Insertion chart data processing method and system based on prediction algorithm

Abstract

The invention discloses an inserted chart data processing method and system based on a prediction algorithm. The method comprises the steps that to-be-converted chart original data and inserted document data input by a target user are acquired; on the basis of a data prediction algorithm, according to user historical data of the target user, predicting data relation parameters corresponding to the chart original data; based on a dynamic programming algorithm, according to the inserted document data and the data relation parameters, determining an object composition strategy corresponding to the original chart data; generating chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library; the chart object data is used for being inserted into the inserted document data. Visibly, according to the method, the more reasonable and visual chart object can be determined by means of the prediction algorithm and the dynamic planning algorithm, so that the success rate and the accuracy of chart data conversion are improved, and more intelligent and automatic chart insertion service is provided for a user.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for processing inserted chart data based on a prediction algorithm. Background Art

[0002] With the development of visualization technology, the demand for data visualization is getting higher and higher. Visualization can make data more intuitive to users and clearly show the changes or relative relationships in the data. Therefore, institutions and enterprises have also begun to improve data visualization display technology. For example, some enterprises have begun to provide programming libraries that can automatically convert visual charts. However, when processing data visualization chart display, the existing technology still relies heavily on the normalization of user input data and the content in its own preset visualization object library. Most of them can only realize chart conversion based on preset simple conversion rules. The degree of intelligence is general and the conversion effect is lacking. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for processing inserted chart data based on a prediction algorithm, which can determine more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for processing inserted chart data based on a prediction algorithm, the method comprising: Obtain the original chart data to be converted and the inserted document data input by the target user; Based on the data prediction algorithm, predict the data relationship parameters corresponding to the original data of the chart according to the user history data of the target user; Based on a dynamic programming algorithm, determining an object composition strategy corresponding to the original data of the chart according to the inserted document data and the data relationship parameters; According to the object composition strategy and at least one preset chart object library, chart object data corresponding to the chart original data is generated; the chart object data is used to be inserted into the insertion document data.

[0005] As an optional embodiment, in the first aspect of the present invention, the data relationship parameters include data types, data type quantities, data type relationships, data value relationships and data relationship themes corresponding to different data parts of the original data of the chart.

[0006] As an optional implementation, in the first aspect of the present invention, the predicting of the data relationship parameters corresponding to the original data of the chart based on the data prediction algorithm according to the user history data of the target user includes: Inputting the original data of the chart into a trained data normative prediction model to obtain corresponding normative parameters; the data normative prediction model is trained by a training data set including a plurality of training chart original data and corresponding data normative expression annotations; Determine whether the normative parameter is greater than a preset parameter threshold and obtain a determination result; When the judgment result is yes, the original data of the chart is input into a trained data arrangement type prediction neural network to obtain a target data arrangement type corresponding to the original data of the chart; When the judgment result is no, determining a plurality of preference data arrangement types corresponding to the target user according to the historical chart selection record of the target user; Determining a target data arrangement type corresponding to the chart original data from a plurality of preference data arrangement types according to a data template corresponding to the preference data arrangement type and the chart original data; According to the data classification corresponding rule corresponding to the target data arrangement type, the data parts of the original data of the chart are classified and the relationship is matched to obtain the data relationship parameters corresponding to the original data of the chart.

[0007] As an optional implementation, in the first aspect of the present invention, the step of selecting a record of the target user's history chart to determine a plurality of preference data arrangement types corresponding to the target user includes: Obtaining the historical chart selection record of the target user; For each preset data arrangement type, count the proportion of records corresponding to the data arrangement type in the historical chart selection records; Sorting all the data arrangement types from large to small according to the record ratio to obtain a type sequence; The data arrangement types of the first preset number of the type sequence and the record ratio of which is greater than a preset ratio threshold are screened out to obtain a plurality of preferred data arrangement types corresponding to the target user.

[0008] As an optional implementation, in the first aspect of the present invention, determining the target data arrangement type corresponding to the chart original data from a plurality of preference data arrangement types according to the data template corresponding to the preference data arrangement type and the chart original data, comprises: For each of the preference data arrangement types, determining a data template corresponding to the preference data arrangement type from a preset arrangement type data template library; Calculating the data similarity between the preference data arrangement type and the original data of the chart; Calculating a weighted average value between the data similarity and the record proportion corresponding to the preference data arrangement type to obtain a type priority parameter corresponding to the preference data arrangement type; The preferred data arrangement type with the highest type priority parameter is determined as the target data arrangement type corresponding to the original data of the chart.

[0009] As an optional implementation, in the first aspect of the present invention, the object composition strategy corresponding to the original chart data is determined based on the dynamic programming algorithm according to the inserted document data and the data relationship parameters, including: Determine document parameters corresponding to the inserted document data; the document parameters include document subject and document type; For each preset candidate image-text coherence prediction model, obtaining a training data set corresponding to the candidate image-text coherence prediction model; Calculating parameter similarity between document parameter annotations of training document data in the training data set and the document parameters; Determining the candidate image-text coherence prediction model with the highest parameter similarity as the target image-text coherence prediction model; Determining the objective function and restriction conditions related to the coherence of the inserted image and text according to the data relationship parameters and the target image and text coherence prediction model; Based on a dynamic programming algorithm, an iterative operation of the object composition scheme is performed according to the objective function and the constraint conditions until an optimal object composition scheme is obtained, so as to determine an object composition strategy corresponding to the original data of the chart; the object composition strategy includes chart types, chart dimensions, chart icon types, chart drawing parameters and chart display positions corresponding to different data parts of the original data of the chart.

[0010] As an optional implementation, in the first aspect of the present invention, the total number of chart types corresponding to all data parts of the original data of the chart in the object composition scheme included in the objective function is minimized; and the restriction conditions include: The object composition scheme is obtained by inputting the original chart data and the data relationship parameters into a preset object prediction neural network for output; the object prediction neural network is trained by a training data set including a plurality of training chart original data and corresponding data relationship parameter annotations and chart object composition scheme annotations; The output prediction probability of the object composition scheme in the object prediction neural network is greater than a preset probability threshold; The image-text coherence corresponding to the object composition scheme is greater than a preset coherence threshold; the image-text coherence is obtained by inputting the document data within a preset data volume before and after the object composition scheme and the insertion position of the chart inserted into the document data into the target image-text coherence prediction model for prediction; the target image-text coherence prediction model is obtained by training a training data set including a plurality of training image-text document data and corresponding image-text coherence annotations.

[0011] As an optional implementation, in the first aspect of the present invention, generating the chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library includes: For each preset chart object library, a corresponding chart generation instruction is generated according to the object composition strategy based on the code rules corresponding to the chart object library; the chart object library is built based on Web Component technology or echart technology; Sending the chart generation instruction to the communication interface corresponding to the chart object library to obtain the candidate chart object data output by the chart object library; Determine the chart completeness corresponding to the candidate chart object data based on a data object completeness algorithm; Inputting the candidate chart object data and the document data within a preset data amount before and after the chart insertion position of the inserted document data into the target graphic-text coherence prediction model to obtain the coherence parameter corresponding to the candidate chart data; Calculating the product of the chart completeness and the coherence parameter to obtain a chart priority parameter corresponding to the candidate chart data; The candidate chart object data with the highest chart priority parameter among all the candidate chart object data output by all the chart object libraries is determined as the chart object data corresponding to the chart original data.

[0012] A second aspect of an embodiment of the present invention discloses an insertion chart data processing system based on a prediction algorithm, the system comprising: The acquisition module is used to acquire the original chart data to be converted and the inserted document data input by the target user; A prediction module, configured to predict data relationship parameters corresponding to the original data of the chart based on a data prediction algorithm and according to the user history data of the target user; A determination module, configured to determine an object composition strategy corresponding to the original data of the chart based on a dynamic programming algorithm according to the inserted document data and the data relationship parameters; A generation module is used to generate chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library; the chart object data is used to be inserted into the insertion document data.

[0013] As an optional embodiment, in the second aspect of the present invention, the data relationship parameters include data types, data type quantities, data type relationships, data value relationships and data relationship themes corresponding to different data parts of the original data of the chart.

[0014] As an optional implementation, in the second aspect of the present invention, the prediction module predicts the data relationship parameters corresponding to the original data of the chart based on the data prediction algorithm and the user history data of the target user in a specific manner, including: Inputting the original data of the chart into a trained data normative prediction model to obtain corresponding normative parameters; the data normative prediction model is trained by a training data set including a plurality of training chart original data and corresponding data normative expression annotations; Determine whether the normative parameter is greater than a preset parameter threshold and obtain a determination result; When the judgment result is yes, the original data of the chart is input into a trained data arrangement type prediction neural network to obtain a target data arrangement type corresponding to the original data of the chart; When the judgment result is no, determining a plurality of preference data arrangement types corresponding to the target user according to the historical chart selection record of the target user; Determining a target data arrangement type corresponding to the chart original data from a plurality of preference data arrangement types according to a data template corresponding to the preference data arrangement type and the chart original data; According to the data classification corresponding rule corresponding to the target data arrangement type, the data parts of the original data of the chart are classified and the relationship is matched to obtain the data relationship parameters corresponding to the original data of the chart.

[0015] As an optional implementation, in the second aspect of the present invention, the prediction module determines the specific manner of arranging the multiple preference data types corresponding to the target user according to the historical chart selection record of the target user, including: Obtaining the historical chart selection record of the target user; For each preset data arrangement type, count the proportion of records corresponding to the data arrangement type in the historical chart selection records; Sorting all the data arrangement types from large to small according to the record ratio to obtain a type sequence; The data arrangement types of the first preset number of the type sequence and the record ratio of which is greater than a preset ratio threshold are screened out to obtain a plurality of preferred data arrangement types corresponding to the target user.

[0016] As an optional implementation, in the second aspect of the present invention, the prediction module determines the specific manner of the target data arrangement type corresponding to the original data of the chart from a plurality of preference data arrangement types according to the data template corresponding to the preference data arrangement type and the original data of the chart, including: For each of the preference data arrangement types, determining a data template corresponding to the preference data arrangement type from a preset arrangement type data template library; Calculating the data similarity between the preference data arrangement type and the original data of the chart; Calculating a weighted average value between the data similarity and the record proportion corresponding to the preference data arrangement type to obtain a type priority parameter corresponding to the preference data arrangement type; The preferred data arrangement type with the highest type priority parameter is determined as the target data arrangement type corresponding to the original data of the chart.

[0017] As an optional implementation, in the second aspect of the present invention, the determination module determines the specific manner of the object composition strategy corresponding to the original chart data based on the inserted document data and the data relationship parameters based on a dynamic programming algorithm, including: Determine document parameters corresponding to the inserted document data; the document parameters include document subject and document type; For each preset candidate image-text coherence prediction model, obtaining a training data set corresponding to the candidate image-text coherence prediction model; Calculating parameter similarity between document parameter annotations of training document data in the training data set and the document parameters; Determining the candidate image-text coherence prediction model with the highest parameter similarity as the target image-text coherence prediction model; Determining the objective function and restriction conditions related to the coherence of the inserted image and text according to the data relationship parameters and the target image and text coherence prediction model; Based on a dynamic programming algorithm, an iterative operation of the object composition scheme is performed according to the objective function and the constraint conditions until an optimal object composition scheme is obtained, so as to determine an object composition strategy corresponding to the original data of the chart; the object composition strategy includes chart types, chart dimensions, chart icon types, chart drawing parameters and chart display positions corresponding to different data parts of the original data of the chart.

[0018] As an optional implementation, in the second aspect of the present invention, the total number of chart types corresponding to all data parts of the original data of the chart in the object composition scheme included in the objective function is minimized; and the restriction conditions include: The object composition scheme is obtained by inputting the original chart data and the data relationship parameters into a preset object prediction neural network for output; the object prediction neural network is trained by a training data set including a plurality of training chart original data and corresponding data relationship parameter annotations and chart object composition scheme annotations; The output prediction probability of the object composition scheme in the object prediction neural network is greater than a preset probability threshold; The image-text coherence corresponding to the object composition scheme is greater than a preset coherence threshold; the image-text coherence is obtained by inputting the document data within a preset data volume before and after the object composition scheme and the insertion position of the chart inserted into the document data into the target image-text coherence prediction model for prediction; the target image-text coherence prediction model is obtained by training a training data set including a plurality of training image-text document data and corresponding image-text coherence annotations.

[0019] As an optional implementation, in the second aspect of the present invention, the specific manner in which the generating module generates the chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library includes: For each preset chart object library, a corresponding chart generation instruction is generated according to the object composition strategy based on the code rules corresponding to the chart object library; the chart object library is built based on Web Component technology or echart technology; Sending the chart generation instruction to the communication interface corresponding to the chart object library to obtain the candidate chart object data output by the chart object library; Determine the chart completeness corresponding to the candidate chart object data based on a data object completeness algorithm; Inputting the candidate chart object data and the document data within a preset data amount before and after the chart insertion position of the inserted document data into the target graphic-text coherence prediction model to obtain the coherence parameter corresponding to the candidate chart data; Calculating the product of the chart completeness and the coherence parameter to obtain a chart priority parameter corresponding to the candidate chart data; The candidate chart object data with the highest chart priority parameter among all the candidate chart object data output by all the chart object libraries is determined as the chart object data corresponding to the chart original data.

[0020] The third aspect of the present invention discloses another insertion chart data processing system based on a prediction algorithm, the system comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the method for processing inserted chart data based on the prediction algorithm disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in the insertion chart data processing method based on the prediction algorithm disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can determine the data relationship parameters corresponding to the original data of the chart based on the data prediction algorithm, and then determine the object composition strategy corresponding to the original data of the chart according to the inserted document data and the data relationship parameters, so as to finally generate chart object data corresponding to the original data of the chart based on at least one preset chart object library to be inserted into the inserted document data, so as to determine more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a method for processing inserted chart data based on a prediction algorithm disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural schematic diagram of an insertion chart data processing system based on a prediction algorithm disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural schematic diagram of another insertion chart data processing system based on a prediction algorithm disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a method and system for processing inserted chart data based on a prediction algorithm, which can determine data relationship parameters corresponding to the original chart data based on the data prediction algorithm, and then determine the object composition strategy corresponding to the original chart data according to the inserted document data and the data relationship parameters, so as to finally generate chart object data corresponding to the original chart data based on at least one preset chart object library to be inserted into the inserted document data, so as to determine a more reasonable and intuitive chart object with the help of a prediction algorithm and a dynamic programming algorithm, so as to improve the success rate and accuracy of chart data conversion, and provide users with a more intelligent and automatic chart insertion service. The following are detailed descriptions.

[0031] Embodiment 1 See also Figure 1 , Figure 1 1 is a flow chart of a method for processing inserted chart data based on a prediction algorithm disclosed in an embodiment of the present invention. Figure 1 The described insertion chart data processing method based on the prediction algorithm can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1As shown, the insertion chart data processing method based on the prediction algorithm may include the following operations: 101. Obtain the original chart data to be converted and the inserted document data input by the target user.

[0032] 102. Based on the data prediction algorithm, according to the user history data of the target user, the data relationship parameters corresponding to the original data of the chart are predicted. 103. Based on the dynamic programming algorithm, the object composition strategy corresponding to the original data of the chart is determined according to the inserted document data and data relationship parameters. 104. Generate chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library.

[0033] Optionally, chart object data is used to insert into the insert document data.

[0034] It can be seen that the above-mentioned embodiment of the invention can determine the data relationship parameters corresponding to the original data of the chart based on the data prediction algorithm, and then determine the object composition strategy corresponding to the original data of the chart according to the inserted document data and the data relationship parameters, so as to finally generate chart object data corresponding to the original data of the chart based on at least one preset chart object library to be inserted into the inserted document data, so that more reasonable and intuitive chart objects can be determined with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0035] As an optional embodiment, in the above steps, the data relationship parameters include data types, data type quantities, data type relationships, data value relationships and data relationship themes corresponding to different data parts of the original data of the chart.

[0036] It can be seen that through the above optional embodiments, the content of the data relationship parameters is limited to comprehensively characterize the data relationship characteristics in the original data of the chart, facilitate the subsequent determination of object strategies and the generation of chart objects, and assist in determining more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0037] As an optional embodiment, in the above steps, based on the data prediction algorithm, according to the user history data of the target user, predicting the data relationship parameters corresponding to the original data of the chart includes: Inputting the original data of the chart into the trained data normative prediction model to obtain corresponding normative parameters; optionally, the data normative prediction model is trained by a training data set including a plurality of training chart original data and corresponding data normative expression annotations; Determine whether the normative parameter is greater than a preset parameter threshold and obtain a determination result; When the judgment result is yes, the original data of the chart is input into the trained data arrangement type prediction neural network to obtain the target data arrangement type corresponding to the original data of the chart; When the judgment result is no, a plurality of preference data arrangement types corresponding to the target user are determined according to the historical chart selection record of the target user; Determining a target data arrangement type corresponding to the chart original data from a plurality of preference data arrangement types according to a data template corresponding to the preference data arrangement type and the chart original data; According to the data classification corresponding rules corresponding to the target data arrangement type, the data parts of the original data of the chart are classified and the relationship correspondence is performed to obtain the data relationship parameters corresponding to the original data of the chart.

[0038] It can be seen that through the above optional embodiments, the standardization of the original data can be judged first based on the prediction model of the data annotation standardization, and the arrangement type prediction can be directly performed using the neural network when it is standardized. When it is not standardized, multiple preferred data arrangement types are determined based on the user's historical chart selection records, and then the target data arrangement type is screened out to classify the data part of the original data of the chart and correspond the relationships to obtain data relationship parameters, which is convenient for the subsequent determination of object strategies and the generation of chart objects, and assists in determining more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0039] As an optional embodiment, in the above step, selecting records according to the historical chart of the target user to determine multiple preference data arrangement types corresponding to the target user includes: Get the historical chart selection records of the target user; For each preset data arrangement type, the proportion of records corresponding to the data arrangement type in the selected records of the statistical history chart; Sort all data arrangement types from large to small according to the record ratio to obtain a type sequence; The data arrangement types of the first preset number of type sequences and whose record ratio is greater than a preset ratio threshold are screened out to obtain a plurality of preferred data arrangement types corresponding to the target user.

[0040] It can be seen that through the above-mentioned optional embodiments, multiple preferred data arrangement types can be screened out based on the proportion of different data arrangement types in the historical chart selection records of the target user, so as to achieve more accurate determination of data relationship parameters in the subsequent process, facilitate the subsequent determination of object strategies and generation of chart objects, and assist in determining more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0041] As an optional embodiment, in the above step, determining the target data arrangement type corresponding to the original chart data from a plurality of preferred data arrangement types according to the data template corresponding to the preferred data arrangement type and the original chart data, includes: For each preference data arrangement type, determining a data template corresponding to the preference data arrangement type from a preset arrangement type data template library; Calculate the data similarity between the preference data arrangement type and the original data of the chart; Calculate the weighted average value between the data similarity and the record proportion corresponding to the preferred data arrangement type to obtain the type priority parameter corresponding to the preferred data arrangement type; The preferred data arrangement type with the highest type priority parameter is determined as the target data arrangement type corresponding to the original data of the chart.

[0042] It can be seen that through the above-mentioned optional embodiments, it is possible to obtain the target data arrangement type based on the similarity calculation between the data template corresponding to the preferred data arrangement type and the original data of the chart and the screening combined with the weighted calculation of the record ratio, so as to achieve more accurate determination of data relationship parameters, facilitate subsequent determination of object strategies and generation of chart objects, and assist in determining more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0043] As an optional embodiment, in the above steps, based on the dynamic programming algorithm, according to the inserted document data and the data relationship parameters, determining the object composition strategy corresponding to the original data of the chart includes: Determine document parameters corresponding to the inserted document data; optionally, the document parameters include document subject and document type; For each preset candidate image-text coherence prediction model, obtaining a training data set corresponding to the candidate image-text coherence prediction model; Calculate the parameter similarity between the document parameter annotations and the document parameters of the training document data in the training data set; The candidate image-text coherence prediction model with the highest parameter similarity is determined as the target image-text coherence prediction model; According to the data relationship parameters and the target image-text coherence prediction model, the objective function and restriction conditions related to the coherence of the inserted image-text are determined; Based on the dynamic programming algorithm, the object composition scheme is iterated according to the objective function and constraints until the optimal object composition scheme is obtained, so as to determine the object composition strategy corresponding to the original data of the chart; the object composition strategy includes chart types, chart dimensions, chart icon types, chart drawing parameters and chart display positions corresponding to different data parts of the original data of the chart.

[0044] It can be seen that through the above-mentioned optional embodiments, it is possible to determine the target image-text coherence prediction model based on the document subject and document type corresponding to the inserted document data, and based on this, determine the precise calculation objective function and restriction conditions related to the coherence of the inserted image and text to determine a more reasonable object strategy based on the dynamic programming algorithm, and assist in determining a more reasonable and intuitive chart object with the help of the prediction algorithm and the dynamic programming algorithm, so as to improve the success rate and accuracy of chart data conversion and provide users with a more intelligent and automatic chart insertion service.

[0045] As an optional embodiment, in the above steps, the total number of chart types corresponding to all data parts of the original chart data in the object composition scheme included in the objective function is minimized; the restriction conditions include: The object composition scheme is obtained by inputting the original chart data and data relationship parameters into a preset object prediction neural network for output; optionally, the object prediction neural network is obtained by training a training data set including a plurality of training chart original data and corresponding data relationship parameter annotations and chart object composition scheme annotations; The output prediction probability of the object composition scheme in the object prediction neural network is greater than a preset probability threshold; The image-text coherence corresponding to the object composition scheme is greater than a preset coherence threshold; optionally, the image-text coherence is obtained by inputting the object composition scheme and the document data within a preset data volume before and after the insertion position of the chart into the document data into a target image-text coherence prediction model for prediction; the target image-text coherence prediction model is trained by a training data set including a plurality of training image-text document data and corresponding image-text coherence annotations.

[0046] It can be seen that through the above optional embodiments, the contents of the objective function and the constraints are defined, so as to effectively limit the calculation convergence conditions of the dynamic programming algorithm based on the trained object prediction neural network and image-text coherence prediction, so as to calculate a more reasonable object strategy, and assist in determining a more reasonable and intuitive chart object with the help of the prediction algorithm and the dynamic programming algorithm, so as to improve the success rate and accuracy of chart data conversion, and provide users with a more intelligent and automatic chart insertion service.

[0047] As an optional embodiment, in the above steps, generating chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library includes: For each preset chart object library, a corresponding chart generation instruction is generated according to the object composition strategy based on the code rules corresponding to the chart object library; optionally, the chart object library is built based on Web Component technology or echart technology; Sending a chart generation instruction to a communication interface corresponding to the chart object library to obtain candidate chart object data output by the chart object library; Determine the chart integrity corresponding to the candidate chart object data based on the data object integrity algorithm; Inputting the candidate chart object data and the document data within a preset data amount before and after the chart insertion position of the inserted document data into the target graphic-text coherence prediction model to obtain the coherence parameter corresponding to the candidate chart data; Calculate the product of the chart completeness and coherence parameters to obtain the chart priority parameters corresponding to the candidate chart data; The candidate chart object data with the highest chart priority parameter among all the candidate chart object data output by all the chart object libraries is determined as the chart object data corresponding to the chart original data.

[0048] It can be seen that through the above-mentioned optional embodiments, after generating chart generation instructions corresponding to each chart object library based on code rules, the chart completeness and coherence parameters of the output candidate chart object data can be predicted to screen out the most suitable chart object data, and more reasonable and intuitive chart objects can be determined with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0049] Embodiment 2 See also Figure 2 , Figure 2 1 is a schematic diagram of a structure of a data processing system for inserting charts based on a prediction algorithm disclosed in an embodiment of the present invention. Figure 2The described insertion chart data processing system based on the prediction algorithm can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the insertion chart data processing system based on the prediction algorithm may include: The acquisition module 201 is used to acquire the original chart data to be converted and the insertion document data input by the target user.

[0050] The prediction module 202 is used to predict the data relationship parameters corresponding to the original data of the chart based on the data prediction algorithm and the user history data of the target user. The determination module 203 is used to determine the object composition strategy corresponding to the original data of the chart based on the dynamic programming algorithm according to the inserted document data and the data relationship parameters. The generating module 204 is used to generate chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library.

[0051] Optionally, chart object data is used to insert into the insert document data.

[0052] It can be seen that the above-mentioned embodiment of the invention can determine the data relationship parameters corresponding to the original data of the chart based on the data prediction algorithm, and then determine the object composition strategy corresponding to the original data of the chart according to the inserted document data and the data relationship parameters, so as to finally generate chart object data corresponding to the original data of the chart based on at least one preset chart object library to be inserted into the inserted document data, so that more reasonable and intuitive chart objects can be determined with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0053] As an optional embodiment, the data relationship parameters include data types, data type quantities, data type relationships, data value relationships, and data relationship themes corresponding to different data parts of the original data of the chart.

[0054] It can be seen that through the above optional embodiments, the content of the data relationship parameters is limited to comprehensively characterize the data relationship characteristics in the original data of the chart, facilitate the subsequent determination of object strategies and the generation of chart objects, and assist in determining more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0055] As an optional embodiment, the prediction module predicts the data relationship parameters corresponding to the original data of the chart based on the data prediction algorithm and the user history data of the target user, including: Inputting the original data of the chart into the trained data normative prediction model to obtain corresponding normative parameters; optionally, the data normative prediction model is trained by a training data set including a plurality of training chart original data and corresponding data normative expression annotations; Determine whether the normative parameter is greater than a preset parameter threshold and obtain a determination result; When the judgment result is yes, the original data of the chart is input into the trained data arrangement type prediction neural network to obtain the target data arrangement type corresponding to the original data of the chart; When the judgment result is no, a plurality of preference data arrangement types corresponding to the target user are determined according to the historical chart selection record of the target user; Determining a target data arrangement type corresponding to the chart original data from a plurality of preference data arrangement types according to a data template corresponding to the preference data arrangement type and the chart original data; According to the data classification corresponding rules corresponding to the target data arrangement type, the data parts of the original data of the chart are classified and the relationship correspondence is performed to obtain the data relationship parameters corresponding to the original data of the chart.

[0056] It can be seen that through the above optional embodiments, the standardization of the original data can be judged first based on the prediction model of the data annotation standardization, and the arrangement type prediction can be directly performed using the neural network when it is standardized. When it is not standardized, multiple preferred data arrangement types are determined based on the user's historical chart selection records, and then the target data arrangement type is screened out to classify the data part of the original data of the chart and correspond the relationships to obtain data relationship parameters, which is convenient for the subsequent determination of object strategies and the generation of chart objects, and assists in determining more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0057] As an optional embodiment, the prediction module selects records according to the historical chart of the target user to determine the specific manner of arranging the multiple preference data types corresponding to the target user, including: Get the historical chart selection records of the target user; For each preset data arrangement type, the proportion of records corresponding to the data arrangement type in the selected records of the statistical history chart; Sort all data arrangement types from large to small according to the record ratio to obtain a type sequence; The data arrangement types of the first preset number of type sequences and whose record ratio is greater than a preset ratio threshold are screened out to obtain a plurality of preferred data arrangement types corresponding to the target user.

[0058] It can be seen that through the above-mentioned optional embodiments, multiple preferred data arrangement types can be screened out based on the proportion of different data arrangement types in the historical chart selection records of the target user, so as to achieve more accurate determination of data relationship parameters in the subsequent process, facilitate the subsequent determination of object strategies and generation of chart objects, and assist in determining more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0059] As an optional embodiment, the prediction module determines the specific manner of the target data arrangement type corresponding to the original chart data from a plurality of preference data arrangement types according to the data template corresponding to the preference data arrangement type and the original chart data, including: For each preference data arrangement type, determining a data template corresponding to the preference data arrangement type from a preset arrangement type data template library; Calculate the data similarity between the preference data arrangement type and the original data of the chart; Calculate the weighted average value between the data similarity and the record proportion corresponding to the preferred data arrangement type to obtain the type priority parameter corresponding to the preferred data arrangement type; The preferred data arrangement type with the highest type priority parameter is determined as the target data arrangement type corresponding to the original data of the chart.

[0060] It can be seen that through the above-mentioned optional embodiments, it is possible to obtain the target data arrangement type based on the similarity calculation between the data template corresponding to the preferred data arrangement type and the original data of the chart and the screening combined with the weighted calculation of the record ratio, so as to achieve more accurate determination of data relationship parameters, facilitate subsequent determination of object strategies and generation of chart objects, and assist in determining more reasonable and intuitive chart objects with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0061] As an optional embodiment, the determination module determines the specific manner of the object composition strategy corresponding to the original data of the chart based on the dynamic programming algorithm and according to the inserted document data and the data relationship parameters, including: Determine document parameters corresponding to the inserted document data; optionally, the document parameters include document subject and document type; For each preset candidate image-text coherence prediction model, obtaining a training data set corresponding to the candidate image-text coherence prediction model; Calculate the parameter similarity between the document parameter annotations and the document parameters of the training document data in the training data set; The candidate image-text coherence prediction model with the highest parameter similarity is determined as the target image-text coherence prediction model; According to the data relationship parameters and the target image-text coherence prediction model, the objective function and restriction conditions related to the coherence of the inserted image-text are determined; Based on the dynamic programming algorithm, the object composition scheme is iterated according to the objective function and constraints until the optimal object composition scheme is obtained, so as to determine the object composition strategy corresponding to the original data of the chart; the object composition strategy includes chart types, chart dimensions, chart icon types, chart drawing parameters and chart display positions corresponding to different data parts of the original data of the chart.

[0062] It can be seen that through the above-mentioned optional embodiments, it is possible to determine the target image-text coherence prediction model based on the document subject and document type corresponding to the inserted document data, and based on this, determine the precise calculation objective function and restriction conditions related to the coherence of the inserted image and text to determine a more reasonable object strategy based on the dynamic programming algorithm, and assist in determining a more reasonable and intuitive chart object with the help of the prediction algorithm and the dynamic programming algorithm, so as to improve the success rate and accuracy of chart data conversion and provide users with a more intelligent and automatic chart insertion service.

[0063] As an optional embodiment, the total number of chart types corresponding to all data parts of the original chart data in the object composition scheme included in the objective function is minimized; the restriction conditions include: The object composition scheme is obtained by inputting the original chart data and data relationship parameters into a preset object prediction neural network for output; optionally, the object prediction neural network is obtained by training a training data set including a plurality of training chart original data and corresponding data relationship parameter annotations and chart object composition scheme annotations; The output prediction probability of the object composition scheme in the object prediction neural network is greater than a preset probability threshold; The image-text coherence corresponding to the object composition scheme is greater than a preset coherence threshold; optionally, the image-text coherence is obtained by inputting the object composition scheme and the document data within a preset data volume before and after the insertion position of the chart into the document data into a target image-text coherence prediction model for prediction; the target image-text coherence prediction model is trained by a training data set including a plurality of training image-text document data and corresponding image-text coherence annotations.

[0064] It can be seen that through the above optional embodiments, the contents of the objective function and the constraints are defined, so as to effectively limit the calculation convergence conditions of the dynamic programming algorithm based on the trained object prediction neural network and image-text coherence prediction, so as to calculate a more reasonable object strategy, and assist in determining a more reasonable and intuitive chart object with the help of the prediction algorithm and the dynamic programming algorithm, so as to improve the success rate and accuracy of chart data conversion, and provide users with a more intelligent and automatic chart insertion service.

[0065] As an optional embodiment, the specific manner in which the generating module generates the chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library includes: For each preset chart object library, a corresponding chart generation instruction is generated according to the object composition strategy based on the code rules corresponding to the chart object library; optionally, the chart object library is built based on Web Component technology or echart technology; Sending a chart generation instruction to a communication interface corresponding to the chart object library to obtain candidate chart object data output by the chart object library; Determine the chart integrity corresponding to the candidate chart object data based on the data object integrity algorithm; Inputting the candidate chart object data and the document data within a preset data amount before and after the chart insertion position of the inserted document data into the target graphic-text coherence prediction model to obtain the coherence parameter corresponding to the candidate chart data; Calculate the product of the chart completeness and coherence parameters to obtain the chart priority parameters corresponding to the candidate chart data; The candidate chart object data with the highest chart priority parameter among all the candidate chart object data output by all the chart object libraries is determined as the chart object data corresponding to the chart original data.

[0066] It can be seen that through the above-mentioned optional embodiments, after generating chart generation instructions corresponding to each chart object library based on code rules, the chart completeness and coherence parameters of the output candidate chart object data can be predicted to screen out the most suitable chart object data, and more reasonable and intuitive chart objects can be determined with the help of prediction algorithms and dynamic programming algorithms, so as to improve the success rate and accuracy of chart data conversion and provide users with more intelligent and automatic chart insertion services.

[0067] Embodiment 3 See also Figure 3 , Figure 3 It is another insertion chart data processing system based on a prediction algorithm disclosed in an embodiment of the present invention. Figure 3The described insertion chart data processing system based on the prediction algorithm is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the insertion chart data processing system based on the prediction algorithm may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the method for processing inserted chart data based on the prediction algorithm described in the first embodiment.

[0068] Embodiment 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method for processing inserted chart data based on a prediction algorithm described in the first embodiment.

[0069] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the method for processing inserted chart data based on a prediction algorithm described in the first embodiment.

[0070] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0072] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0073] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0074] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0077] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0078] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0079] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0081] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0082] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0083] Finally, it should be noted that the method and system for processing inserted chart data based on a prediction algorithm disclosed in the embodiment of the present invention disclose only the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for processing inserted chart data based on a prediction algorithm, characterized in that: The method comprises: Obtain the original chart data to be converted and the inserted document data input by the target user; Based on the data prediction algorithm, predict the data relationship parameters corresponding to the original data of the chart according to the user history data of the target user; Based on a dynamic programming algorithm, determining an object composition strategy corresponding to the original data of the chart according to the inserted document data and the data relationship parameters; According to the object composition strategy and at least one preset chart object library, chart object data corresponding to the chart original data is generated; the chart object data is used to be inserted into the insertion document data.

2. The method for processing inserted chart data based on prediction algorithm according to claim 1, characterized in that: The data relationship parameters include data types, data type quantities, data type relationships, data value relationships and data relationship themes corresponding to different data parts of the original data of the chart.

3. The method for processing inserted chart data based on prediction algorithm according to claim 2, characterized in that: The method of predicting the data relationship parameters corresponding to the original data of the chart based on the historical user data of the target user based on the data prediction algorithm includes: Inputting the original data of the chart into a trained data normative prediction model to obtain corresponding normative parameters; the data normative prediction model is trained by a training data set including a plurality of training chart original data and corresponding data normative expression annotations; Determine whether the normative parameter is greater than a preset parameter threshold and obtain a determination result; When the judgment result is yes, the original data of the chart is input into a trained data arrangement type prediction neural network to obtain a target data arrangement type corresponding to the original data of the chart; When the judgment result is no, determining a plurality of preference data arrangement types corresponding to the target user according to the historical chart selection record of the target user; Determining a target data arrangement type corresponding to the chart original data from a plurality of preference data arrangement types according to a data template corresponding to the preference data arrangement type and the chart original data; According to the data classification corresponding rule corresponding to the target data arrangement type, the data parts of the original data of the chart are classified and the relationship is matched to obtain the data relationship parameters corresponding to the original data of the chart.

4. The method for processing inserted chart data based on prediction algorithm according to claim 3, characterized in that: The step of selecting a record based on the historical chart of the target user to determine a plurality of preference data arrangement types corresponding to the target user includes: Obtaining the historical chart selection record of the target user; For each preset data arrangement type, count the proportion of records corresponding to the data arrangement type in the historical chart selection records; Sorting all the data arrangement types from large to small according to the record ratio to obtain a type sequence; The data arrangement types of the first preset number of the type sequence and the record ratio of which is greater than a preset ratio threshold are screened out to obtain a plurality of preferred data arrangement types corresponding to the target user.

5. The method for processing inserted chart data based on prediction algorithm according to claim 4, characterized in that: The step of determining a target data arrangement type corresponding to the chart original data from a plurality of preference data arrangement types according to the data template corresponding to the preference data arrangement type and the chart original data includes: For each of the preference data arrangement types, determining a data template corresponding to the preference data arrangement type from a preset arrangement type data template library; Calculating the data similarity between the preference data arrangement type and the original data of the chart; Calculating a weighted average value between the data similarity and the record proportion corresponding to the preference data arrangement type to obtain a type priority parameter corresponding to the preference data arrangement type; The preferred data arrangement type with the highest type priority parameter is determined as the target data arrangement type corresponding to the original data of the chart.

6. The method for processing inserted chart data based on prediction algorithm according to claim 2, characterized in that: The method of determining the object composition strategy corresponding to the original chart data based on the dynamic programming algorithm according to the inserted document data and the data relationship parameters includes: Determine document parameters corresponding to the inserted document data; the document parameters include document subject and document type; For each preset candidate image-text coherence prediction model, obtaining a training data set corresponding to the candidate image-text coherence prediction model; Calculating parameter similarity between document parameter annotations of training document data in the training data set and the document parameters; Determining the candidate image-text coherence prediction model with the highest parameter similarity as the target image-text coherence prediction model; Determining the objective function and restriction conditions related to the coherence of the inserted image and text according to the data relationship parameters and the target image and text coherence prediction model; Based on a dynamic programming algorithm, an iterative operation of the object composition scheme is performed according to the objective function and the constraint conditions until an optimal object composition scheme is obtained, so as to determine an object composition strategy corresponding to the original data of the chart; the object composition strategy includes chart types, chart dimensions, chart icon types, chart drawing parameters and chart display positions corresponding to different data parts of the original data of the chart.

7. The method for processing inserted chart data based on prediction algorithm according to claim 6, characterized in that: The total number of chart types corresponding to all data parts of the original data of the chart in the object composition scheme in the objective function is minimized; the restriction conditions include: The object composition scheme is obtained by inputting the original chart data and the data relationship parameters into a preset object prediction neural network for output; the object prediction neural network is trained by a training data set including a plurality of training chart original data and corresponding data relationship parameter annotations and chart object composition scheme annotations; The output prediction probability of the object composition scheme in the object prediction neural network is greater than a preset probability threshold; The image-text coherence corresponding to the object composition scheme is greater than a preset coherence threshold; the image-text coherence is obtained by inputting the document data within a preset data volume before and after the object composition scheme and the insertion position of the chart inserted into the document data into the target image-text coherence prediction model for prediction; the target image-text coherence prediction model is obtained by training a training data set including a plurality of training image-text document data and corresponding image-text coherence annotations.

8. The method for processing inserted chart data based on prediction algorithm according to claim 6, characterized in that: Generating the chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library includes: For each preset chart object library, a corresponding chart generation instruction is generated according to the object composition strategy based on the code rules corresponding to the chart object library; the chart object library is built based on Web Component technology or echart technology; Sending the chart generation instruction to the communication interface corresponding to the chart object library to obtain the candidate chart object data output by the chart object library; Determine the chart completeness corresponding to the candidate chart object data based on a data object completeness algorithm; Inputting the candidate chart object data and the document data within a preset data amount before and after the chart insertion position of the inserted document data into the target graphic-text coherence prediction model to obtain the coherence parameter corresponding to the candidate chart data; Calculating the product of the chart completeness and the coherence parameter to obtain a chart priority parameter corresponding to the candidate chart data; The candidate chart object data with the highest chart priority parameter among all the candidate chart object data output by all the chart object libraries is determined as the chart object data corresponding to the chart original data.

9. An insertion chart data processing system based on a prediction algorithm, characterized in that: The system comprises: The acquisition module is used to acquire the original chart data to be converted and the inserted document data input by the target user; A prediction module, configured to predict data relationship parameters corresponding to the original data of the chart based on a data prediction algorithm and according to the user history data of the target user; A determination module, configured to determine an object composition strategy corresponding to the original data of the chart based on a dynamic programming algorithm according to the inserted document data and the data relationship parameters; A generation module is used to generate chart object data corresponding to the chart original data according to the object composition strategy and at least one preset chart object library; the chart object data is used to be inserted into the insertion document data.

10. An insertion chart data processing system based on a prediction algorithm, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the insertion chart data processing method based on the prediction algorithm as described in any one of claims 1-8.

Images