after the parameter adjustment as a target detection model.
And when the target prediction model is obtained, calculating the label vector and the feature vector through a decision tree processing layer and a classification layer, and finally outputting to obtain the prediction connection probability between each report corresponding to the current target report. The predicted connection probability refers to a probability value of another report appearing after each report, such as a probability value of a report B appearing after a report A, and a probability value of a report C appearing after a report B. And when the predicted connection probabilities among all reports are obtained, selecting the report corresponding to the predicted connection probability with the maximum report probability value as the next connection report of the current report. For example, if the probability value of the report B appearing after the report A is 0.5, and the probability value of the report C appearing after the report A is 0.8, the report C corresponding to 0.8 is selected as the next linked report of the current report A.
Step S203, the report forms of the target report are subjected to prediction sorting according to the prediction connection probability to obtain a sorting result, and the report content in the target report is matched with the report forms according to the sorting result to obtain the optimal report forms of the target report.
In this embodiment, when the predicted join probability is obtained, the reports of the target report are sorted according to the predicted join probability to obtain a sorting result, where the sorting result is the arrangement order of each report. For example, the predicted join probability of the report B to the report a is the largest, the report B is joined after the report a, the predicted join probability of the report C to the report B is the largest, the report C is joined after the report B, and the final obtained sorting result is A, B, C. And after the sequencing result is obtained, matching the corresponding report with the content of the report according to the sequencing result, and finally obtaining the optimal report of the target report.
According to the embodiment, the automatic generation of the data report is realized, the report generation efficiency is improved, and the intelligent visualization of data is further realized.
In some embodiments of the present application, the inputting the label vector and the feature vector into the target prediction model, and obtaining the prediction join probability between each report through calculation by a gradient boosting decision tree and a logistic regression model in the target prediction model includes:
inputting the label vector and the feature vector into a gradient lifting decision tree in the target prediction model, outputting through leaf nodes of the gradient lifting decision tree to obtain discrete features, and coding the discrete features to obtain coding features;
and carrying out weighted summation on the coding features to obtain a summation result, inputting the summation result to the logistic regression model, and calculating to obtain the prediction connection probability.
In this embodiment, the gradient boosting decision tree is an iterative decision tree, and is composed of a plurality of decision trees, the gradient boosting decision tree performs multiple iterations, each iteration generates one decision tree, and each decision tree is trained on the basis of the residual error of the previous iteration, so as to finally obtain an optimal decision tree. The logistic regression model is a classification model, and the logistic regression model can judge the property of the articles, predict the suitability probability of the articles and the target and sequence the articles. In this embodiment, the prediction result finally obtained by the logistic regression model is the probability value of the connection between the reports. Specifically, different paths from the root node to the leaf nodes of the gradient lifting decision tree correspond to feature combinations of different features, the leaf nodes of each decision tree can uniquely represent one path, and a plurality of different feature combinations can be obtained according to the path output of each leaf node. When the label vector and the feature vector are obtained, the label vector and the feature vector are input into a gradient lifting decision tree, and a plurality of discrete features are obtained through the path output of each leaf node of the gradient lifting decision tree. And carrying out one-hot coding on the discrete features to obtain coding features. Then, carrying out linear weighted summation on the coding characteristics of each leaf node to obtain a summation value; and inputting the summation value to a logistic regression model, and outputting through the logistic regression model to obtain the predicted engagement probability.
According to the embodiment, the input data is calculated through the gradient lifting decision tree and the logistic regression model, the data processing and classification efficiency is improved, the automatic generation of the report is realized, and the report generation efficiency is improved.
In some embodiments of the present application, the obtaining of the preset target prediction model includes:
acquiring a preset basic prediction model, historical label data, historical characteristic data and historical interaction data;
and training the basic prediction model according to the historical label data, the historical characteristic data and the historical interaction data to obtain the target prediction model.
In this embodiment, a base prediction model is obtained, which includes an initial gradient boosting decision tree and an initial logistic regression model. The initial gradient boost decision tree and the initial logistic regression model in the basic prediction model are trained simultaneously through historical label data, historical characteristic data and historical interaction data, and a final target prediction model can be obtained through training.
Specifically, a plurality of groups of historical label data, historical characteristic data and historical interaction data are collected in advance to serve as sample data, wherein the historical label data are historical stored report type labels, the historical characteristic data are historical stored report type data, and the historical interaction data are linking data of reports in each report type and the report type. Inputting the historical label data, the historical characteristic data and the historical interaction data into a gradient lifting decision tree and a logistic regression model for training, and obtaining the target prediction model when the training of the historical label data, the historical characteristic data and the historical interaction data on the basic prediction model is completed.
In the embodiment, the basic prediction model is trained through the historical label data, the historical characteristic data and the historical interaction data, so that the data can be accurately calculated through the trained target prediction model, and the prediction accuracy of the target prediction model on the data is further improved.
In some embodiments of the present application, the training the basic prediction model according to the historical label data, the historical feature data, and the historical interaction data to obtain the target prediction model includes:
selecting a first preset number of the historical label data, the historical characteristic data and the historical interaction data as training data, and selecting a second preset number of the historical label data, the historical characteristic data and the historical interaction data as verification data;
training the basic prediction model according to the training data to obtain a model to be optimized, verifying the model to be optimized according to the verification data, and determining the model to be optimized as the target prediction model when the verification passing rate of the model to be optimized on the verification data is greater than or equal to a preset threshold value.
In this embodiment, when obtaining the historical tag data, the historical feature data, and the historical interaction data, all the historical table data, the historical feature data, and the historical interaction data are divided into training data and verification data according to a preset ratio. The training data comprises a first preset number of historical label data, historical feature data and historical interaction data, and the verification data comprises a second preset number of historical label data, historical feature data and historical interaction data. Training the basic prediction model according to the training data to obtain a model to be optimized, then verifying the model to be optimized according to verification data, and determining the model to be optimized as a target detection model when the verification passing rate of the model to be optimized on the verification data is larger than or equal to a preset threshold value.
According to the embodiment, the basic prediction model is trained and verified through the training data and the verification data, and the accuracy of model prediction is ensured.
In some embodiments of the present application, after the verifying the model to be optimized according to the verification data, the method further includes:
when the verification passing rate of the model to be optimized on the verification data is smaller than the preset threshold value, acquiring a preset loss function, adjusting the parameter size of the model to be optimized according to the loss function, and when the loss function is converged, determining that the parameter adjustment of the model to be optimized is completed, so as to obtain the model to be optimized with the parameter adjustment completed;
and verifying the model to be optimized after the parameter adjustment according to the verification data, and determining the model to be optimized after the parameter adjustment as the target prediction model when the verification passing rate of the model to be optimized after the parameter adjustment on the verification data is greater than or equal to the preset threshold value.
In this embodiment, when the verification passing rate of the model to be optimized for the verification data is smaller than the preset threshold, a preset loss function is obtained, where the loss function is a log-likelihood loss, and the parameter of the model to be optimized is adjusted according to the loss function.
If the calculated loss function is not converged, acquiring a preset parameter adjusting instruction according to the result obtained by calculating the loss function, increasing or decreasing the parameters of the model to be optimized according to the preset parameter adjusting instruction, and taking the model to be optimized after each parameter adjustment as the model to be optimized corresponding to the next training data until the loss function calculated according to the model to be optimized is converged; and when the loss function is converged, determining that the parameter adjustment of the model to be optimized is completed at the moment, and obtaining the model to be optimized with the parameter adjustment completed. And verifying the model to be optimized after the parameter adjustment according to the verification data, and determining the model to be optimized after the parameter adjustment as a target prediction model when the verification passing rate of the model to be optimized after the parameter adjustment on the verification data is greater than or equal to a preset threshold value. And if the verification passing rate of the model to be optimized after parameter adjustment on the verification data is still smaller than the preset threshold value, the selection of the verification data or the training data is wrong, and new verification data and new training data are selected again to train the basic prediction model.
According to the embodiment, the model is subjected to parameter adjustment through the loss function, so that the training efficiency of the model is improved, and the prediction accuracy of the model in the process of predicting data is further improved.
In some embodiments of the present application, the adjusting the parameter size of the model to be optimized according to the loss function includes:
obtaining a prediction result obtained by calculating historical label data and historical characteristic data in the training data by the model to be optimized;
calculating a loss value of the prediction result and the historical interaction data according to the loss function, obtaining a preset parameter adjusting instruction corresponding to the loss value, and adjusting the parameter of the model to be optimized according to the preset parameter adjusting instruction.
In this embodiment, when a loss function is calculated, the historical label data and the historical feature data are input to a gradient lifting decision tree in a model to be optimized, and then are output through a logistic regression model to obtain a prediction result. And comparing the prediction result with the historical interactive data, and adjusting the parameters of the basic training model according to the error of the prediction result and the historical interactive data, wherein the error is the loss value calculated according to the loss function. And acquiring a corresponding preset parameter adjusting instruction according to the loss value, and increasing or decreasing the parameter of the model to be optimized according to the preset parameter adjusting instruction.
Specifically, the calculation formula of the loss function is as follows:
wherein Y is an output variable, X is an input variable, L is a loss function, N is an input sample size, M is a possible class number,in order to be a true probability,is the prediction probability.
According to the embodiment, the loss value of the prediction result and the loss value of the historical interaction data are compared, so that the prediction result calculated by the model is closer to the real result, and the prediction accuracy of the model is improved.
In some embodiments of the present application, after obtaining the preferred report of the target report, the method further includes:
and storing the preferred report in a block chain.
In this embodiment, it should be emphasized that, in order to further ensure the privacy and security of the preferred report, the preferred report may also be stored in a node of a block chain.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
In the embodiment, the privacy and the safety of the preferred report can be ensured by storing the preferred report in the block chain, so that the information leakage is prevented.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, the processes of the embodiments of the methods described above can be included. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 3, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an automatic report generation apparatus, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 3, the automated report generating apparatus 300 according to this embodiment includes: an acquisition module 301, a prediction module 302, and a ranking module 303. Wherein:
an obtaining module 301, configured to obtain a report type of a target report and all stored report types, convert the report type into a tag vector through a feature engineering, and convert the report type into a feature vector;
in this embodiment, the target report is a data report that needs to be subjected to chart conversion, and when the target report is received, the report type of the target report, such as the categories of the financial category and the business category, is obtained. The report type is converted into a label vector through feature engineering. Specifically, the feature engineering is a data conversion mode for converting original data into initial parameter data which can be input by a model, and the feature engineering comprises feature data conversion modes such as linear normalization, category coding and a plurality of feature combinations. When the report type is a character string, the report type can be converted into a label vector through category coding, wherein the category coding comprises serial number coding, one-hot coding and binary coding, and the report type can be converted into the label vector through any one mode of sequence coding, one-hot coding and binary coding. Taking the one-hot coding as an example, the one-hot coding is to encode N states by using N-bit state registers using parameters expressed by 0, 1, and when a report type or a report type is obtained, the report type or the report type can be directly converted into a corresponding tag vector or a corresponding feature vector through the one-hot coding.
The report types comprise chart types and digital report types, and all the stored chart types and digital report types are obtained. The chart type and the digital report type can be converted into corresponding feature vectors by the conversion mode of the feature engineering, and the description is omitted here.
The prediction module 302 is configured to obtain a preset target prediction model, input the tag vector and the feature vector into the target prediction model, and obtain a prediction connection probability between reports through calculation of a gradient lifting decision tree and a logistic regression model in the target prediction model;
among them, the prediction module 302 includes:
the first calculation unit is used for inputting the label vector and the feature vector into a gradient lifting decision tree in the target prediction model, obtaining discrete features through leaf node output of the gradient lifting decision tree, and coding the discrete features to obtain coding features;
and the second calculation unit is used for carrying out weighted summation on the coding features to obtain a summation result, inputting the summation result to the logistic regression model, and calculating to obtain the prediction connection probability.
The acquisition unit is used for acquiring a preset basic prediction model, historical label data, historical characteristic data and historical interaction data;
and the training unit is used for training the basic prediction model according to the historical label data, the historical characteristic data and the historical interaction data to obtain the target prediction model.
Wherein, the training unit includes:
the first obtaining subunit is configured to select a first preset number of the historical label data, the historical feature data, and the historical interaction data as training data, and select a second preset number of the historical label data, the historical feature data, and the historical interaction data as verification data;
and the first verification subunit is used for training the basic prediction model according to the training data to obtain a model to be optimized, verifying the model to be optimized according to the verification data, and determining the model to be optimized as the target prediction model when the verification passing rate of the model to be optimized on the verification data is greater than or equal to a preset threshold value.
The first adjusting subunit is configured to, when the verification passing rate of the model to be optimized for the verification data is smaller than the preset threshold, obtain a preset loss function, adjust the parameter size of the model to be optimized according to the loss function, and when the loss function converges, determine that parameter adjustment of the model to be optimized is completed, so as to obtain a model to be optimized, of which the parameter adjustment is completed;
and the second verification subunit is used for verifying the model to be optimized after the parameter adjustment according to the verification data, and determining the model to be optimized after the parameter adjustment as the target prediction model when the verification passing rate of the model to be optimized after the parameter adjustment on the verification data is greater than or equal to the preset threshold value.
Wherein, the first adjustment subunit includes:
the second obtaining subunit is configured to obtain a prediction result obtained by calculating historical label data and historical feature data in the training data by the model to be optimized;
and the second adjusting subunit is used for calculating a loss value of the prediction result and the historical interaction data according to the loss function, acquiring a preset parameter adjusting instruction corresponding to the loss value, and adjusting the parameter of the model to be optimized according to the preset parameter adjusting instruction.
In this embodiment, a preset target prediction model is obtained, where the target prediction model includes a feature input layer, a decision tree processing layer and a classification layer, the decision tree processing layer is a gradient lifting decision tree structure, the classification layer is a logistic regression model structure, and an output result of a previous layer is input data of a next layer. When the label vector and the feature vector are obtained, the label vector and the feature vector are used as input data of the target prediction model and are input into the target prediction model. The target prediction model is obtained by training a basic prediction model, and the basic prediction model and the target prediction model adopt the same structure but have different parameters. Pre-collecting a plurality of groups of historical label data, historical characteristic data and historical interaction data to train a basic prediction model; and adjusting parameters of the basic prediction model according to each training result, wherein each parameter adjustment can be specifically determined according to the training result and the corresponding preset parameter adjustment instruction, and different training results correspond to different preset parameter adjustment instructions. The training result can be represented by a loss value of a prediction result and historical interactive data calculated by a basic prediction model, the historical label data is a historical stored report type label, the historical characteristic data is historical stored report type data, and the historical interactive data is joint data of reports in each report type and the report type. And when the verification passing rate of the model after the parameter adjustment on the preset verification data is greater than or equal to a preset threshold value, determining the model after the parameter adjustment as a target detection model.
And when the target prediction model is obtained, calculating the label vector and the feature vector through a decision tree processing layer and a classification layer, and finally outputting to obtain the prediction connection probability between each report corresponding to the current target report. The predicted connection probability refers to a probability value of another report appearing after each report, such as a probability value of a report B appearing after a report A, and a probability value of a report C appearing after a report B. And when the predicted connection probabilities among all reports are obtained, selecting the report corresponding to the predicted connection probability with the maximum report probability value as the next connection report of the current report. For example, if the probability value of the report B appearing after the report A is 0.5, and the probability value of the report C appearing after the report A is 0.8, the report C corresponding to 0.8 is selected as the next linked report of the current report A.
And the sorting module 303 is configured to perform predictive sorting on the report of the target report according to the predictive link probability to obtain a sorting result, and match the report content in the target report with the report according to the sorting result to obtain an optimal report of the target report.
In this embodiment, when the predicted join probability is obtained, the reports of the target report are sorted according to the predicted join probability to obtain a sorting result, where the sorting result is the arrangement order of each report. For example, the predicted join probability of the report B to the report a is the largest, the report B is joined after the report a, the predicted join probability of the report C to the report B is the largest, the report C is joined after the report B, and the final obtained sorting result is A, B, C. And after the sequencing result is obtained, matching the corresponding report with the content of the report according to the sequencing result, and finally obtaining the optimal report of the target report.
The automatic report generating device provided by this embodiment further includes:
and the storage module is used for storing the preferred report in a block chain.
In this embodiment, it should be emphasized that, in order to further ensure the privacy and security of the preferred report, the preferred report may also be stored in a node of a block chain.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The automatic report generation device provided by the embodiment realizes the automatic generation of the data report, improves the report generation efficiency, and further realizes the intelligent visualization of data.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 4, fig. 4 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 6 comprises a memory 61, a processor 62, a network interface 63 communicatively connected to each other via a system bus. It is noted that only a computer device 6 having components 61-63 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 61 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 61 may be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 6. Of course, the memory 61 may also comprise both an internal storage unit of the computer device 6 and an external storage device thereof. In this embodiment, the memory 61 is generally used for storing an operating system installed on the computer device 6 and various application software, such as computer readable instructions of an automated report generation method. Further, the memory 61 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 62 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 62 is typically used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is configured to execute computer readable instructions or process data stored in the memory 61, for example, execute computer readable instructions of the automated report generation method.
The network interface 63 may comprise a wireless network interface or a wired network interface, and the network interface 63 is typically used for establishing a communication connection between the computer device 6 and other electronic devices.
The computer equipment provided by the embodiment realizes the automatic generation of the data report, improves the report generation efficiency, and further realizes the intelligent visualization of data.
The present application further provides another embodiment, which is to provide a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the automated report generation method as described above.
The computer-readable storage medium provided by the embodiment realizes automatic generation of the data report, improves report generation efficiency, and further realizes intelligent visualization of data.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.
Claims (10)
1. An automatic report generation method is characterized by comprising the following steps:
acquiring a report type of a target report and all stored report types, converting the report type into a label vector through a feature engineering, and converting the report type into a feature vector;
acquiring a preset target prediction model, inputting the label vector and the feature vector into the target prediction model, and calculating by a gradient lifting decision tree and a logistic regression model in the target prediction model to obtain the prediction connection probability between reports;
and predicting and sequencing the report forms of the target report according to the predicted connection probability to obtain a sequencing result, and matching the report content in the target report with the report forms according to the sequencing result to obtain an optimal report form of the target report.
2. The automated report generation method according to claim 1, wherein the step of inputting the label vector and the feature vector into the target prediction model and calculating the prediction join probability between each report through a gradient boosting decision tree and a logistic regression model in the target prediction model specifically comprises:
inputting the label vector and the feature vector into a gradient lifting decision tree in the target prediction model, outputting through leaf nodes of the gradient lifting decision tree to obtain discrete features, and coding the discrete features to obtain coding features;
and carrying out weighted summation on the coding features to obtain a summation result, inputting the summation result to the logistic regression model, and calculating to obtain the prediction connection probability.
3. The automated report generation method according to claim 1, wherein the step of obtaining a preset target prediction model specifically comprises:
acquiring a preset basic prediction model, historical label data, historical characteristic data and historical interaction data;
and training the basic prediction model according to the historical label data, the historical characteristic data and the historical interaction data to obtain the target prediction model.
4. The automated report generation method according to claim 3, wherein the step of training the basic prediction model according to the historical label data, the historical feature data and the historical interaction data to obtain the target prediction model specifically comprises:
selecting a first preset number of the historical label data, the historical characteristic data and the historical interaction data as training data, and selecting a second preset number of the historical label data, the historical characteristic data and the historical interaction data as verification data;
training the basic prediction model according to the training data to obtain a model to be optimized, verifying the model to be optimized according to the verification data, and determining the model to be optimized as the target prediction model when the verification passing rate of the model to be optimized on the verification data is greater than or equal to a preset threshold value.
5. The automated report generation method according to claim 4, further comprising, after the step of verifying the model to be optimized according to the verification data:
when the verification passing rate of the model to be optimized on the verification data is smaller than the preset threshold value, acquiring a preset loss function, adjusting the parameter size of the model to be optimized according to the loss function, and when the loss function is converged, determining that the parameter adjustment of the model to be optimized is completed, so as to obtain the model to be optimized with the parameter adjustment completed;
and verifying the model to be optimized after the parameter adjustment according to the verification data, and determining the model to be optimized after the parameter adjustment as the target prediction model when the verification passing rate of the model to be optimized after the parameter adjustment on the verification data is greater than or equal to the preset threshold value.
6. The automated report generation method according to claim 5, wherein the step of adjusting the parameter size of the model to be optimized according to the loss function specifically comprises:
obtaining a prediction result obtained by calculating historical label data and historical characteristic data in the training data by the model to be optimized;
calculating a loss value of the prediction result and the historical interaction data according to the loss function, obtaining a preset parameter adjusting instruction corresponding to the loss value, and adjusting the parameter of the model to be optimized according to the preset parameter adjusting instruction.
7. The automated report generation method according to claim 1, further comprising, after the step of obtaining a preferred report for the target report:
and storing the preferred report in a block chain.
8. An automated report generation apparatus, comprising:
the acquisition module is used for acquiring the report type of a target report and all the stored report types, converting the report type into a label vector through a feature engineering, and converting the report type into a feature vector;
the prediction module is used for acquiring a preset target prediction model, inputting the label vector and the feature vector into the target prediction model, and calculating through a gradient lifting decision tree and a logistic regression model in the target prediction model to obtain the prediction connection probability between reports;
and the sequencing module is used for predicting and sequencing the report of the target report according to the predicted connection probability to obtain a sequencing result, and matching the report content in the target report with the report according to the sequencing result to obtain an optimal report of the target report.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor that when executed performs the steps of the automated report generation method according to any of claims 1 to 7.
10. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the automated report generation method according to any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110650664.2A CN113283222B (en) | 2021-06-11 | 2021-06-11 | Automatic report generation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110650664.2A CN113283222B (en) | 2021-06-11 | 2021-06-11 | Automatic report generation method and device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113283222A true CN113283222A (en) | 2021-08-20 |
CN113283222B CN113283222B (en) | 2021-10-08 |
Family
ID=77284233
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110650664.2A Active CN113283222B (en) | 2021-06-11 | 2021-06-11 | Automatic report generation method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113283222B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113643522A (en) * | 2021-08-31 | 2021-11-12 | 中国银行股份有限公司 | Alarm prediction method, device, equipment and storage medium |
CN113836132A (en) * | 2021-11-29 | 2021-12-24 | 中航金网(北京)电子商务有限公司 | Method and device for checking multi-end report forms |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180114131A1 (en) * | 2016-10-20 | 2018-04-26 | Micron Technology, Inc. | Boolean satisfiability |
CN108733752A (en) * | 2018-04-09 | 2018-11-02 | 北京橙立方软件技术有限公司 | Autoreport storage method and system |
WO2018207973A1 (en) * | 2017-05-12 | 2018-11-15 | 한국전력공사 | System and method for automatic diagnosis of power generation facility |
CN109800333A (en) * | 2019-01-02 | 2019-05-24 | 平安科技(深圳)有限公司 | Report form generation method, device and computer equipment based on machine learning |
CN110008470A (en) * | 2019-03-19 | 2019-07-12 | 阿里巴巴集团控股有限公司 | The sensibility stage division and device of report |
CN111190946A (en) * | 2019-12-10 | 2020-05-22 | 平安医疗健康管理股份有限公司 | Report generation method and device, computer equipment and storage medium |
CN111611784A (en) * | 2020-04-29 | 2020-09-01 | 平安科技(深圳)有限公司 | Report generation method and device, terminal equipment and storage medium |
CN111881158A (en) * | 2020-07-31 | 2020-11-03 | 平安国际融资租赁有限公司 | Management report data processing method and device, computer system and readable storage medium |
CN112084752A (en) * | 2020-09-08 | 2020-12-15 | 中国平安财产保险股份有限公司 | Statement marking method, device, equipment and storage medium based on natural language |
CN112800036A (en) * | 2020-12-30 | 2021-05-14 | 银盛通信有限公司 | Report analysis chart automatic generation and display method and system |
CN112884534A (en) * | 2021-01-26 | 2021-06-01 | 中通诚资产评估有限公司 | Income method valuation model |
-
2021
- 2021-06-11 CN CN202110650664.2A patent/CN113283222B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180114131A1 (en) * | 2016-10-20 | 2018-04-26 | Micron Technology, Inc. | Boolean satisfiability |
WO2018207973A1 (en) * | 2017-05-12 | 2018-11-15 | 한국전력공사 | System and method for automatic diagnosis of power generation facility |
CN108733752A (en) * | 2018-04-09 | 2018-11-02 | 北京橙立方软件技术有限公司 | Autoreport storage method and system |
CN109800333A (en) * | 2019-01-02 | 2019-05-24 | 平安科技(深圳)有限公司 | Report form generation method, device and computer equipment based on machine learning |
CN110008470A (en) * | 2019-03-19 | 2019-07-12 | 阿里巴巴集团控股有限公司 | The sensibility stage division and device of report |
CN111190946A (en) * | 2019-12-10 | 2020-05-22 | 平安医疗健康管理股份有限公司 | Report generation method and device, computer equipment and storage medium |
CN111611784A (en) * | 2020-04-29 | 2020-09-01 | 平安科技(深圳)有限公司 | Report generation method and device, terminal equipment and storage medium |
CN111881158A (en) * | 2020-07-31 | 2020-11-03 | 平安国际融资租赁有限公司 | Management report data processing method and device, computer system and readable storage medium |
CN112084752A (en) * | 2020-09-08 | 2020-12-15 | 中国平安财产保险股份有限公司 | Statement marking method, device, equipment and storage medium based on natural language |
CN112800036A (en) * | 2020-12-30 | 2021-05-14 | 银盛通信有限公司 | Report analysis chart automatic generation and display method and system |
CN112884534A (en) * | 2021-01-26 | 2021-06-01 | 中通诚资产评估有限公司 | Income method valuation model |
Non-Patent Citations (3)
Title |
---|
CHANGHUN HYUN;HYEYOUNG PARK: ""Image Recommendation for Automatic Report Generation using Semantic Similarity"", 《2019 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE IN INFORMATION AND COMMUNICATION (ICAIIC)》 * |
冯文堂;王纪梅: ""报表自动生成模型"", 《计算机***应用》 * |
靳庆泽;张穗雨: ""上汽集团财务报表分析及报表预测——基于灰色预测模型的分析"", 《山西农经》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113643522A (en) * | 2021-08-31 | 2021-11-12 | 中国银行股份有限公司 | Alarm prediction method, device, equipment and storage medium |
CN113836132A (en) * | 2021-11-29 | 2021-12-24 | 中航金网(北京)电子商务有限公司 | Method and device for checking multi-end report forms |
Also Published As
Publication number | Publication date |
---|---|
CN113283222B (en) | 2021-10-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112084383A (en) | Information recommendation method, device and equipment based on knowledge graph and storage medium | |
CN112307472B (en) | Abnormal user identification method and device based on intelligent decision and computer equipment | |
CN113127633B (en) | Intelligent conference management method and device, computer equipment and storage medium | |
CN113326991B (en) | Automatic authorization method, device, computer equipment and storage medium | |
CN113283222B (en) | Automatic report generation method and device, computer equipment and storage medium | |
CN112528029A (en) | Text classification model processing method and device, computer equipment and storage medium | |
CN112084752B (en) | Sentence marking method, device, equipment and storage medium based on natural language | |
CN112686301A (en) | Data annotation method based on cross validation and related equipment | |
CN112365202B (en) | Method for screening evaluation factors of multi-target object and related equipment thereof | |
CN112182118B (en) | Target object prediction method based on multiple data sources and related equipment thereof | |
CN112529477A (en) | Credit evaluation variable screening method, device, computer equipment and storage medium | |
CN115329876A (en) | Equipment fault processing method and device, computer equipment and storage medium | |
CN114398477A (en) | Policy recommendation method based on knowledge graph and related equipment thereof | |
CN113052262A (en) | Form generation method and device, computer equipment and storage medium | |
CN113947095A (en) | Multilingual text translation method and device, computer equipment and storage medium | |
CN114493255A (en) | Enterprise abnormity monitoring method based on knowledge graph and related equipment thereof | |
CN112308173A (en) | Multi-target object evaluation method based on multi-evaluation factor fusion and related equipment thereof | |
CN114359582B (en) | Small sample feature extraction method based on neural network and related equipment | |
CN112036483A (en) | Object prediction classification method and device based on AutoML, computer equipment and storage medium | |
CN114358023A (en) | Intelligent question-answer recall method and device, computer equipment and storage medium | |
CN112598039B (en) | Method for obtaining positive samples in NLP (non-linear liquid) classification field and related equipment | |
CN112417886A (en) | Intention entity information extraction method and device, computer equipment and storage medium | |
CN116402625B (en) | Customer evaluation method, apparatus, computer device and storage medium | |
CN116186295B (en) | Attention-based knowledge graph link prediction method, attention-based knowledge graph link prediction device, attention-based knowledge graph link prediction equipment and attention-based knowledge graph link prediction medium | |
CN112434746A (en) | Pre-labeling method based on hierarchical transfer learning and related equipment thereof |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |