CN116700710A - Element detection method, element detection device, electronic equipment and storage medium - Google Patents
Element detection method, element detection device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116700710A CN116700710A CN202210177109.7A CN202210177109A CN116700710A CN 116700710 A CN116700710 A CN 116700710A CN 202210177109 A CN202210177109 A CN 202210177109A CN 116700710 A CN116700710 A CN 116700710A
- Authority
- CN
- China
- Prior art keywords
- target
- node
- similarity
- sub
- child
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 claims description 39
- 238000012545 processing Methods 0.000 claims description 35
- 238000010606 normalization Methods 0.000 claims description 10
- 230000001419 dependent effect Effects 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 12
- 238000013461 design Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 108010001267 Protein Subunits Proteins 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/38—Creation or generation of source code for implementing user interfaces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The embodiment of the application discloses an element detection method, an element detection device, electronic equipment and a storage medium; comprising the following steps: acquiring a node to be judged, wherein the node to be judged comprises a plurality of target sub-nodes, and each target sub-node comprises a first number of features; for each target sub-node, weighting the first number of features included in the target sub-node to obtain target weighted features of the target sub-node; according to the target weighting characteristics corresponding to the target child nodes, determining the similarity between every two target child nodes, and obtaining a plurality of similarity operation results; determining a target operation result with a numerical value exceeding a preset similarity from a plurality of similarity operation results; if the non-repeated number of the target child nodes corresponding to the target operation result exceeds a preset threshold, determining the node to be judged as a target element. According to the embodiment of the application, the node to be judged is judged by the first quantity of the features, and the element detection method can be accurately and efficiently executed due to the fact that the number of the dependent features is large.
Description
Technical Field
The present application relates to the field of computers, and in particular, to an element detection method, an element detection device, an electronic device, and a storage medium.
Background
In the software development process, a designer typically presents a static example of a software page, and then a software engineer develops the software page according to the design draft. Designers typically implement the design of software page examples through the use of a Sketch, figma, adobe XD, or other development tool.
However, existing development tools typically do not identify the list in the software page instance, and therefore are typically implemented manually by a software engineer when identifying the list in the software page instance, which is inefficient.
Disclosure of Invention
The embodiment of the application provides an element detection method, an element detection device, electronic equipment and a storage medium, which can solve the problem that the efficiency is low when a list in a software page example is identified in the prior art.
The embodiment of the application provides an element detection method, which is used for detecting nodes to be judged in a software page and comprises the following steps:
the node to be judged is obtained, wherein the node to be judged comprises a plurality of target sub-nodes, and each target sub-node comprises a first number of features;
for each target sub-node, carrying out weighting processing on a first number of features included in the target sub-node to obtain target weighted features of the target sub-node, wherein the dimension of the target weighted features is the first number;
According to the target weighting characteristics corresponding to the target child nodes, determining the similarity between every two target child nodes to obtain a plurality of similarity operation results;
determining a target operation result with a numerical value exceeding a preset similarity from the similarity operation results; and if the non-repeated number of the target child nodes corresponding to the target operation result exceeds a preset threshold, determining the node to be judged as the target element.
The embodiment of the application also provides an element detection device, which comprises: the method is used for detecting the node to be judged in the software page and comprises the following steps:
the node obtaining unit is used for obtaining the node to be judged, wherein the node to be judged comprises a plurality of target sub-nodes, and each target sub-node comprises a first number of features;
the weighting processing unit is used for carrying out weighting processing on a first number of features included in each target sub-node to obtain target weighted features of the target sub-nodes, wherein the dimension of the target weighted features is the first number;
the similarity determining unit is used for determining the similarity between every two target child nodes according to the target weighting characteristics corresponding to the target child nodes to obtain a plurality of similarity operation results;
The target result unit is used for determining a target operation result with a numerical value exceeding a preset similarity from the plurality of similarity operation results;
and the node first judging unit is used for determining the node to be judged as the target element when the non-repeated number of the target sub-nodes corresponding to the target operation result exceeds a preset threshold value.
In some embodiments, the weighted processing unit includes:
a normalization subunit, configured to normalize each feature in the first number of features included in the target child node to obtain a first number of normalized results;
and the factor multiplication subunit is used for multiplying each normalization processing result with the corresponding characteristic weight factor to obtain a first number of dimensions, wherein the target weighting characteristic is a vector with the first number of dimensions.
In some embodiments, the similarity determination unit includes:
a sub-node obtaining sub-unit, configured to obtain a first sub-node corresponding to the first feature vector and a second sub-node corresponding to the second feature vector, where the first feature vector and the second feature vector are any two target weighting features of the plurality of target weighting features, and the first sub-node and the second sub-node are two target sub-nodes of the plurality of target sub-nodes;
A cosine subunit, configured to calculate a cosine similarity value of the first feature vector and the second feature vector when no child node exists in the first child node and the second child node;
and the similarity subunit is used for calculating the similarity of the first sub-node and the second sub-node according to a preset weight value and a cosine similarity value of the first feature vector and the second feature vector.
In some embodiments, the apparatus further comprises:
and the integral similarity unit is used for calculating the integral similarity of the first sub-node and the second sub-node when the first sub-node and the second sub-node both have sub-nodes.
In some embodiments, the global similarity unit is specifically configured to: and calculating a weighted average of the target cosine similarity value and the target child node average similarity value, wherein the weighted average is the overall similarity, the target cosine similarity value is the cosine similarity value of the first feature vector and the second feature vector, and the target child node average similarity value is the average similarity value of the child nodes of the first child node and the second child node.
In some embodiments, the apparatus further comprises:
a secondary computing unit, configured to compute an overall similarity between a child node of the first child node and a child node of the second child node, where the overall similarity is recorded as a secondary overall similarity;
and the weighted average obtaining unit is used for obtaining a weighted average value of the secondary overall similarity, wherein the weighted average value of the secondary overall similarity is the average similarity value of the target child nodes.
In some embodiments, the apparatus further comprises:
and the node second judging unit is used for determining that the node to be judged is not the target element when the non-repeated number of the target child nodes corresponding to the target operation result does not exceed a preset threshold value.
The embodiment of the application also provides electronic equipment, which comprises a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute steps in any one of the element detection methods provided by the embodiments of the present application.
The embodiment of the application also provides a computer readable storage medium, which stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor to execute the steps in any element detection method provided by the embodiment of the application.
The embodiment of the application can acquire the node to be determined comprising a plurality of target sub-nodes, wherein each target sub-node comprises a first number of characteristics. And for each target sub-node, carrying out weighting processing on the first number of the features included in the target sub-node, so that the target weighting features corresponding to each target sub-node can be obtained. Then calculating the similarity between every two of the plurality of target sub-nodes according to the target weighting characteristics corresponding to each target sub-node respectively, so as to obtain a plurality of similarity operation results; each similarity operation result corresponds to two target child nodes. And then obtaining a similarity operation result with the value exceeding the preset similarity, and marking the similarity operation result as a target operation result. Comparing the non-repeated number of the target sub-nodes corresponding to the target operation result with a preset threshold value, and if the non-repeated number of the target sub-nodes is larger than the preset threshold value, determining the node to be judged as a target element.
In the application, a plurality of target sub-nodes subordinate to the node to be judged can be processed, in the processing process, the target weighting characteristics can be generated according to the first number of characteristics included in the target sub-nodes, the similarity between every two target sub-nodes is obtained according to the target weighting characteristics, and whether the node to be judged is a target element is further determined according to the similarity between the target sub-nodes. That is, determining whether the target element depends on the similarity between the target child nodes, and in making the similarity determination, it is necessary to depend on a first number of features included in each target child node; therefore, whether the node to be judged is the target element depends on the first number of features included in each target child node or not is judged, and the element detection method provided by the embodiment of the application can be more accurately executed due to more depending features, so that the detection efficiency is improved compared with the prior art.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1a is a schematic view of a scenario of an element detection method according to an embodiment of the present application;
FIG. 1b is a schematic flow chart of an element detection method according to an embodiment of the present application;
FIG. 1c shows a specific schematic of a static software page design script;
FIG. 1d shows a schematic diagram of a dependency of a target child node a and a target child node b;
FIG. 2 is a schematic flow chart of a specific implementation of the element detection method according to the embodiment of the present application;
FIG. 3 is a schematic diagram of a structure of an element detecting device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
The embodiment of the application provides an element detection method, an element detection device, electronic equipment and a storage medium.
The element detection device can be integrated in an electronic device, and the electronic device can be a terminal, a server and other devices. The terminal can be a mobile phone, a tablet computer, an intelligent Bluetooth device, a notebook computer, a personal computer (Personal Computer, PC) or the like; the server may be a single server or a server cluster composed of a plurality of servers.
In some embodiments, the element detecting apparatus may also be integrated in a plurality of electronic devices, for example, the element detecting apparatus may be integrated in a plurality of servers, and the element detecting method of the present application is implemented by the plurality of servers.
In some embodiments, the server may also be implemented in the form of a terminal.
For example, referring to fig. 1a, the electronic device may obtain the node to be determined, where the node to be determined includes a plurality of target sub-nodes, each of the target sub-nodes includes a first number of features; for each target sub-node, carrying out weighting processing on a first number of features included in the target sub-node to obtain target weighted features of the target sub-node, wherein the dimension of the target weighted features is the first number; according to the target weighting characteristics corresponding to the target child nodes, determining the similarity between every two target child nodes to obtain a plurality of similarity operation results; determining a target operation result with a numerical value exceeding a preset similarity from the similarity operation results; and if the non-repeated number of the target child nodes corresponding to the target operation result exceeds a preset threshold, determining the node to be judged as the target element.
The following will describe in detail. The numbers of the following examples are not intended to limit the preferred order of the examples.
In this embodiment, an element detection method is provided, as shown in fig. 1b, and the specific flow of the element detection method may be as follows steps 110 to 150:
110. and acquiring the node to be judged, wherein the node to be judged comprises a plurality of target sub-nodes, and each target sub-node comprises a first number of features.
The node to be judged is a node in the static software page design manuscript, and whether the node to be judged belongs to the target element or not is judged. The software page design draft is a design drawing of one of the pages of the software to be developed that is presented by a designer. The target element is an element in the software page design draft that needs to be paid attention to by a software engineer, and for example, the target element may be a list element. List elements are containers aggregated from a series of similar nodes. The target element may be other elements besides a list element, such as a card element, a graphic element, and the like. For convenience of description, the target element is exemplified as a list element.
The target child node is a child node subordinate to the node to be judged. Referring to FIG. 1c for details, FIG. 1c shows a schematic representation of a static software page design. As shown in fig. 1c, the group background 102, the group head portrait 103, the group name 104, the group introduction information 105, and the group population 106 are all child nodes of the group 10, and the group 10 is a parent node of the group background 102, the group head portrait 103, the group name 104, the group introduction information 105, and the group population 106. Group online population 101 is a child node of group background 102, and group background 102 is a parent node of group online population 101.
Each target child node includes a first number of features. The specific numerical values of the first quantity should not be construed as limiting the application. Features a parameter that reflects some inherent property of the node.
Alternatively, in one embodiment, the first number may specifically take the value of 15, and the 15 features may be represented by f i Indicating that i takes a value between 1 and 15. The 15 features may be: depth of the target child node in the whole rendering tree, index value Index of the target child node in the child node corresponding to the father node (i.e. the node to be judged), number child of the target child node, font size Font of the target child node, font Color of the target child node, width of the target child node in the software page design draft, height of the target child node in the software page design draft, lateral offset X of the upper left coordinate of the target child node relative to the upper left coordinate of the father node corresponding to the node to be judged, longitudinal offset Y of the upper left coordinate of the target child node relative to the upper left coordinate of the father node corresponding to the node to be judged, and lower right coordinate of the target child node relative to the lower right coordinate of the father node corresponding to the node to be judged And a lateral offset X2Edge, a longitudinal offset Y2Edge of a lower Right coordinate of the target child node relative to a lower Right coordinate of a corresponding parent node (i.e., a node to be determined), a Left distance Left between the target child node and a Left sibling node in a horizontal direction, a Right distance Right between the target child node and a Right sibling node in a horizontal direction, an upper distance Top between the target child node and an upper sibling node in a vertical direction, and a lower distance Bottom between the target child node and a lower sibling node in a vertical direction.
Wherein a plurality of child nodes belonging to the same parent node are sibling nodes. For details, please refer to fig. 1c, wherein the group background 102, the group head portrait 103, the group name 104, the group introduction information 105, and the group number 106 are sibling nodes, and fig. 1c illustrates 6 groups: the group A game player 1, the group A game player water blowing group, the group A game friend making group 1, the group A game player 2, the group A game friend making group 2 and the group A game player 3 are brother nodes.
120. And for each target sub-node, carrying out weighting processing on a first number of features included in the target sub-node to obtain target weighted features of the target sub-node, wherein the dimension of the target weighted features is the first number.
For each feature in the first number of features, each feature has its own corresponding feature weight factor, so that the target weighting feature corresponding to each target child node can be obtained by multiplying each feature by its corresponding feature weight factor. The dimension of the target weighted feature is the same as the number of features of the target child node in value, and the first number is the same as the number of features of the target child node.
Alternatively, in one embodiment, step 120 may specifically include the following steps 121 to 122:
121. and carrying out normalization processing on each feature in the first number of features included in the target child node to obtain a first number of normalization processing results.
Each feature in the first number of features has a respective corresponding feature maximum value, and each feature of the target child node can perform ratio operation with the corresponding feature maximum value, thereby obtainingA first number of normalized processing results. The features mentioned above are denoted by f i The representation continues the explanation and can be represented by f i ' represents a first number of normalized processing results.
122. Multiplying each normalization processing result by a corresponding feature weight factor to obtain a first number of dimensions, wherein the target weight feature is a vector with the first number of dimensions.
Continuing with the above example, each normalized result f i ' all have self-corresponding characteristic weight factors w i The value of the characteristic weight factor can be set manually by a developer according to development experience and actual conditions of a project to be developed; for more important features, a higher value of the feature weight factor may be set, where the feature weight factor may be at [0,2 ]]Between them.
Multiplying the first number of normalized processing results by the corresponding feature weight factors to obtain a 1×first number of target weighted features, and if the first number is 15, marking the corresponding target weighted features as
130. And determining the similarity between every two target child nodes according to the target weighting characteristics corresponding to the target child nodes, and obtaining a plurality of similarity operation results.
Each of the plurality of similarity operation results corresponds to two target child nodes. Two target child nodes with high similarity tend to be the same type, and some properties of the nodes, such as arrangement, size, etc., are also the same.
Optionally, in an embodiment, the step 130 may specifically include the following steps 131 to 134:
131. And acquiring a first sub-node corresponding to the first feature vector and a second sub-node corresponding to the second feature vector.
The first feature vector and the second feature vector are any two target weighting features in the target weighting features, and the first sub-node and the second sub-node are two target sub-nodes in the target sub-nodes.
The method comprises the steps that a plurality of target sub-nodes included in a node to be judged can be provided with 5 target sub-nodes, and the target sub-nodes are respectively: the target sub-node a, the target sub-node b, the target sub-node c, the target sub-node d and the target sub-node e can be any two of the 5 target sub-nodes; the first child node may be the target child node a, and the second child node may be the target child node b.
132. And if no child node exists in the first child node and the second child node, calculating cosine similarity values of the first feature vector and the second feature vector.
133. And calculating the similarity of the first sub-node and the second sub-node according to a preset weight value and a cosine similarity value of the first feature vector and the second feature vector.
In the case that the first child node and the second child node have no child node, when calculating the similarity between the first child node and the second child node, the formula may be as follows:
Sim total (a,b)＝Sim self (a,b)×(1-weight)+Sim child (a, b) calculating the overall similarity Sim of the first child node and the second child node total (a, b). Wherein Sim is self (a, b) is cosine similarity value of the first feature vector and the second feature vector, weight is preset weight value, sim child (a, b) is an average similarity value of a child node of a first child node and a child node of the second child node. Sim in case of no child nodes of the first and second child nodes child And (a, b) takes a value of 1, the overall similarity calculation formula can be modified into: sim (Sim) total (a,b)＝Sim self (a, b) × (1-weight) +weight. The similarity between the first child node and the second child node can be calculated by using the formula.
According to the formulaCalculating cosine similarity value Sim of first feature vector and second feature vector self (a, b) wherein->For the first feature vector, ++>Is a first feature vector;
134. if the first child node and the second child node both have child nodes, calculating the overall similarity of the first child node and the second child node.
In the case that the first child node and the second child node have child nodes, sim child (a, b) no longer takes on a value of 1, and can therefore be calculated according to the formula Sim total (a,b)＝Sim self (a,b)×(1-weight)+Sim child (a, b) calculating the overall similarity Sim of the first child node and the second child node total (a,b)。
Optionally, in a specific embodiment, the step of "calculating the overall similarity between the first child node and the second child node" includes:
and calculating a weighted average value of the target cosine similarity value and the average similarity value of the target child nodes, wherein the weighted average value is the overall similarity.
In this embodiment, the target cosine similarity value is a cosine similarity value of the first feature vector and the second feature vector, i.e. Sim self The calculation method of the target cosine similarity value is described above, and will not be described here.
The average similarity value of the target child nodes is the average similarity value of the child nodes of the first child node and the child nodes of the second child node, namely Sim child (a,b)。
Optionally, in a specific embodiment, before calculating the weighted average value of the target cosine similarity value and the target child node average similarity value, the target child node average similarity value needs to be calculated. The specific calculation method of the average similarity value of the target child nodes comprises the following steps:
Calculating the overall similarity of the child node of the first child node and the child node of the corresponding second child node, and recording the overall similarity as a secondary overall similarity;
and obtaining a weighted average value of the secondary overall similarity, wherein the weighted average value of the secondary overall similarity is the average similarity value of the target child nodes.
The first sub-node can be provided with m sub-nodes in total, and correspondingly, the second sub-node can be provided with m sub-nodes in total, so that any sub-node a of the first sub-node cj And a in the second child node cj Corresponding child node b cj Can be according to the formula Sim total (a cj ,b cj )＝Sim self (a cj ,b cj )×(1-weight)+Sim child (a cj ,b cj ) Xweight calculation a cj And b cj Is of secondary overall similarity Sim total (a cj ,b cj )。
Since the first sub-node and the second sub-node share m sub-nodes, m secondary overall similarities can be calculated, and a weighted average of m secondary overall similarities can be calculated, where the weighted average of m secondary overall similarities is the average similarity value of the target sub-nodes.
I.e. according to the formula:calculating average similarity value Sim of target child nodes child (a, b). Wherein each secondary overall similarity Sim total (a cj ,b cj ) Corresponding impact weight cj Can be set manually by a developer according to working experience and requirements of software development projects, weight cj The value range of (2) is [0,1 ]]，weight cj Satisfy->
For details, please refer to fig. 1d, the target node a may have two nodes, namely a node a1 and a node a2, wherein the node a2 itself further has a node a21; the target sub-node b has two sub-nodes, namely a sub-node b1 and a sub-node b2, wherein the sub-node b2 also has a sub-node b21; when the similarity operation result between the target child node a and the target child node b is calculated by using the steps, the method specifically comprises the following steps:
according to the formula Sim total (a,b)＝Sim self (a,b)×(1-weight)+Sim child (a, b) x weight, wherein,
since the target child node a has two child nodes a1 and a2 and the target child node b has two child nodes b1 and b2, sim child (a,b)＝Sim total (a 1 ,b 1 )*weight c1 +Sim total (a 2 ,b 2 )*weight c2 . Wherein weight is c1 Weight(s) c2 Is manually valued by a developer, weight c1 Weight(s) c2 The value range of (2) is [0,1 ]]And weight is weight c1 +weight c2 ＝1。
The secondary overall similarity Sim between a1 and b1 total (a 1 ,b 1 ) Calculated according to the following formula:
Sim total (a 1 ,b 1 )＝Sim self (a 1 ,b 1 )×(1-weight)+Sim child (a 1 ,b 1 ) Xweight, see FIG. 1d for details, and Sim since neither a1 nor b1 has a child node child (a 1 ,b 1 ) The value is 1.
The above changes are: sim (Sim) total (a 1 ,b 1 )＝Sim self (a 1 ,b 1 ) X (1-weight) +weight. Wherein, the liquid crystal display device comprises a liquid crystal display device,
the secondary overall similarity Sim between a2 and b2 total (a 2 ,b 2 ) Calculated according to the following formula:
Sim total (a 2 ,b 2 )＝Sim self (a 2 ,b 2 )×(1-weight)+Sim child (a 2 ,b 2 ) Xweight, see FIG. 1d for details, since a2 has only one child node a21, b2 has only one child node b21, sim child (a 2 ,b 2 ) The weighted average operation is no longer necessary, so:
Sim child (a 2 ,b 2 )＝Sim total (a 21 ,b 21 )。
wherein Sim is total (a 21 ,b 21 )＝Sim self (a 21 ,b 21 )×(1-weight)+Sim child (a 21 ,b 21 )×weight。
For details, please refer to fig. 1d, and because a21 has no child node and b21 has no child node, sim child (a 21 ,b 21 ) The value is 1; the above can be modified as follows:
Sim total (a 21 ,b 21 )＝Sim self (a 21 ,b 21 )×(1-weight)+weight。
wherein, the liquid crystal display device comprises a liquid crystal display device,
as can be seen from the above-mentioned similarity calculation results of the target child node a and the target child node b, the calculation method of the similarity calculation result provided by the application can continuously carry out recursive calculation according to the child nodes existing in the node until the calculation reaches the child node at the bottommost layer. The operation process fully considers the subordinate relations among the nodes, considers the importance degree of the nodes while considering the subordinate relations, and sets a weight value according to the importance degree of the nodes; therefore, the obtained similarity operation result can be more accurate.
140. And determining a target operation result with the numerical value exceeding the preset similarity from the similarity operation results.
The preset similarity is a preset similarity value, and the specific numerical value of the similarity value should not be construed as limiting the application. For example, the preset similarity may take a value of 0.3, or may take other values, such as 0.4.
By repeating the steps 131 to 134, the similarity between every two of the plurality of target child nodes can be obtained, so that a plurality of similarity calculation results can be obtained. Continuing with the above example, for a total of 5 target child nodes included in the node to be determined, the target child nodes are respectively: under the conditions of the target sub-node a, the target sub-node b, the target sub-node c, the target sub-node d and the target sub-node e, the following similarity operation results can be obtained together:
similarity of the target sub-node a and the target sub-node b, similarity of the target sub-node a and the target sub-node c, similarity of the target sub-node a and the target sub-node d, and similarity of the target sub-node a and the target sub-node e;
similarity of the target sub-node b and the target sub-node c, similarity of the target sub-node b and the target sub-node d, and similarity of the target sub-node b and the target sub-node e;
similarity of the target child node c and the target child node d, and similarity of the target child node c and the target child node e;
similarity of the target child node d and the target child node e; and 10 similarity operation results.
And comparing the 10 similarity operation results with preset similarity respectively, so that a plurality of similarity operation results with values exceeding the preset similarity can be obtained, and a plurality of similarity operation results with values exceeding the preset similarity are all recorded as target operation results.
150. And if the non-repeated number of the target child nodes corresponding to the target operation result exceeds a preset threshold, determining the node to be judged as the target element.
The preset threshold is a preset value threshold, which may take on a value of 3, or may take on other values, such as a value of 4, and the specific value of the preset threshold should not be construed as limiting the present application.
Since each target operation result corresponds to two target child nodes, there may be a case where the same target child node repeatedly appears. Thus, for a repeatedly occurring target child node, it can be noted once, no matter how many times the target child node repeatedly occurs. For example, the target calculation result may include: the similarity of the target child node a and the target child node b, the similarity of the target child node a and the target child node c, and the similarity of the target child node c and the target child node e. It is clear that, for the above-mentioned target operation result, the target sub-node a and the target sub-node c both appear twice, and when the non-repetition number is counted in step 150, the non-repetition number of the target sub-node corresponding to the target operation result is 4 times for the target sub-node a and the target sub-node c, respectively, the target sub-node a is regarded as appearing once, the target sub-node b appears once, the target sub-node c is regarded as appearing once, and the target sub-node e appears once.
If the number of non-repetitions exceeds the preset threshold, it is indicated that the number of target child nodes with higher similarity (higher than the preset similarity) in the plurality of target child nodes is greater, so that a parent node (i.e., a node to be determined) common to the plurality of target child nodes can be determined as the target element. When the similarity between the target sub-nodes is judged, the method provided by the embodiment utilizes the importance degrees respectively corresponding to the different characteristics of the target sub-nodes, so that the judging process of the node to be judged can be more accurate.
Optionally, in a specific implementation, after step 140, the embodiment of the present application may further include the following steps: and if the non-repeated number of the target child nodes corresponding to the target operation result does not exceed a preset threshold, determining that the node to be judged is not the target element.
If the number of non-repetitions does not exceed the preset threshold, it is indicated that the number of target sub-nodes with higher similarity (higher than the preset similarity) is smaller, so that it may be determined that: a parent node (i.e., a node to be determined) common to a plurality of target child nodes is not a target element.
The method and the device can acquire the node to be determined comprising a plurality of target sub-nodes, wherein each target sub-node comprises a first number of features. And for each target sub-node, carrying out weighting processing on the first number of the features included in the target sub-node, so that the target weighting features corresponding to each target sub-node can be obtained. Then calculating the similarity between every two of the plurality of target sub-nodes according to the target weighting characteristics corresponding to each target sub-node respectively, so as to obtain a plurality of similarity operation results; each similarity operation result corresponds to two target child nodes. And then obtaining a similarity operation result with the value exceeding the preset similarity, and marking the similarity operation result as a target operation result. Comparing the non-repeated number of the target sub-nodes corresponding to the target operation result with a preset threshold value, and if the non-repeated number of the target sub-nodes is larger than the preset threshold value, determining the node to be judged as a target element.
In the application, a plurality of target sub-nodes subordinate to the node to be judged can be processed, in the processing process, the target weighting characteristics can be generated according to the first number of characteristics included in the target sub-nodes, the similarity between every two target sub-nodes is obtained according to the target weighting characteristics, and whether the node to be judged is a target element is further determined according to the similarity between the target sub-nodes. That is, determining whether the target element depends on the similarity between the target child nodes, and in making the similarity determination, it is necessary to depend on a first number of features included in each target child node; therefore, whether the node to be judged is the target element depends on the first number of features included in each target child node or not is judged, and the element detection method provided by the embodiment of the application can be more accurately executed due to more depending features, so that the detection efficiency is improved compared with the prior art.
The method described in the above embodiments will be described in further detail below.
In this embodiment, a method according to an embodiment of the present application will be described in detail taking an example that the target element is a list element and the first number of features includes 15 features.
Wherein, 15 characteristics are respectively: the Depth of the target child node in the whole rendering tree is Depth, the target child node is in a child node Index value Index of a corresponding father node (i.e. a node to be judged), the number of child nodes of the target child node is child num, the Font size of the target child node is Font, the Font Color of the target child node is Color of the target child node, the target child node is Width of a software page design draft, the target child node is at the Height of the software page design draft, the Left upper coordinate of the target child node is in a transverse offset X of the Left upper coordinate of the target child node relative to the Left upper coordinate of the corresponding father node (i.e. the node to be judged), the Left upper coordinate of the target child node is in a longitudinal offset Y of the Left upper coordinate of the corresponding father node (i.e. the node to be judged), the Right lower coordinate of the target child node is in a transverse offset X2Edge of the Right lower coordinate of the corresponding father node (i.e. the node to be judged), the Right lower coordinate of the target child node is in a vertical offset Y2Edge of the Right lower coordinate of the corresponding to the father node (i.e. the node to be judged), and the Right upper brother of the target child node is in a vertical distance of the Right lower brothers from the Right lower brothers of the target node to the Right lower node.
As shown in fig. 2, a specific flow of the element detection method is as follows:
201. and obtaining a node to be judged, wherein the node to be judged comprises a plurality of target sub-nodes, and each target sub-node comprises 15 characteristics.
The 15 features are respectively: depth, index, childNum, food, color, width, height, X, Y, X2Edge, Y2Edge, left, right, top, bottom.
202. And for each target sub-node, carrying out normalization processing on each of 15 features included in the target sub-node to obtain 15 normalization processing results.
203. And multiplying each normalized processing result in the 15 normalized processing results with a corresponding characteristic weight factor to obtain a target weighted characteristic with 15 dimensions.
204. And acquiring a first sub-node corresponding to the first feature vector and a second sub-node corresponding to the second feature vector, wherein the first feature vector and the second feature vector are any two target weighting features in the target weighting features, and the first sub-node and the second sub-node are two target sub-nodes in the target sub-nodes.
205. If no child node exists in the first child node and the second child node, cosine similarity values of the first feature vector and the second feature vector are calculated, and similarity of the first child node and the second child node is calculated according to a preset weight value and the cosine similarity values of the first feature vector and the second feature vector, wherein the similarity is a similarity operation result of the first child node and the second child node.
206. If the first sub-node and the second sub-node both have sub-nodes, calculating the overall similarity of the first sub-node and the second sub-node, wherein the overall similarity is a weighted average value of a target cosine similarity value and a target sub-node average similarity value; the overall similarity is a similarity operation result of the first child node and the second child node.
The target cosine similarity value is the cosine similarity value of the first feature vector and the second feature vector, and the target sub-node average similarity value is the average similarity value of the sub-nodes of the first sub-node and the second sub-node.
The calculation method of the average similarity value of the target child nodes is as follows:
calculating the overall similarity of the child node of the first child node and the child node of the corresponding second child node, and recording the overall similarity as a secondary overall similarity; and obtaining a weighted average value of the secondary overall similarity, wherein the weighted average value of the secondary overall similarity is the average similarity value of the target child nodes.
207. By executing steps 204 to 206 a plurality of times, the similarities between the target child nodes are obtained and recorded as the results of the similarity operations.
208. From the plurality of similarity operation results, a target operation result having a value exceeding 0.3 is determined.
209. And if the non-repeated number of the target child nodes corresponding to the target operation result exceeds 3, determining the node to be judged as a list element.
Steps 201 to 209 correspond to the same element detection method in the previous embodiment, and will not be described here.
As can be seen from the above, the present application can process a plurality of target sub-nodes subordinate to the node to be determined, and in the process of processing, the target weighted feature can be generated depending on the first number of features included in the target sub-nodes, and the similarity between every two target sub-nodes is obtained according to the target weighted feature, and further, whether the node to be determined is a target element is determined according to the similarity between every two target sub-nodes. That is, determining whether the target element depends on the similarity between the target child nodes, and in making the similarity determination, it is necessary to depend on a first number of features included in each target child node; therefore, whether the node to be judged is the target element depends on the first number of the features included in each target sub-node is judged, and the importance degree of the features is referred to while the features are relied on due to the fact that the features are more relied on, so that the element detection method provided by the embodiment of the application can be accurately executed.
The application can improve the detection accuracy and the detection efficiency.
In order to better implement the method, the embodiment of the application also provides an element detection device which can be integrated in electronic equipment, wherein the electronic equipment can be a terminal, a server and the like. The terminal can be a mobile phone, a tablet personal computer, an intelligent Bluetooth device, a notebook computer, a personal computer and other devices; the server may be a single server or a server cluster composed of a plurality of servers.
For example, in the present embodiment, a method according to an embodiment of the present application will be described in detail by taking an example in which an element detecting device is specifically integrated in an electronic device.
For example, as shown in fig. 3, the element detecting device may include:
a node obtaining unit 301, configured to obtain the node to be determined, where the node to be determined includes a plurality of target sub-nodes, each of the target sub-nodes includes a first number of features;
a weighting processing unit 302, configured to perform a weighting process on a first number of features included in the target child node for each target child node, to obtain target weighted features of the target child node, where a dimension of the target weighted features is the first number;
A similarity determining unit 303, configured to determine, according to the target weighted features corresponding to the target child nodes, a similarity between every two target child nodes, so as to obtain a plurality of similarity operation results;
a target result unit 304, configured to determine a target operation result with a value exceeding a preset similarity from the multiple similarity operation results;
and the node first judging unit 305 is configured to determine the node to be judged as the target element when the non-repetition number of the target child nodes corresponding to the target operation result exceeds a preset threshold.
In some embodiments, the weighting processing unit 302 includes:
a normalization subunit, configured to normalize each feature in the first number of features included in the target child node to obtain a first number of normalized results;
and the factor multiplication subunit is used for multiplying each normalization processing result with the corresponding characteristic weight factor to obtain a first number of dimensions, wherein the target weighting characteristic is a vector with the first number of dimensions.
In some embodiments, the similarity determination unit 303 includes:
a sub-node obtaining sub-unit, configured to obtain a first sub-node corresponding to the first feature vector and a second sub-node corresponding to the second feature vector, where the first feature vector and the second feature vector are any two target weighting features of the plurality of target weighting features, and the first sub-node and the second sub-node are two target sub-nodes of the plurality of target sub-nodes;
A cosine subunit, configured to calculate a cosine similarity value of the first feature vector and the second feature vector when no child node exists in the first child node and the second child node;
and the similarity subunit is used for calculating the similarity of the first sub-node and the second sub-node according to a preset weight value and a cosine similarity value of the first feature vector and the second feature vector.
In some embodiments, the apparatus further comprises:
and the integral similarity unit is used for calculating the integral similarity of the first sub-node and the second sub-node when the first sub-node and the second sub-node both have sub-nodes.
In some embodiments, the global similarity unit is specifically configured to: and calculating a weighted average of the target cosine similarity value and the target child node average similarity value, wherein the weighted average is the overall similarity, the target cosine similarity value is the cosine similarity value of the first feature vector and the second feature vector, and the target child node average similarity value is the average similarity value of the child nodes of the first child node and the second child node.
In some embodiments, the apparatus further comprises:
a secondary computing unit, configured to compute an overall similarity between a child node of the first child node and a child node of the second child node, where the overall similarity is recorded as a secondary overall similarity;
and the weighted average obtaining unit is used for obtaining a weighted average value of the secondary overall similarity, wherein the weighted average value of the secondary overall similarity is the average similarity value of the target child nodes.
In some embodiments, the apparatus further comprises:
and the node second judging unit is used for determining that the node to be judged is not the target element when the non-repeated number of the target child nodes corresponding to the target operation result does not exceed a preset threshold value.
In the implementation, each unit may be implemented as an independent entity, or may be implemented as the same entity or several entities in any combination, and the implementation of each unit may be referred to the foregoing method embodiment, which is not described herein again.
As can be seen from the above, the present application can process a plurality of target sub-nodes subordinate to the node to be determined, and in the process of processing, the target weighted feature can be generated depending on the first number of features included in the target sub-nodes, and the similarity between every two target sub-nodes is obtained according to the target weighted feature, and further, whether the node to be determined is a target element is determined according to the similarity between every two target sub-nodes. That is, determining whether the target element depends on the similarity between the target child nodes, and in making the similarity determination, it is necessary to depend on a first number of features included in each target child node; therefore, whether the node to be judged is the target element depends on the first number of the features included in each target sub-node is judged, and the importance degree of the features is referred to while the features are relied on due to the fact that the features are more relied on, so that the element detection method provided by the embodiment of the application can be accurately executed.
The application can improve the detection accuracy and the detection efficiency.
The embodiment of the application also provides electronic equipment which can be a terminal, a server and other equipment. The terminal can be a mobile phone, a tablet computer, an intelligent Bluetooth device, a notebook computer, a personal computer and the like; the server may be a single server, a server cluster composed of a plurality of servers, or the like.
In some embodiments, the element detecting apparatus may also be integrated in a plurality of electronic devices, for example, the element detecting apparatus may be integrated in a plurality of servers, and the element detecting method of the present application is implemented by the plurality of servers.
In this embodiment, a detailed description will be given taking an example in which the electronic device of this embodiment is an electronic device, for example, as shown in fig. 4, which shows a schematic structural diagram of the electronic device according to the embodiment of the present application, specifically:
the electronic device may include one or more processor cores 401, one or more computer-readable storage media memory 402, a power supply 403, an input module 404, and a communication module 405, among other components. Those skilled in the art will appreciate that the electronic device structure shown in fig. 4 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components. Wherein:
The processor 401 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 402, and calling data stored in the memory 402. In some embodiments, processor 401 may include one or more processing cores; in some embodiments, processor 401 may integrate an application processor that primarily processes operating systems, user interfaces, applications, and the like, with a modem processor that primarily processes wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 401.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by executing the software programs and modules stored in the memory 402. The memory 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc. In addition, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.
The electronic device also includes a power supply 403 for powering the various components, and in some embodiments, the power supply 403 may be logically connected to the processor 401 by a power management system, such that charge, discharge, and power consumption management functions are performed by the power management system. The power supply 403 may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
The electronic device may also include an input module 404, which input module 404 may be used to receive entered numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
The electronic device may also include a communication module 405, and in some embodiments the communication module 405 may include a wireless module, through which the electronic device may wirelessly transmit over a short distance, thereby providing wireless broadband internet access to the user. For example, the communication module 405 may be used to assist a user in e-mail, browsing web pages, accessing streaming media, and so forth.
Although not shown, the electronic device may further include a display unit or the like, which is not described herein. In particular, in this embodiment, the processor 401 in the electronic device loads executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 executes the application programs stored in the memory 402, so as to implement various functions as follows:
the node to be judged is obtained, wherein the node to be judged comprises a plurality of target sub-nodes, and each target sub-node comprises a first number of features; for each target sub-node, carrying out weighting processing on a first number of features included in the target sub-node to obtain target weighted features of the target sub-node, wherein the dimension of the target weighted features is the first number; according to the target weighting characteristics corresponding to the target child nodes, determining the similarity between every two target child nodes to obtain a plurality of similarity operation results; determining a target operation result with a numerical value exceeding a preset similarity from the similarity operation results; and if the non-repeated number of the target child nodes corresponding to the target operation result exceeds a preset threshold, determining the node to be judged as the target element.
The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.
To this end, embodiments of the present application provide a computer readable storage medium having stored therein a plurality of instructions capable of being loaded by a processor to perform any of the steps of the element detection method provided by the embodiments of the present application. For example, the instructions may perform the steps of:
the node to be judged is obtained, wherein the node to be judged comprises a plurality of target sub-nodes, and each target sub-node comprises a first number of features; for each target sub-node, carrying out weighting processing on a first number of features included in the target sub-node to obtain target weighted features of the target sub-node, wherein the dimension of the target weighted features is the first number; according to the target weighting characteristics corresponding to the target child nodes, determining the similarity between every two target child nodes to obtain a plurality of similarity operation results; determining a target operation result with a numerical value exceeding a preset similarity from the similarity operation results; and if the non-repeated number of the target child nodes corresponding to the target operation result exceeds a preset threshold, determining the node to be judged as the target element.
Wherein the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
According to one aspect of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the methods provided in the various alternative implementations of the element detection aspect of the software page provided in the above embodiments.
The instructions stored in the storage medium may perform steps in any element detection method provided by the embodiments of the present application, so that the beneficial effects that any element detection method provided by the embodiments of the present application can be achieved, which are detailed in the previous embodiments and are not described herein.
The foregoing has described in detail the methods, apparatuses, electronic devices and computer readable storage medium for detecting elements provided by the embodiments of the present application, and specific examples have been applied to illustrate the principles and embodiments of the present application, where the above description of the embodiments is only for helping to understand the methods and core ideas of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, the present description should not be construed as limiting the present application.
Claims (10)
1. The element detection method is characterized by comprising the following steps of:
the node to be judged is obtained, wherein the node to be judged comprises a plurality of target sub-nodes, and each target sub-node comprises a first number of features;
for each target sub-node, carrying out weighting processing on a first number of features included in the target sub-node to obtain target weighted features of the target sub-node, wherein the dimension of the target weighted features is the first number;
according to the target weighting characteristics corresponding to the target child nodes, determining the similarity between every two target child nodes to obtain a plurality of similarity operation results;
determining a target operation result with a numerical value exceeding a preset similarity from the similarity operation results;
and if the non-repeated number of the target child nodes corresponding to the target operation result exceeds a preset threshold, determining the node to be judged as a target element.
2. The method of claim 1, wherein weighting the first number of features included in the target child node to obtain the target weighted feature of the target child node comprises:
Normalizing each feature in the first number of features included in the target child node to obtain a first number of normalized processing results;
multiplying each normalization processing result by a corresponding feature weight factor to obtain a first number of dimensions, wherein the target weight feature is a vector with the first number of dimensions.
3. The method of claim 1, wherein the determining the similarity between the target child nodes according to the target weighted features corresponding to the target child nodes to obtain a plurality of similarity operation results includes:
acquiring a first sub-node corresponding to a first feature vector and a second sub-node corresponding to a second feature vector, wherein the first feature vector and the second feature vector are any two target weighting features in a plurality of target weighting features, and the first sub-node and the second sub-node are two target sub-nodes in a plurality of target sub-nodes;
if no child node exists in the first child node and the second child node, calculating cosine similarity values of the first feature vector and the second feature vector;
And calculating the similarity of the first sub-node and the second sub-node according to a preset weight value and a cosine similarity value of the first feature vector and the second feature vector.
4. The method of claim 3, wherein after the obtaining the first child node corresponding to the first feature vector and the second child node corresponding to the second feature vector, the method further comprises:
if the first child node and the second child node both have child nodes, calculating the overall similarity of the first child node and the second child node.
5. The method of claim 4, wherein the calculating the overall similarity of the first child node and the second child node comprises:
and calculating a weighted average of the target cosine similarity value and the target child node average similarity value, wherein the weighted average is the overall similarity, the target cosine similarity value is the cosine similarity value of the first feature vector and the second feature vector, and the target child node average similarity value is the average similarity value of the child nodes of the first child node and the second child node.
6. The method of claim 5, wherein prior to said calculating a weighted average of the target cosine similarity value and the target child node average similarity value, the method further comprises:
calculating the overall similarity of the child node of the first child node and the child node of the corresponding second child node, and recording the overall similarity as a secondary overall similarity;
and obtaining a weighted average value of the secondary overall similarity, wherein the weighted average value of the secondary overall similarity is the average similarity value of the target child nodes.
7. The method of claim 1, wherein after determining a target operation result having a value exceeding a preset similarity from the plurality of similarity operation results, the method further comprises:
and if the non-repeated number of the target child nodes corresponding to the target operation result does not exceed a preset threshold, determining that the node to be judged is not the target element.
8. The element detection device is characterized by being used for detecting nodes to be judged in a software page and comprising the following components:
the node obtaining unit is used for obtaining the node to be judged, wherein the node to be judged comprises a plurality of target sub-nodes, and each target sub-node comprises a first number of features;
The weighting processing unit is used for carrying out weighting processing on a first number of features included in each target sub-node to obtain target weighted features of the target sub-nodes, wherein the dimension of the target weighted features is the first number;
the similarity determining unit is used for determining the similarity between every two target child nodes according to the target weighting characteristics corresponding to the target child nodes to obtain a plurality of similarity operation results;
the target result unit is used for determining a target operation result with a numerical value exceeding a preset similarity from the plurality of similarity operation results;
and the node first judging unit is used for determining the node to be judged as a target element when the non-repeated number of the target sub-nodes corresponding to the target operation result exceeds a preset threshold value.
9. An electronic device comprising a processor and a memory, the memory storing a plurality of instructions; the processor loads instructions from the memory to perform the steps in the element detection method according to any one of claims 1 to 7.
10. A computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the steps in the element detection method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210177109.7A CN116700710A (en) | 2022-02-25 | 2022-02-25 | Element detection method, element detection device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210177109.7A CN116700710A (en) | 2022-02-25 | 2022-02-25 | Element detection method, element detection device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116700710A true CN116700710A (en) | 2023-09-05 |
Family
ID=87829894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210177109.7A Pending CN116700710A (en) | 2022-02-25 | 2022-02-25 | Element detection method, element detection device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116700710A (en) |
-
2022
- 2022-02-25 CN CN202210177109.7A patent/CN116700710A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7711735B2 (en) | User segment suggestion for online advertising | |
| CN110245687B (en) | User classification method and device | |
| GB2544857A (en) | Multimedia document summarization | |
| WO2022142551A1 (en) | Form processing method and apparatus, and medium and computer device | |
| CN110362832B (en) | Paragraph merging method and device, storage medium and electronic equipment | |
| CN109918678B (en) | Method and device for identifying field meaning | |
| CN104516635A (en) | Content display management | |
| CN108650104A (en) | The treating method and apparatus of one population message | |
| CN111125658A (en) | Method, device, server and storage medium for identifying fraudulent users | |
| CN110941961A (en) | Information clustering method and device, electronic equipment and storage medium | |
| CN114564620A (en) | Graph data storage method and system and computer equipment | |
| CN110929285B (en) | Method and device for processing private data | |
| CN110210572B (en) | Image classification method, device, storage medium and equipment | |
| EP3611629A1 (en) | Photo processing method and apparatus, and computer device | |
| CN115878761B (en) | Event context generation method, device and medium | |
| CN116700710A (en) | Element detection method, element detection device, electronic equipment and storage medium | |
| JP7219011B2 (en) | typesetness score for tables | |
| CN110781410A (en) | Community detection method and device | |
| US20230419015A1 (en) | Font recommendation, topic extraction, and training data generation | |
| CN113220949B (en) | Construction method and device of private data identification system | |
| CN113076395B (en) | Semantic model training and search display method, device, equipment and storage medium | |
| JP5885956B2 (en) | Font matching | |
| CN111652741B (en) | User preference analysis method, device and readable storage medium | |
| CN110278250B (en) | Terminal selection method, device and storage medium | |
| CN106886486B (en) | Method and device for evaluating user terminal use attribute |
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 |