CN111191090B - Method, device, equipment and storage medium for determining service data presentation graph type - Google Patents

Method, device, equipment and storage medium for determining service data presentation graph type Download PDF

Info

Publication number
CN111191090B
CN111191090B CN202010281322.3A CN202010281322A CN111191090B CN 111191090 B CN111191090 B CN 111191090B CN 202010281322 A CN202010281322 A CN 202010281322A CN 111191090 B CN111191090 B CN 111191090B
Authority
CN
China
Prior art keywords
matrix
trained
service data
nodes
service
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.)
Active
Application number
CN202010281322.3A
Other languages
Chinese (zh)
Other versions
CN111191090A (en
Inventor
蔡耀华
王炜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alipay Hangzhou Information Technology Co Ltd
Original Assignee
Alipay Hangzhou Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Alipay Hangzhou Information Technology Co Ltd filed Critical Alipay Hangzhou Information Technology Co Ltd
Priority to CN202010281322.3A priority Critical patent/CN111191090B/en
Publication of CN111191090A publication Critical patent/CN111191090A/en
Application granted granted Critical
Publication of CN111191090B publication Critical patent/CN111191090B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/904Browsing; Visualisation therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/906Clustering; Classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computer systems based on biological models
    • G06N3/02Computer systems based on biological models using neural network models
    • G06N3/04Architectures, e.g. interconnection topology
    • G06N3/0454Architectures, e.g. interconnection topology using a combination of multiple neural nets

Abstract

One embodiment of the present specification provides a method, an apparatus, a device, and a storage medium for determining a service data presentation graph type, where the method includes: and acquiring service data of the type of the display graph to be determined in the first service scene. And the display graph type represents the layout mode of each node and the layout mode of edges among the nodes in the display graph of the business data. The service data comprises node identification of the node, service dimension identification corresponding to the first service scene, dimension information of the node in the service dimension and information of edges between the nodes. And constructing a first feature matrix according to the node identification, the service dimension identification and the dimension information of the node. The first feature matrix is used for representing service dimension features of the nodes. And constructing a second feature matrix according to the node identification and the information of the edges between the nodes. The second feature matrix is used for representing the connection relation features between the nodes. And predicting the target display graph type corresponding to the service data according to the first characteristic matrix, the second characteristic matrix and the display graph type prediction model.

Description

Method, device, equipment and storage medium for determining service data presentation graph type
Technical Field
The present disclosure relates to the field of computer devices, and in particular, to a method, an apparatus, a device, and a storage medium for determining a service data presentation graph type.
Background
With the increase of service scenes, more and more service data can be processed by a computer, and service personnel generally need to summarize and analyze the service data in order to know the service progress, so that how to better show the service data to the service personnel becomes a problem to be solved.
In some service scenarios, the service data may include node data and connection relationship data between nodes, and for such service data, because a certain connection relationship exists between nodes, the content of the service data may be displayed in a manner of generating a display diagram corresponding to the service data, which is convenient for service personnel to quickly know the content of the service data. In one example, the service data display graph may include a plurality of nodes corresponding to the service data, and the nodes are connected by edges.
Since the type of the display graph directly affects the readability of the display graph when the display graph corresponding to the service data is generated, for example, the readability of displaying the same service data in a tree graph manner is different from the readability of displaying the same service data in a flow graph manner, it is necessary to provide a technical solution for accurately determining the type of the target display graph corresponding to the service data in the scene of generating the display graph corresponding to the service data.
Disclosure of Invention
An object of one embodiment of the present specification is to provide a method, an apparatus, a device, and a storage medium for determining a type of a service data presentation graph, so as to accurately determine a target presentation graph type corresponding to service data in a scenario where a presentation graph corresponding to service data is generated.
To solve the above technical problem, one embodiment of the present specification is implemented as follows:
one embodiment of the present specification provides a method for determining a service data presentation graph type, including: and acquiring service data of the type of the display graph to be determined in the first service scene. The display graph type represents a layout mode of each node and a layout mode of edges between each node in the display graph of the service data. The service data comprises a node identifier of the node, a service dimension identifier corresponding to the first service scene, dimension information of the node in the service dimension and information of edges between the nodes. And constructing a first feature matrix according to the node identification, the service dimension identification and the dimension information of the node in the service dimension. The first feature matrix is used for representing service dimension features of the nodes. And constructing a second feature matrix according to the node identification and the information of the edges between the nodes. The second feature matrix is used for representing the connection relation features between the nodes. And predicting the target display graph type corresponding to the service data according to the first characteristic matrix, the second characteristic matrix and a pre-trained display graph type prediction model.
One embodiment of the present specification provides an apparatus for determining a service data presentation graph type, including: the acquisition module acquires service data of the type of the display graph to be determined in the first service scene. The display graph type represents a layout mode of each node and a layout mode of edges between each node in the display graph of the service data. The service data comprises a node identifier of the node, a service dimension identifier corresponding to the first service scene, dimension information of the node in the service dimension and information of edges between the nodes. And the first construction module is used for constructing a first feature matrix according to the node identification, the service dimension identification and the dimension information of the node in the service dimension. The first feature matrix is used for representing service dimension features of the nodes. And the second construction module is used for constructing a second feature matrix according to the node identification and the information of the edges between the nodes. The second feature matrix is used for representing the connection relation features between the nodes. And the prediction module predicts the target display graph type corresponding to the service data according to the first characteristic matrix, the second characteristic matrix and a display graph type prediction model trained in advance.
One embodiment of the present specification provides an apparatus for determining a service data presentation graph type, including: a processor, and a memory arranged to store computer executable instructions. The computer executable instructions, when executed, cause the processor to implement the steps of the method of determining a type of a business data presentation graph as described above.
One embodiment of the present specification provides a storage medium to store computer-executable instructions. The computer executable instructions, when executed, implement the steps of the above-described method of determining a type of business data presentation graph.
Drawings
In order to more clearly illustrate the technical solutions in one or more embodiments of the present disclosure, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present disclosure, and for those skilled in the art, other drawings can be obtained according to these drawings without any creative effort.
Fig. 1 is a flowchart illustrating a method for determining a type of a business data presentation graph according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram illustrating a structure of a presentation type prediction model according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram illustrating a structure of a presentation type prediction model according to another embodiment of the present disclosure;
FIG. 4 is a schematic flow chart diagram illustrating a model training method according to an embodiment of the present disclosure;
FIG. 5 is a schematic flow chart diagram illustrating a model training method according to another embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a display diagram of business data provided by an embodiment of the present description;
FIG. 7 is a block diagram of an apparatus for determining a type of a traffic data display map according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of an apparatus for determining a traffic data presentation graph type according to an embodiment of the present specification.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from one or more of the embodiments described herein without making any inventive step shall fall within the scope of protection of this document.
An object of one embodiment of the present specification is to provide a method for determining a type of a service data presentation graph, so as to accurately determine a type of a target presentation graph corresponding to service data in a scenario where a presentation graph corresponding to service data is generated. The method can be applied to a background server and executed by the background server. The method can be realized based on the GCN (Graph convolutional neural network) theory.
Fig. 1 is a schematic flowchart of a method for determining a type of a business data presentation graph according to an embodiment of the present disclosure, where as shown in fig. 1, the flowchart includes the following steps:
step S102, acquiring service data of a to-be-determined display diagram type in a first service scene; the display graph type represents the layout mode of each node and the layout mode of edges among the nodes in the display graph of the business data; the service data comprises node identification of the node, service dimension identification corresponding to the first service scene, dimension information of the node in the service dimension and information of edges between the nodes;
step S104, constructing a first characteristic matrix according to the node identification, the service dimension identification and the dimension information of the node in the service dimension, wherein the first characteristic matrix is used for expressing the service dimension characteristic of the node;
step S106, constructing a second feature matrix according to the node identification and the information of the edges between the nodes, wherein the second feature matrix is used for representing the connection relation features between the nodes;
and S108, predicting the target display graph type corresponding to the service data according to the first characteristic matrix, the second characteristic matrix and a display graph type prediction model trained in advance.
In this embodiment, first, service data of a to-be-determined display diagram type in a first service scene is obtained, then a first feature matrix and a second feature matrix are constructed according to the service data, and finally, a target display diagram type corresponding to the service data is predicted according to the first feature matrix, the second feature matrix and a pre-trained display diagram type prediction model. Therefore, according to the embodiment, the target display diagram type corresponding to the business data can be accurately determined in the scene that the display diagram corresponding to the business data needs to be generated, so that the display diagram of the business data is generated according to the target display diagram type, the readability of the display diagram of the business data is improved, and business personnel can conveniently and accurately know the business data through the display diagram of the business data.
In step S102, the first business scenario may be, for example, a scenario in which an interpersonal relationship between people is determined, or a scenario in which a fund transaction relationship between enterprises is determined. The service data in the first service scenario may be displayed in a display diagram form, so that a display diagram type corresponding to the service data in the first service scenario needs to be determined, that is, a target display diagram type needs to be determined. The display graph type represents a layout mode of each node and a layout mode of edges between each node in the display graph of the business data. For example, if the display diagram type is a tree diagram, the nodes in the display diagram representing the service data are arranged in a tree shape, and the edges between the nodes are also arranged in a tree shape, or if the display diagram type is a circle diagram, the nodes in the display diagram representing the service data are arranged in a circle shape, and the edges between the nodes are also arranged in a circle shape.
Because the display graph of the service data includes each node and the edge between each node, correspondingly, the service data includes the node identifier of the node, the service dimension identifier corresponding to the first service scenario, the dimension information of the node in the service dimension, and the information of the edge between the nodes. The information of the edges between the nodes includes, but is not limited to, the number of edges between the nodes, the identification of each edge between the nodes, and the like.
In one example, the first service scenario may be a scenario in which the interpersonal relationship between characters is determined, in which nodes in the service data represent characters, and edges between the nodes represent the interpersonal relationship between the characters. The node identification of each node in the business data may be a name of each person, the business dimension identification corresponding to the first business scenario in the business data includes, but is not limited to, "age", "gender", "native place", "activity experience", and the like, the dimension information of the node in the business dimension in the business data includes, but is not limited to, information of the age, gender, native place, activity experience, and the like of each person, the information of the edge between the nodes in the business data includes, but is not limited to, the identification of the edge between any two persons and the number of the edges, for example, there are two interpersonal relationship types, namely, a colleague and a colleague between the person a and the person B, then there are two edges between the node of the person a and the node of the person B, the identification of one edge may be "colleague", and the identification of.
In another example, the first business scenario may be a scenario of determining a fund flow relationship between companies, where nodes in the business data represent companies, and edges between the nodes represent the fund flow relationship between the companies. The node identifier of each node in the service data may be a name of each company, the service dimension identifier corresponding to the first service scenario in the service data includes, but is not limited to, "operating duration," affiliated industry, "" shareholder name, "and the like, the dimension information of the node in the service dimension in the service data includes, but is not limited to, information of the operating duration, the affiliated industry, the shareholder name, and the like of each company, the information of the edge between the nodes in the service data includes, but is not limited to, the identifier and the number of the edge between any two companies, for example, two fund exchange relationship types, namely an investment relationship and a loan relationship exist between a company a and a company B, two edges exist between the node of the person a and the node of the person B, the identifier of one edge may be" investment, "and the identifier of the other edge may be" loan.
In the step S104, a first feature matrix is constructed according to the node identifier, the service dimension identifier, and the dimension information of the node in each service dimension, where the first feature matrix is used to represent the service dimension feature of the node. The method comprises the following steps:
(a1) establishing a first two-dimensional matrix, setting column data of the first two-dimensional matrix to correspond to nodes one by one according to the node identification, and setting row data of the first two-dimensional matrix to correspond to service dimensions one by one according to the service dimension identification;
(a2) and determining element values of elements in the first two-dimensional matrix according to the dimension information of the node in the service dimension, and taking the determined first two-dimensional matrix as a first characteristic matrix.
Specifically, a first two-dimensional matrix is established, and according to the node identifiers, column data of the first two-dimensional matrix is set to correspond to nodes one by one, that is, each column of data of the first two-dimensional matrix is set to correspond to one node, and the number of columns of the first two-dimensional matrix is set to be equal to the number of nodes. Similarly, according to the service dimension identifier, the row data of the first two-dimensional matrix is set to correspond to the service dimensions one by one, that is, each row data of the first two-dimensional matrix is set to correspond to one service dimension, and the number of the row data of the first two-dimensional matrix is set to be equal to the number of the service dimensions.
And then, determining the element value of each element in the first two-dimensional matrix according to the dimension information of the node in the service dimension. In one example, a mapping relationship between the dimension information of the node in the service dimension and the element value is preset, and the element value of any node relative to any service dimension is determined according to the mapping relationship. For example, the service dimension includes income and age, the element value corresponding to income greater than 100 is preset to be 1, the element value corresponding to income less than 100 is 0, the element value corresponding to age greater than 10 is preset to be 1, the element value corresponding to age less than 10 is 0, it is assumed that a node a exists, if the income corresponding to the node a is greater than 100 and the age corresponding to the node a is less than 10, the element value of the node a in the first two-dimensional matrix relative to the income dimension is set to be 1, and the element value of the node a in the first two-dimensional matrix relative to the age dimension is set to be 0.
Finally, the first two-dimensional matrix after the element values are set is taken as a first feature matrix. In one example, the first feature matrix may be represented as a two-dimensional matrix N × M, where N is the number of the service dimensions and M is the number of nodes, and the element values in the matrix N × M are determined according to a preset mapping relationship between the dimension information and the element values of the nodes in the service dimensions.
In the step S106, a second feature matrix is constructed according to the node identifier and the information of the edge between the nodes, where the second feature matrix is used to represent the connection relationship features between the nodes, and the step specifically includes:
(b1) establishing a second two-dimensional matrix, setting column data of the second two-dimensional matrix to correspond to nodes one by one according to node identification, and setting row data of the second two-dimensional matrix to correspond to the nodes one by one;
(b2) calculating the number of edges between any two nodes according to the information of the edges between the nodes, and setting the number as the element value of the corresponding element in the second two-dimensional matrix;
(b3) and performing Fourier transform on the set second two-dimensional matrix to obtain a second characteristic matrix.
Firstly, a second two-dimensional matrix is established, column data of the second two-dimensional matrix is set to be in one-to-one correspondence with nodes according to node identifications, row data of the second two-dimensional matrix is set to be in one-to-one correspondence with the nodes, namely, each column of data of the second two-dimensional matrix is set to correspond to one node, the number of columns of the second two-dimensional matrix is set to be equal to the number of the nodes, each row of data of the second two-dimensional matrix is set to correspond to one node, and the number of rows of the second two-dimensional matrix is.
Then, the number of edges between any two nodes is calculated from the information of the edges between the nodes, and the number is set as the element value of the corresponding element in the second two-dimensional matrix. For example, node a represents user a, node B represents user B, and user a and user B have two interpersonal relationships, including a classmate relationship and a coworker relationship, the information of the edge between node a and node B includes 2 edges, and also includes an identifier of each edge, for example, the identifier of edge 1 is "classmate", and the identifier of edge 2 is "coworker", and in this step, the element value of the element corresponding to node a and node B is set to 2.
And finally, carrying out Fourier transform on the set second two-dimensional matrix to obtain a second characteristic matrix.
In one example, the process of acts (b 1) and (b 2) above is also called building the laplacian matrix of the graph. And then, carrying out Fourier transform on the Laplace matrix of the graph to obtain a characteristic matrix of the graph in a frequency domain, namely a second characteristic matrix. In yet another example, the second feature matrix may be represented as a two-dimensional matrix M × M, where M is the number of nodes and the element values in the matrix M × M are equal to the number of edges between corresponding nodes.
It should be noted that, the step S104 and the step S106 may be executed successively, for example, the step S104 is executed first, and then the step S106 is executed, or the step S106 is executed first, and then the step S104 is executed, or the step S104 and the step S106 may also be executed synchronously, which is not limited in the embodiment of the present specification.
Through the above process, the preparation required before the display diagram type prediction model is called in the embodiment is relatively simple, so that the threshold of calling the model is reduced, and the method can be used in various service scenarios.
In step S108, predicting the target display diagram type corresponding to the service data according to the first feature matrix, the second feature matrix and the display diagram type prediction model trained in advance, specifically:
(c1) performing dot product on the first feature matrix and the second feature matrix to obtain a third feature matrix;
(c2) and inputting the third feature matrix into the display graph type prediction model, and predicting the target display graph type corresponding to the service data through the display graph type prediction model.
Firstly, performing dot product on the first feature matrix and the second feature matrix to obtain a third feature matrix. In one example, the first feature matrix is a two-dimensional matrix N × M, the second feature matrix is a two-dimensional matrix M × M, where N is the number of the service dimensions, and M is the number of the nodes, and then the dot product is performed on the first feature matrix and the second feature matrix to obtain a third feature matrix N × M.
And then, inputting the third feature matrix into the display graph type prediction model, and predicting the target display graph type corresponding to the service data through the display graph type prediction model. The presentation graph type prediction model may be a convolutional neural network model. In one example, the action of performing a dot product on the first feature matrix and the second feature matrix to obtain a third feature matrix may also be performed in the display graph type prediction model.
In one example, the presentation graph type predictive model includes at least one convolution layer, an average pooling layer, and an activation function layer. In this example, predicting a target display graph type corresponding to the business data by using the display graph type prediction model includes:
(c21) performing convolution processing on the third feature matrix at least once by using a convolution layer in the display graph type prediction model and a pre-trained convolution kernel to obtain a fourth feature matrix, wherein the row number of the fourth feature matrix is the number of nodes, the column number of the fourth feature matrix is the number of preset display graph types, and the element value of the fourth feature matrix represents the feature value of a corresponding node relative to the corresponding preset display graph type;
(c22) performing average pooling on the fourth feature matrix through an average pooling layer in the display graph type prediction model to obtain a one-dimensional matrix, wherein the row number of the one-dimensional matrix is 1, the column number of the one-dimensional matrix is the number of preset display graph types, and the element values of the one-dimensional matrix represent feature values corresponding to the display graph types;
(c23) and predicting a matching degree value between each preset display graph type and the service data according to the one-dimensional matrix through an activation function layer in the display graph type prediction model, and outputting a target display graph type corresponding to the service data based on the matching degree value.
Specifically, the display graph type prediction model includes at least one convolution layer, each convolution layer includes a pre-trained convolution kernel, and in act (c 21), the pre-trained convolution kernel is used to perform at least one convolution process on the third feature matrix through the convolution layer in the display graph type prediction model, that is, the convolution kernel performs at least one convolution on the third feature matrix, so as to obtain a fourth feature matrix. The number of rows of the fourth feature matrix is the number of nodes, the number of columns of the fourth feature matrix is the number of predetermined presentation graph types, and the element values of the fourth feature matrix represent feature values of corresponding nodes relative to the corresponding predetermined presentation graph types.
In one example, where the number of convolutional layers is 2, each convolutional kernel can be represented as a matrix of N X, where N is the number of traffic dimensions and X is the number of predetermined presentation types, and the values of each convolutional kernel are the same. In this example, the third feature matrix is N × M, and the convolution kernel is used to perform convolution processing on the third feature matrix twice, that is, the convolution kernel and the third feature matrix are convolved twice, so as to obtain a fourth feature matrix M × X.
Then, through the above-mentioned operation (c 22), the fourth feature matrix is subjected to average pooling processing through an average pooling layer in the display diagram type prediction model, so as to obtain a one-dimensional matrix, where the row number of the one-dimensional matrix is 1, the column number of the one-dimensional matrix is the number of the predetermined display diagram types, and the element values of the one-dimensional matrix represent feature values corresponding to the display diagram types. Since the number of rows of the fourth feature matrix is the number of nodes and the number of columns is the number of predetermined display diagram types, when the fourth feature matrix is subjected to average pooling, it can be understood that the average value is calculated for the same column data, so that the number of rows of the averaged pooled fourth feature matrix is 1 row and the number of columns is the number of predetermined display diagram types.
Finally, through the above action (c 23), the obtained one-dimensional matrix is input to an activation function layer, which may include an activation function for multi-classification, such as a Softmax function, and the one-dimensional matrix is processed by the activation function to obtain matching degree values between each predetermined presentation graph type and the service data, and a target presentation graph type corresponding to the service data is output based on the matching degree values.
In one example, a one-dimensional matrix 1X is input to the Softmax function, X being the number of predetermined exposition types. And calculating the one-dimensional matrix through a Softmax function, so that each element value in the one-dimensional matrix is normalized to be between 0 and 1, the normalization result represents the matching degree between the corresponding preset showing graph type and the service data, and the preset showing graph type with the highest matching degree is selected as the target showing graph type corresponding to the service data.
Fig. 2 is a schematic structural diagram of a display diagram type prediction model provided in an embodiment of the present disclosure, and as shown in fig. 2, the model includes a first convolution layer 201, a second convolution layer 202, an average pooling layer 203, and an activation function layer 204, where the two convolution layers have convolution kernels with the same size and value, and a specific operation process of the model refers to the foregoing description and is not repeated here.
As can be seen from the foregoing description, based on N being the number of service dimensions, M being the number of nodes, and X being the number of predetermined display types, the first feature matrix may be N × M, the second feature matrix may be M × M, and the third feature matrix may be obtained by dot product of the first feature matrix and the second feature matrix, and may be N × M. And if the convolution kernel can be N X, performing convolution processing on the third feature matrix for multiple times, such as twice convolution processing, namely performing convolution processing on the convolution kernel and the third feature matrix for multiple times to obtain a fourth feature matrix M X, and performing average pooling processing on the fourth feature matrix through the average pooling layer to obtain a one-dimensional matrix 1X.
It is therefore easy to think that in other embodiments, based on N being the number of service dimensions, M being the number of nodes, and X being the number of predetermined presentation graph types, the first feature matrix may be M × N, the second feature matrix may be M × M, and the third feature matrix may be M × N, which is obtained by dot product of the second feature matrix and the first feature matrix. And if the convolution kernel can be xn, performing multiple convolution processing on the third feature matrix for example twice by using the convolution kernel, namely performing multiple convolution on the convolution kernel and the third feature matrix to obtain a fourth feature matrix xm, and performing average pooling processing on the fourth feature matrix through the average pooling layer to obtain a one-dimensional matrix X1. Both of these examples are within the scope of the description and the protection of this document.
In another embodiment, the presentation type prediction model includes at least one convolutional layer and one classifier layer. The classifier may be an SVM classifier, and in this example, predicting the target display graph type corresponding to the service data by using the display graph type prediction model includes:
(c24) performing convolution processing on the third feature matrix at least once by using a convolution layer in the display graph type prediction model and a pre-trained convolution kernel to obtain a fourth feature matrix, wherein the row number of the fourth feature matrix is the number of nodes, the column number of the fourth feature matrix is the number of preset display graph types, and the element value of the fourth feature matrix represents the feature value of a corresponding node relative to the corresponding preset display graph type;
(c25) through a classifier layer in the display diagram type prediction model, the matching degree value between each preset display diagram type and the service data is predicted according to the fourth feature matrix, and the target display diagram type corresponding to the service data is output based on the matching degree value.
The process of act (c 24) may refer to the preceding description and will not be repeated here. In act (c 25), the coefficients of the classifier are trained in advance, the fourth feature matrix M × X is input to the classifier layer, the classifier layer may predict matching degree values between each predetermined display pattern type and the service data according to the pre-trained coefficients, the matching degree value may be a value between 0 and 1, and the predetermined display pattern type with the largest matching degree value is determined as the target display pattern type corresponding to the service data.
Fig. 3 is a schematic structural diagram of a display diagram type prediction model provided in another embodiment of the present disclosure, and as shown in fig. 3, the model includes a first convolution layer 301, a second convolution layer 302, and a classifier layer 303, and the specific operation process of the model refers to the foregoing description and is not repeated here.
In this embodiment, after convolution processing is performed on the convolution layer, each node may also be clustered according to the fourth feature matrix obtained by convolution, and the clustering result is provided to the service staff, so that the service staff classifies the nodes based on the clustering result, and determines the target display graph type corresponding to the service data.
Through the process, the prediction model in the embodiment is simple in structure and easy to implement, so that the requirements of various service scene prediction target display graph types are met.
Fig. 4 is a flowchart illustrating a model training method provided in an embodiment of the present disclosure when the display diagram type prediction model is composed of a convolutional layer, an average pooling layer, and an activation function layer, and the display diagram type prediction model can be obtained by training through the model training method in fig. 4. As shown in fig. 4, the method includes:
step S402, obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data;
step S404, constructing a model to be trained comprising a convolutional layer to be trained, an average pooling layer and an activation function layer, and inputting a third feature matrix corresponding to sample business data and a target display graph type marked by the sample business data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained;
step S406, after the training of the convolution kernel to be trained is completed, taking the trained model as a display graph type prediction model.
Specifically, sample service data marked with a target display graph type is obtained, and the sample service data also includes a node identifier, a service dimension identifier, dimension information of the node in the service dimension, and information of edges between the nodes. And determining the target display graph type corresponding to the sample business data. Then, a first feature matrix, a second feature matrix and a third feature matrix corresponding to the sample service data are constructed through the method.
And then, constructing a model to be trained comprising a convolutional layer to be trained, an average pooling layer and an activation function layer, wherein in the model, a convolution kernel in the convolutional layer to be trained needs to be trained, and the average pooling layer and the activation function layer can adopt a universal model structure without retraining. Then, inputting the third feature matrix corresponding to the sample service data and the target display graph type marked by the sample service data into the model to be trained so as to train the convolution kernel to be trained in the convolution layer to be trained. The matrix size of the convolution kernel to be trained is predefined, and the sizes of the convolution kernels to be trained in each convolution layer to be trained are the same.
And finally, when the element values in the convolution kernel to be trained approach convergence, determining that the convolution kernel to be trained is trained. And after the training of the convolution kernel to be trained is finished, taking the trained model as a display graph type prediction model.
Fig. 5 is a flowchart illustrating a model training method according to another embodiment of the present disclosure when the display diagram type prediction model is composed of a convolutional layer and a classifier layer, and the display diagram type prediction model can be obtained by training through the model training method in fig. 5. As shown in fig. 5, the method includes:
step S502, obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data;
step S504, a model to be trained comprising a convolutional layer to be trained and a classifier layer to be trained is constructed, a third feature matrix corresponding to sample service data and a target display graph type marked by the sample service data are input into the model to be trained, and a convolutional kernel to be trained in the convolutional layer to be trained and a classifier coefficient to be trained in the classifier layer to be trained are trained;
step S506, after training of the convolution kernel to be trained and the classifier coefficient to be trained is completed, the model obtained through training is used as a display graph type prediction model.
Specifically, sample service data marked with a target display graph type is obtained, and the sample service data also includes a node identifier, a service dimension identifier, dimension information of the node in the service dimension, and information of edges between the nodes. And determining the target display graph type corresponding to the sample business data. Then, a first feature matrix, a second feature matrix and a third feature matrix corresponding to the sample service data are constructed through the method.
And then, constructing a model to be trained comprising a convolutional layer to be trained and a classifier layer to be trained, wherein in the model, convolutional kernels in the convolutional layer to be trained need to be trained, and classifier coefficients in the classifier layer to be trained need to be trained. Then, inputting a third feature matrix corresponding to the sample service data and the target display graph type marked by the sample service data into the model to be trained so as to train the convolution kernel to be trained in the convolution layer to be trained and the classifier coefficient to be trained in the classifier layer to be trained. The matrix size of the convolution kernel to be trained is predefined, and the sizes of the convolution kernels to be trained in each convolution layer to be trained are the same. The value range of the classifier coefficient to be trained is preset.
And finally, determining that the training of the convolution kernel to be trained is finished when the element values in the convolution kernel to be trained approach convergence and the values of the classifier coefficients to be trained approach convergence. And after the training of the convolution kernel to be trained is finished, taking the trained model as a display graph type prediction model.
Further, the convolution kernels may include a third two-dimensional matrix having a number of rows equal to the number N of service dimensions and a number of columns equal to the number X of predetermined presentation types, and each convolution kernel may be represented as a matrix of N × X. The activation function layer includes a softmax activation function.
Further, the preset show types may include tree circles, ring circles, force guide circles, flow charts, radial circles, mesh circles, concentric circles, arc diagrams, etc., and thus the target show types may include at least one of tree circles, ring circles, force guide circles, flow charts, radial circles, mesh circles, concentric circles, arc diagrams, etc.
Fig. 6 is a schematic view of a display diagram of service data provided in an embodiment of this specification, and as shown in fig. 6, taking a target display diagram type as a tree-shaped circle as an example, a first service scenario is a scenario in which a relationship between persons in a family is determined, a node represents each person in the same family, and the tree-shaped circle may represent a relationship between nodes in a parent-child node manner, so that after determining that the target display diagram type corresponding to the service data is a tree-shaped circle, a layout manner of each node and a layout manner of edges between nodes may be determined, and then the service data is laid out to generate the display diagram.
In summary, by the method in this embodiment, the target display diagram type corresponding to the business data can be accurately determined in a scene where the display diagram corresponding to the business data needs to be generated, so that the display diagram of the business data is generated according to the target display diagram type, readability of the display diagram of the business data is improved, and a business worker can conveniently and accurately know the business data through the display diagram of the business data. The method in the embodiment automatically learns the structure information of the graph data through the convolutional neural network model, determines the target display graph type corresponding to the service data according to the structure information, has accurate determination result, high operation speed and high determination efficiency, has no requirement on the number of nodes and the connection relation between the nodes, and can be suitable for determining the display graph type in any service scene.
Fig. 7 is a schematic block diagram illustrating an apparatus for determining a service data presentation graph type according to an embodiment of the present disclosure, as shown in fig. 7, the apparatus includes:
the obtaining module 71 obtains service data of a to-be-determined display diagram type in a first service scene; the display graph type represents a layout mode of each node and a layout mode of edges among the nodes in the display graph of the service data; the service data comprises a node identifier of the node, a service dimension identifier corresponding to the first service scene, dimension information of the node in the service dimension and information of edges between the nodes; a first constructing module 72, configured to construct a first feature matrix according to the node identifier, the service dimension identifier, and the dimension information of the node in the service dimension, where the first feature matrix is used to represent the service dimension feature of the node; a second constructing module 73, configured to construct a second feature matrix according to the node identifier and the information of the edge between the nodes, where the second feature matrix is used to represent a connection relationship feature between the nodes; and the predicting module 74 predicts the target display graph type corresponding to the service data according to the first feature matrix, the second feature matrix and a display graph type prediction model trained in advance.
Optionally, the first building module 72 is specifically configured to: establishing a first two-dimensional matrix, setting column data of the first two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the first two-dimensional matrix to be in one-to-one correspondence with the service dimension according to the service dimension identification; and determining element values of elements in the first two-dimensional matrix according to the dimension information of the nodes in the service dimension, and taking the determined first two-dimensional matrix as the first feature matrix.
Optionally, the second building module 73 is specifically configured to: establishing a second two-dimensional matrix, setting column data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes; calculating the number of edges between any two nodes according to the information of the edges between the nodes, and setting the number as the element value of the corresponding element in the second two-dimensional matrix; and carrying out Fourier transform on the set second two-dimensional matrix to obtain the second characteristic matrix.
Optionally, the prediction module 74 is specifically configured to: performing dot product on the first feature matrix and the second feature matrix to obtain a third feature matrix; and inputting the third feature matrix into the display graph type prediction model, and predicting the target display graph type corresponding to the service data through the display graph type prediction model.
Optionally, the prediction module 74 is further specifically configured to: performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types; performing average pooling processing on the fourth feature matrix through an average pooling layer in the display diagram type prediction model to obtain a one-dimensional matrix, wherein the row number of the one-dimensional matrix is 1, the column number of the one-dimensional matrix is the number of the preset display diagram types, and the element values of the one-dimensional matrix represent feature values corresponding to the display diagram types; and predicting matching degree values between each preset display graph type and the service data according to the one-dimensional matrix through an activation function layer in the display graph type prediction model, and outputting a target display graph type corresponding to the service data based on the matching degree values.
Optionally, the prediction module 74 is further specifically configured to: performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types; through a classifier layer in the display diagram type prediction model, the matching degree value between each preset display diagram type and the service data is predicted according to the fourth feature matrix, and the target display diagram type corresponding to the service data is output based on the matching degree value.
Optionally, the presentation graph type prediction model is trained by: obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data; constructing a model to be trained comprising a convolutional layer to be trained, an average pooling layer and an activation function layer, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained; and after the training of the convolution kernel to be trained is finished, taking the trained model as the display graph type prediction model.
Optionally, the presentation graph type prediction model is trained by: obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data; constructing a model to be trained comprising a convolutional layer to be trained and a classifier layer to be trained, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained and a classifier coefficient to be trained in the classifier layer to be trained; and after the training of the convolution kernel to be trained and the classifier coefficient to be trained is finished, taking a model obtained by training as the display graph type prediction model.
Optionally, the convolution kernel comprises a third two-dimensional matrix; the number of rows of the third two-dimensional matrix is equal to the number of the service dimensions, and the number of columns of the third two-dimensional matrix is equal to the number of the preset display graph types; the activation function layer includes a softmax activation function.
Optionally, the target presentation graph type comprises at least one of a tree graph, a ring graph, a force directed graph, a flow chart, a radial graph, a grid graph, a concentric circle graph, and an arc graph.
In this embodiment, first, service data of a to-be-determined display diagram type in a first service scene is obtained, then a first feature matrix and a second feature matrix are constructed according to the service data, and finally, a target display diagram type corresponding to the service data is predicted according to the first feature matrix, the second feature matrix and a pre-trained display diagram type prediction model. Therefore, according to the embodiment, the target display diagram type corresponding to the business data can be accurately determined in the scene that the display diagram corresponding to the business data needs to be generated, so that the display diagram of the business data is generated according to the target display diagram type, the readability of the display diagram of the business data is improved, and business personnel can conveniently and accurately know the business data through the display diagram of the business data.
It should be noted that the apparatus in this embodiment can implement each process of the foregoing method embodiment, and achieve the same effect and function, which is not described herein again.
Further, another embodiment of the present specification further provides a device for determining a service data presentation graph type, and fig. 8 is a schematic structural diagram of the device for determining a service data presentation graph type provided in an embodiment of the present specification, as shown in fig. 8. The device may vary widely in configuration or performance and may include one or more processors 901 and memory 902, where the memory 902 may store one or more stored applications or data. Memory 902 may be, among other things, transient storage or persistent storage. The application program stored in memory 902 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for the device. Still further, the processor 901 may be arranged in communication with the memory 902, on which device a series of computer-executable instructions in the memory 902 are executed. The apparatus may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input-output interfaces 905, one or more keyboards 906, and the like.
In a particular embodiment, the apparatus includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the apparatus, and the one or more programs configured for execution by the one or more processors include computer-executable instructions for:
acquiring service data of a to-be-determined display diagram type in a first service scene; the display graph type represents a layout mode of each node and a layout mode of edges among the nodes in the display graph of the service data; the service data comprises a node identifier of the node, a service dimension identifier corresponding to the first service scene, dimension information of the node in the service dimension and information of edges between the nodes;
constructing a first feature matrix according to the node identification, the service dimension identification and the dimension information of the node in the service dimension, wherein the first feature matrix is used for representing the service dimension characteristic of the node;
constructing a second feature matrix according to the node identification and the information of the edges between the nodes, wherein the second feature matrix is used for representing the connection relation features between the nodes;
and predicting the target display graph type corresponding to the service data according to the first characteristic matrix, the second characteristic matrix and a pre-trained display graph type prediction model.
Optionally, when executed, the computer-executable instructions construct a first feature matrix according to the node identifier, the service dimension identifier, and the dimension information of the node in the service dimension, including: establishing a first two-dimensional matrix, setting column data of the first two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the first two-dimensional matrix to be in one-to-one correspondence with the service dimension according to the service dimension identification; and determining element values of elements in the first two-dimensional matrix according to the dimension information of the nodes in the service dimension, and taking the determined first two-dimensional matrix as the first feature matrix.
Optionally, the computer executable instructions, when executed, construct a second feature matrix from the node identifiers and information of edges between the nodes, including: establishing a second two-dimensional matrix, setting column data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes; calculating the number of edges between any two nodes according to the information of the edges between the nodes, and setting the number as the element value of the corresponding element in the second two-dimensional matrix; and carrying out Fourier transform on the set second two-dimensional matrix to obtain the second characteristic matrix.
Optionally, when executed, the computer-executable instructions predict a target display graph type corresponding to the service data according to the first feature matrix, the second feature matrix, and a display graph type prediction model trained in advance, where the predicting includes: performing dot product on the first feature matrix and the second feature matrix to obtain a third feature matrix; and inputting the third feature matrix into the display graph type prediction model, and predicting the target display graph type corresponding to the service data through the display graph type prediction model.
Optionally, when executed, the computer-executable instructions predict, through the display graph type prediction model, a target display graph type corresponding to the business data, including: performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types; performing average pooling processing on the fourth feature matrix through an average pooling layer in the display diagram type prediction model to obtain a one-dimensional matrix, wherein the row number of the one-dimensional matrix is 1, the column number of the one-dimensional matrix is the number of the preset display diagram types, and the element values of the one-dimensional matrix represent feature values corresponding to the display diagram types; and predicting matching degree values between each preset display graph type and the service data according to the one-dimensional matrix through an activation function layer in the display graph type prediction model, and outputting a target display graph type corresponding to the service data based on the matching degree values.
Optionally, when executed, the computer-executable instructions predict, through the display graph type prediction model, a target display graph type corresponding to the business data, including: performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types; through a classifier layer in the display diagram type prediction model, the matching degree value between each preset display diagram type and the service data is predicted according to the fourth feature matrix, and the target display diagram type corresponding to the service data is output based on the matching degree value.
Optionally, the computer executable instructions, when executed, the presentation graph type prediction model is trained by: obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data; constructing a model to be trained comprising a convolutional layer to be trained, an average pooling layer and an activation function layer, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained; and after the training of the convolution kernel to be trained is finished, taking the trained model as the display graph type prediction model.
Optionally, the computer executable instructions, when executed, the presentation graph type prediction model is trained by: obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data; constructing a model to be trained comprising a convolutional layer to be trained and a classifier layer to be trained, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained and a classifier coefficient to be trained in the classifier layer to be trained; and after the training of the convolution kernel to be trained and the classifier coefficient to be trained is finished, taking a model obtained by training as the display graph type prediction model.
Optionally, the computer-executable instructions, when executed, the convolution kernel comprises a third two-dimensional matrix; the number of rows of the third two-dimensional matrix is equal to the number of the service dimensions, and the number of columns of the third two-dimensional matrix is equal to the number of the preset display graph types; the activation function layer includes a softmax activation function.
Optionally, the computer executable instructions, when executed, the target presentation graph type comprises at least one of a treemap, a torus, a force directed graph, a flow chart, a radial graph, a grid graph, a concentric circle graph, an arc graph.
In this embodiment, first, service data of a to-be-determined display diagram type in a first service scene is obtained, then a first feature matrix and a second feature matrix are constructed according to the service data, and finally, a target display diagram type corresponding to the service data is predicted according to the first feature matrix, the second feature matrix and a pre-trained display diagram type prediction model. Therefore, according to the embodiment, the target display diagram type corresponding to the business data can be accurately determined in the scene that the display diagram corresponding to the business data needs to be generated, so that the display diagram of the business data is generated according to the target display diagram type, the readability of the display diagram of the business data is improved, and business personnel can conveniently and accurately know the business data through the display diagram of the business data.
It should be noted that the device in this embodiment can implement each process of the foregoing method embodiment, and achieve the same effect and function, which is not described herein again.
Further, another embodiment of the present specification further provides a storage medium for storing computer-executable instructions, and in a specific embodiment, the storage medium may be a usb disk, an optical disk, a hard disk, or the like, and the storage medium stores computer-executable instructions that, when executed by a processor, implement the following processes:
acquiring service data of a to-be-determined display diagram type in a first service scene; the display graph type represents a layout mode of each node and a layout mode of edges among the nodes in the display graph of the service data; the service data comprises a node identifier of the node, a service dimension identifier corresponding to the first service scene, dimension information of the node in the service dimension and information of edges between the nodes;
constructing a first feature matrix according to the node identification, the service dimension identification and the dimension information of the node in the service dimension, wherein the first feature matrix is used for representing the service dimension characteristic of the node;
constructing a second feature matrix according to the node identification and the information of the edges between the nodes, wherein the second feature matrix is used for representing the connection relation features between the nodes;
and predicting the target display graph type corresponding to the service data according to the first characteristic matrix, the second characteristic matrix and a pre-trained display graph type prediction model.
Optionally, when executed by a processor, the storage medium stores computer-executable instructions for constructing a first feature matrix according to the node identifier, the service dimension identifier, and the dimension information of the node in the service dimension, including: establishing a first two-dimensional matrix, setting column data of the first two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the first two-dimensional matrix to be in one-to-one correspondence with the service dimension according to the service dimension identification; and determining element values of elements in the first two-dimensional matrix according to the dimension information of the nodes in the service dimension, and taking the determined first two-dimensional matrix as the first feature matrix.
Optionally, the storage medium stores computer-executable instructions that, when executed by the processor, construct a second feature matrix from the node identifiers and information of edges between the nodes, including: establishing a second two-dimensional matrix, setting column data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes; calculating the number of edges between any two nodes according to the information of the edges between the nodes, and setting the number as the element value of the corresponding element in the second two-dimensional matrix; and carrying out Fourier transform on the set second two-dimensional matrix to obtain the second characteristic matrix.
Optionally, when executed by a processor, the computer-executable instructions stored in the storage medium predict a target display graph type corresponding to the service data according to the first feature matrix, the second feature matrix, and a pre-trained display graph type prediction model, and include: performing dot product on the first feature matrix and the second feature matrix to obtain a third feature matrix; and inputting the third feature matrix into the display graph type prediction model, and predicting the target display graph type corresponding to the service data through the display graph type prediction model.
Optionally, when executed by a processor, the computer-executable instructions stored in the storage medium predict a target presentation graph type corresponding to the service data through the presentation graph type prediction model, and include: performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types; performing average pooling processing on the fourth feature matrix through an average pooling layer in the display diagram type prediction model to obtain a one-dimensional matrix, wherein the row number of the one-dimensional matrix is 1, the column number of the one-dimensional matrix is the number of the preset display diagram types, and the element values of the one-dimensional matrix represent feature values corresponding to the display diagram types; and predicting matching degree values between each preset display graph type and the service data according to the one-dimensional matrix through an activation function layer in the display graph type prediction model, and outputting a target display graph type corresponding to the service data based on the matching degree values.
Optionally, when executed by a processor, the computer-executable instructions stored in the storage medium predict a target presentation graph type corresponding to the service data through the presentation graph type prediction model, and include: performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types; through a classifier layer in the display diagram type prediction model, the matching degree value between each preset display diagram type and the service data is predicted according to the fourth feature matrix, and the target display diagram type corresponding to the service data is output based on the matching degree value.
Optionally, the storage medium stores computer executable instructions that, when executed by the processor, the presentation graph type prediction model is trained by: obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data; constructing a model to be trained comprising a convolutional layer to be trained, an average pooling layer and an activation function layer, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained; and after the training of the convolution kernel to be trained is finished, taking the trained model as the display graph type prediction model.
Optionally, the storage medium stores computer executable instructions that, when executed by the processor, the presentation graph type prediction model is trained by: obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data; constructing a model to be trained comprising a convolutional layer to be trained and a classifier layer to be trained, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained and a classifier coefficient to be trained in the classifier layer to be trained; and after the training of the convolution kernel to be trained and the classifier coefficient to be trained is finished, taking a model obtained by training as the display graph type prediction model.
Optionally, the storage medium stores computer-executable instructions that, when executed by the processor, the convolution kernel includes a third two-dimensional matrix; the number of rows of the third two-dimensional matrix is equal to the number of the service dimensions, and the number of columns of the third two-dimensional matrix is equal to the number of the preset display graph types; the activation function layer includes a softmax activation function.
Optionally, the storage medium stores computer executable instructions that, when executed by the processor, the target presentation graph type includes at least one of a tree graph, a ring graph, a force directed graph, a flow chart, a radial graph, a grid graph, a concentric circle graph, and an arc graph.
In this embodiment, first, service data of a to-be-determined display diagram type in a first service scene is obtained, then a first feature matrix and a second feature matrix are constructed according to the service data, and finally, a target display diagram type corresponding to the service data is predicted according to the first feature matrix, the second feature matrix and a pre-trained display diagram type prediction model. Therefore, according to the embodiment, the target display diagram type corresponding to the business data can be accurately determined in the scene that the display diagram corresponding to the business data needs to be generated, so that the display diagram of the business data is generated according to the target display diagram type, the readability of the display diagram of the business data is improved, and business personnel can conveniently and accurately know the business data through the display diagram of the business data.
It should be noted that the storage medium in this embodiment can implement the processes of the foregoing method embodiments, and achieve the same effects and functions, which are not described herein again.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Language Description Language), traffic, pl (core unified Programming Language), HDCal, JHDL (Java Hardware Description Language), langue, Lola, HDL, laspam, hardsradware (Hardware Description Language), vhjhd (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, 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.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the various elements may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
Embodiments of the present description are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, 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 disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present specification and is not intended to limit the present document. Various modifications and changes may occur to the embodiments described herein, as will be apparent to those skilled in the art. Any modifications, equivalents, improvements, etc. which come within the spirit and principle of the disclosure are intended to be included within the scope of the claims of this document.

Claims (20)

1. A method for determining a business data presentation graph type comprises the following steps:
acquiring service data of a to-be-determined display diagram type in a first service scene; the display graph type represents a layout mode of each node and a layout mode of edges among the nodes in the display graph of the service data; the service data comprises a node identifier of the node, a service dimension identifier corresponding to the first service scene, dimension information of the node in the service dimension and information of edges between the nodes;
constructing a first feature matrix according to the node identification, the service dimension identification and the dimension information of the node in the service dimension, wherein the first feature matrix is used for representing the service dimension characteristic of the node;
constructing a second feature matrix according to the node identification and the information of the edges between the nodes, wherein the second feature matrix is used for representing the connection relation features between the nodes;
and performing dot product on the first characteristic matrix and the second characteristic matrix to obtain a third characteristic matrix, inputting the third characteristic matrix to a display graph type prediction model, and predicting a target display graph type corresponding to the service data through the display graph type prediction model.
2. The method of claim 1, constructing a first feature matrix according to the node identifier, the service dimension identifier, and the dimension information of the node in the service dimension, comprising:
establishing a first two-dimensional matrix, setting column data of the first two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the first two-dimensional matrix to be in one-to-one correspondence with the service dimension according to the service dimension identification;
and determining element values of elements in the first two-dimensional matrix according to the dimension information of the nodes in the service dimension, and taking the determined first two-dimensional matrix as the first feature matrix.
3. The method of claim 1, constructing a second feature matrix from the node identification and information of edges between the nodes, comprising:
establishing a second two-dimensional matrix, setting column data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes;
calculating the number of edges between any two nodes according to the information of the edges between the nodes, and setting the number as the element value of the corresponding element in the second two-dimensional matrix;
and carrying out Fourier transform on the set second two-dimensional matrix to obtain the second characteristic matrix.
4. The method of claim 1, predicting, by the presentation type prediction model, a target presentation type to which the traffic data corresponds, comprising:
performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types;
performing average pooling processing on the fourth feature matrix through an average pooling layer in the display diagram type prediction model to obtain a one-dimensional matrix, wherein the row number of the one-dimensional matrix is 1, the column number of the one-dimensional matrix is the number of the preset display diagram types, and the element values of the one-dimensional matrix represent feature values corresponding to the display diagram types;
and predicting matching degree values between each preset display graph type and the service data according to the one-dimensional matrix through an activation function layer in the display graph type prediction model, and outputting a target display graph type corresponding to the service data based on the matching degree values.
5. The method of claim 1, predicting, by the presentation type prediction model, a target presentation type to which the traffic data corresponds, comprising:
performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types;
through a classifier layer in the display diagram type prediction model, the matching degree value between each preset display diagram type and the service data is predicted according to the fourth feature matrix, and the target display diagram type corresponding to the service data is output based on the matching degree value.
6. The method of claim 4, the presentation type prediction model trained by:
obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data;
constructing a model to be trained comprising a convolutional layer to be trained, an average pooling layer and an activation function layer, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained;
and after the training of the convolution kernel to be trained is finished, taking the trained model as the display graph type prediction model.
7. The method of claim 5, the presentation type prediction model trained by:
obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data;
constructing a model to be trained comprising a convolutional layer to be trained and a classifier layer to be trained, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained and a classifier coefficient to be trained in the classifier layer to be trained;
and after the training of the convolution kernel to be trained and the classifier coefficient to be trained is finished, taking a model obtained by training as the display graph type prediction model.
8. The method of claim 6, the convolution kernel to be trained comprising a third two-dimensional matrix; the number of rows of the third two-dimensional matrix is equal to the number of the service dimensions, and the number of columns of the third two-dimensional matrix is equal to the number of the preset display graph types; the activation function layer includes a softmax activation function.
9. The method of any of claims 1 to 8, the target presentation graph type comprising at least one of a treemap, a torus, a force directed graph, a flow chart, a radial graph, a grid graph, a concentric circle graph, an arc graph.
10. An apparatus for determining a type of a business data presentation graph, comprising:
the acquisition module acquires service data of a to-be-determined display diagram type in a first service scene; the display graph type represents a layout mode of each node and a layout mode of edges among the nodes in the display graph of the service data; the service data comprises a node identifier of the node, a service dimension identifier corresponding to the first service scene, dimension information of the node in the service dimension and information of edges between the nodes;
the first construction module is used for constructing a first feature matrix according to the node identification, the service dimension identification and the dimension information of the node in the service dimension, wherein the first feature matrix is used for representing the service dimension feature of the node;
the second construction module is used for constructing a second feature matrix according to the node identification and the information of the edges between the nodes, wherein the second feature matrix is used for representing the connection relation features between the nodes;
and the prediction module is used for performing dot product on the first characteristic matrix and the second characteristic matrix to obtain a third characteristic matrix, inputting the third characteristic matrix into a display graph type prediction model, and predicting a target display graph type corresponding to the service data through the display graph type prediction model.
11. The apparatus of claim 10, the first building block being specifically configured to:
establishing a first two-dimensional matrix, setting column data of the first two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the first two-dimensional matrix to be in one-to-one correspondence with the service dimension according to the service dimension identification;
and determining element values of elements in the first two-dimensional matrix according to the dimension information of the nodes in the service dimension, and taking the determined first two-dimensional matrix as the first feature matrix.
12. The apparatus of claim 10, the second building block being specifically configured to:
establishing a second two-dimensional matrix, setting column data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes according to the node identification, and setting row data of the second two-dimensional matrix to be in one-to-one correspondence with the nodes;
calculating the number of edges between any two nodes according to the information of the edges between the nodes, and setting the number as the element value of the corresponding element in the second two-dimensional matrix;
and carrying out Fourier transform on the set second two-dimensional matrix to obtain the second characteristic matrix.
13. The apparatus of claim 10, the prediction module further specifically configured to:
performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types;
performing average pooling processing on the fourth feature matrix through an average pooling layer in the display diagram type prediction model to obtain a one-dimensional matrix, wherein the row number of the one-dimensional matrix is 1, the column number of the one-dimensional matrix is the number of the preset display diagram types, and the element values of the one-dimensional matrix represent feature values corresponding to the display diagram types;
and predicting matching degree values between each preset display graph type and the service data according to the one-dimensional matrix through an activation function layer in the display graph type prediction model, and outputting a target display graph type corresponding to the service data based on the matching degree values.
14. The apparatus of claim 10, the prediction module further specifically configured to:
performing convolution processing on the third feature matrix at least once by using a pre-trained convolution kernel through convolution layers in the display graph type prediction model to obtain a fourth feature matrix, wherein the number of rows of the fourth feature matrix is the number of the nodes, the number of columns of the fourth feature matrix is the number of the preset display graph types, and the element values of the fourth feature matrix represent the feature values of the corresponding nodes relative to the preset display graph types;
through a classifier layer in the display diagram type prediction model, the matching degree value between each preset display diagram type and the service data is predicted according to the fourth feature matrix, and the target display diagram type corresponding to the service data is output based on the matching degree value.
15. The device of claim 13, the show-type prediction model trained by:
obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data;
constructing a model to be trained comprising a convolutional layer to be trained, an average pooling layer and an activation function layer, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained;
and after the training of the convolution kernel to be trained is finished, taking the trained model as the display graph type prediction model.
16. The device of claim 14, the show-type prediction model trained by:
obtaining sample service data marked with a target display graph type, constructing a first characteristic matrix and a second characteristic matrix corresponding to the sample service data, and performing dot product on the first characteristic matrix and the second characteristic matrix corresponding to the sample service data to obtain a third characteristic matrix corresponding to the sample service data;
constructing a model to be trained comprising a convolutional layer to be trained and a classifier layer to be trained, and inputting a third feature matrix corresponding to the sample service data and a target display graph type marked by the sample service data into the model to be trained so as to train a convolutional kernel to be trained in the convolutional layer to be trained and a classifier coefficient to be trained in the classifier layer to be trained;
and after the training of the convolution kernel to be trained and the classifier coefficient to be trained is finished, taking a model obtained by training as the display graph type prediction model.
17. The apparatus of claim 15, the convolution kernel to be trained comprising a third two-dimensional matrix; the number of rows of the third two-dimensional matrix is equal to the number of the service dimensions, and the number of columns of the third two-dimensional matrix is equal to the number of the preset display graph types; the activation function layer includes a softmax activation function.
18. The apparatus of any one of claims 10 to 17, the target presentation graph type comprising at least one of a tree graph, a ring graph, a force directed graph, a flow chart, a radial graph, a grid graph, a concentric circle graph, an arc graph.
19. An apparatus for determining a type of a business data presentation graph, comprising: a processor; and a memory arranged to store computer executable instructions which, when executed, cause the processor to carry out the steps of the method of determining a type of a business data presentation graph of any one of claims 1 to 9 above
20. A storage medium storing computer-executable instructions which, when executed, implement the steps of the method of determining a business data presentation graph type of any one of claims 1 to 9 above.
CN202010281322.3A 2020-04-10 2020-04-10 Method, device, equipment and storage medium for determining service data presentation graph type Active CN111191090B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010281322.3A CN111191090B (en) 2020-04-10 2020-04-10 Method, device, equipment and storage medium for determining service data presentation graph type

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010281322.3A CN111191090B (en) 2020-04-10 2020-04-10 Method, device, equipment and storage medium for determining service data presentation graph type

Publications (2)

Publication Number Publication Date
CN111191090A CN111191090A (en) 2020-05-22
CN111191090B true CN111191090B (en) 2020-09-08

Family

ID=70710949

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010281322.3A Active CN111191090B (en) 2020-04-10 2020-04-10 Method, device, equipment and storage medium for determining service data presentation graph type

Country Status (1)

Country Link
CN (1) CN111191090B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080140623A1 (en) * 2006-12-11 2008-06-12 Microsoft Corporation Recursive reporting via a spreadsheet
CN104866567A (en) * 2015-05-22 2015-08-26 国家计算机网络与信息安全管理中心 Method and apparatus for presenting business data
CN106484667A (en) * 2016-10-13 2017-03-08 广州视源电子科技股份有限公司 The method and device of display data
CN106598988A (en) * 2015-10-16 2017-04-26 阿里巴巴集团控股有限公司 Data processing method and device
US20180088753A1 (en) * 2016-09-29 2018-03-29 Google Inc. Generating charts from data in a data table
CN110007989A (en) * 2018-12-13 2019-07-12 国网信通亿力科技有限责任公司 Data visualization platform system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080140623A1 (en) * 2006-12-11 2008-06-12 Microsoft Corporation Recursive reporting via a spreadsheet
CN104866567A (en) * 2015-05-22 2015-08-26 国家计算机网络与信息安全管理中心 Method and apparatus for presenting business data
CN106598988A (en) * 2015-10-16 2017-04-26 阿里巴巴集团控股有限公司 Data processing method and device
US20180088753A1 (en) * 2016-09-29 2018-03-29 Google Inc. Generating charts from data in a data table
CN106484667A (en) * 2016-10-13 2017-03-08 广州视源电子科技股份有限公司 The method and device of display data
CN110007989A (en) * 2018-12-13 2019-07-12 国网信通亿力科技有限责任公司 Data visualization platform system

Also Published As

Publication number Publication date
CN111191090A (en) 2020-05-22

Similar Documents

Publication Publication Date Title
US20210157992A1 (en) Information processing method and terminal device
US9449140B2 (en) Conflict detection for self-aligned multiple patterning compliance
US10229499B2 (en) Skin lesion segmentation using deep convolution networks guided by local unsupervised learning
US20190156144A1 (en) Method and apparatus for detecting object, method and apparatus for training neural network, and electronic device
US10019657B2 (en) Joint depth estimation and semantic segmentation from a single image
US9858525B2 (en) System for training networks for semantic segmentation
EP3451192A1 (en) Text classification method and apparatus
US9697423B1 (en) Identifying the lines of a table
CN110785736B (en) Automatic code generation
KR20190094191A (en) Blockchain based data processing method and apparatus
US10373312B2 (en) Automated skin lesion segmentation using deep side layers
CN103593194A (en) Object serialization method and device
CN106293074B (en) Emotion recognition method and mobile terminal
US20180174037A1 (en) Suggesting resources using context hashing
Thilagamani et al. Gaussian and gabor filter approach for object segmentation
CN106874174B (en) Method and device for realizing interface test and function test
CN106909931B (en) Feature generation method and device for machine learning model and electronic equipment
US20180365025A1 (en) Systems and methods for adaptive user interfaces
US20150032708A1 (en) Database analysis apparatus and method
CN108345580B (en) Word vector processing method and device
CN107516105B (en) Image processing method and device
JP6484730B2 (en) Collaborative filtering method, apparatus, server, and storage medium for fusing time factors
CN107358247B (en) Method and device for determining lost user
US10628001B2 (en) Adapting user interfaces based on gold standards
CN108876792B (en) Semantic segmentation method, device and system and storage medium

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