Feature analysis method and device, electronic equipment and storage medium

Abstract

The invention provides a feature analysis method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence, and the method comprises the steps: obtaining meta-information of each to-be-analyzed feature; the meta-information comprises a feature name, an analyzer and a dependency parameter; combining all the same meta-information of the resolver; establishing a feature dependence tree containing each piece of meta-information; the feature name of the father node in the feature dependency tree corresponds to the dependency parameter of the child node; and based on the topological sequence of the feature dependency tree, calling the parser of each node to obtain the feature corresponding to each node. According to the method, the information of the same feature elements of the resolvers is combined, the more simplified feature dependence tree is established, the resolvers of the nodes are called based on the topological sequence of the feature dependence tree, the total calling frequency of the resolvers is reduced, and therefore time consumed in the feature obtaining stage can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a feature analysis method and device, electronic equipment and a storage medium. BACKGROUND

[0002] When a business recommendation is made using an artificial intelligence model, each feature related to the business needs to be input into the model, which requires obtaining each feature. The feature is obtained by calling a parser to analyze a remote procedure call (RPC) request. The current feature acquisition method has the problem of calling the parser too many times, resulting in a long time consumption in the feature acquisition stage. SUMMARY

[0003] The present application provides a feature analysis method, device, electronic equipment and storage medium to solve the technical problem of long time consumption in the feature acquisition stage in the prior art.

[0004] The present application provides a feature analysis method, comprising: obtaining meta information of each feature to be analyzed; the meta information includes a feature name, a parser and a dependent parameter; merging each meta information of the same parser; establishing a feature dependency tree containing each meta information; the feature name of the parent node in the feature dependency tree corresponds to the dependent parameter of the child node; based on the topological order of the feature dependency tree, calling the parser of each node to obtain the feature corresponding to each node.

[0005] According to the feature analysis method provided by the present application, the parser of each node is called to obtain the feature corresponding to each node, comprising: parallelly calling the parser of each node in the same level to obtain the feature corresponding to each node in the same level.

[0006] According to the feature analysis method provided by the present application, the parser of each node is called to obtain the feature corresponding to each node, comprising: calling the parser of the parent node to obtain the feature corresponding to the parent node; determining the dependent parameter of the child node in the feature corresponding to the parent node; calling the parser of the child node based on the dependent parameter of the child node to obtain the feature corresponding to the child node.

[0007] According to the feature analysis method provided by the present application, the dependent parameter of the child node is determined in the feature corresponding to the parent node, comprising: If the feature corresponding to the parent node has only one, the feature corresponding to the parent node is directly taken as the dependent parameter of the child node; If the feature corresponding to the parent node has multiple, the feature corresponding to the parent node is taken as an index, and a feature same as the index is found in the dependent parameter of the child node as the dependent parameter of the child node.

[0008] According to the feature analysis method provided by the application, before the topological order of the feature dependency tree is used to call the parser of each node to obtain the feature corresponding to each node, the method further comprises: obtaining context information; taking the context information as the dependent parameter of the root node of the feature dependency tree.

[0009] According to the feature analysis method provided by the application, the meta information further comprises a cache identifier; After the topological order of the feature dependency tree is used to call the parser of each node to obtain the feature corresponding to each node, the method further comprises: If the cache identifier indicates that the feature is enabled for caching, the obtained feature is stored in the cache.

[0010] The application further provides a feature analysis device, comprising: An obtaining module is configured to obtain meta information of each feature to be analyzed; the meta information comprises a feature name, a parser and a dependent parameter; A merging module is configured to merge each meta information with the same parser; An establishing module is configured to establish a feature dependency tree comprising each meta information; the feature name of a parent node in the feature dependency tree corresponds to the dependent parameter of a child node; An analysis module is configured to call the parser of each node based on the topological order of the feature dependency tree to obtain the feature corresponding to each node.

[0011] The application further provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the feature analysis method according to any one of the above when executing the program.

[0012] The application further provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the feature analysis method according to any one of the above.

[0013] The application further provides a computer program product comprising a computer program, wherein the computer program is executable by a processor to implement the feature analysis method according to any one of the above.

[0014] The feature analysis method, device, electronic equipment and storage medium provided by the present application combine each feature meta information of the same parser, establish a more simplified feature dependency tree, call the parser of each node based on the topological order of the feature dependency tree, reduce the total number of parser calls, and thus the time consumption of the feature acquisition stage can be reduced. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0016] Figure 1 is a schematic diagram of the feature dependency tree in the prior art.

[0017] Figure 2 is a schematic diagram of the feature analysis method provided by the present application.

[0018] Figure 3 is a schematic diagram of the feature dependency tree provided by the present application.

[0019] Figure 4 is a schematic diagram of the feature and its dependent parameters provided by the present application.

[0020] Figure 5 is a schematic diagram of the feature tree provided by the present application.

[0021] Figure 6 is a schematic diagram of the feature analysis device provided by the present application.

[0022] Figure 7 is a schematic diagram of the electronic equipment provided by the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of the present application more clear, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0024] The feature acquisition stage of the large model needs to first construct a feature dependency tree composed of feature meta information, and then call the parser of each meta information according to the topological order of the feature dependency tree, so as to obtain the required features.

[0025] The metadata of a feature can include the feature name, parser, dependency parameters, and cacheable flag. The naming convention for the feature name is "feature entity.feature name". The parser is the processor used to parse the feature, responsible for retrieving the feature from the RPC request; a single parser can parse multiple features. The dependency parameters are the parameters that the parser depends on; these can be context information or other features. The parser must obtain the dependency parameters before it can parse a feature. The cacheable flag indicates whether the feature is cached. If caching is enabled, the same feature can be retrieved directly from the cache without calling the parser the next time. The structure of the metadata can be: { "name": "feature entity.feature name", "parser": "xxx", "dependency": [ "xxx" "xxx" ], "cacheable": false / true } Here, `cacheable` being `false` means caching is disabled, and `cacheable` being `true` means caching is enabled.

[0026] An example of a feature dependency tree in existing technology is provided. Assume the features to be parsed are User.A, User.B, User.C, User.D, User.E, User.F, and Order.A, and the metadata of each feature is as follows: { "name": "User.A" "parser": "ParserUser" "dependency": [ "context: userID" ], "cacheable": false }; (Named Meta-information A) { "name": "User.B" "parser": "ParserUserIdentity", "dependency": [ "context:userID" ], "cacheable":false }; (named MetaInfoB) { "name":"User.C", "parser":"ParserUser", "dependency":[ "context:userID" ], "cacheable":false }; (named MetaInfoC) { "name":"User.D", "parser":"ParserAccount", "dependency":[ "User.C" "User.B" ], "cacheable":false }; (named MetaInfoD) { "name":"User.E", "parser":"ParserAccount", "dependency":[ "User.C" "User.B" ], "cacheable":false }; (named MetaInfoE) { "name":"User.F", "parser":"ParserOrderCount", "dependency":[ "Order.A" "User.E" ], "cacheable":false }; (named MetaInfoF) { "name":"Order.A", "parser" : "ParserOrder", "dependency" : [ "User.A" "User.D" ], "cacheable" : false } ; (named as meta information O) The feature dependency tree established in the prior art is shown in Figure 1 The process of obtaining each feature is as follows: Obtain the userID; Call the parser ParserUser based on the userID to obtain the feature User.C, call the parser ParserUserIdentity based on the userID to obtain the feature User.B, and call the parser ParserAccount based on the feature User.C and the feature User.B to obtain the feature User.E; Call the parser ParserUser based on the userID to obtain the feature User.C, call the parser ParserUserIdentity based on the userID to obtain the feature User.B, and call the parser ParserAccount based on the feature User.C and the feature User.B to obtain the feature User.D; Call the parser ParserUser based on the userID to obtain the feature User.A, and call the parser ParserOrder based on the feature User.D and the feature User.A to obtain the feature Order.A; Call the parser ParserOrderCount based on the feature Order.A and the feature User.E to obtain the feature User.F.

[0027] It can be seen that the above process repeatedly calls the parser ParserUser 3 times, repeatedly calls the parser ParserUserIdentity 2 times, repeatedly calls the parser ParserAccount 2 times, and the total number of calls of the parser is 9 times.

[0028] The feature parsing method, device, electronic equipment and storage medium provided by the present application will be described below. Figures 2-7 The feature parsing method, device, electronic equipment and storage medium provided by the present application will be described below.

[0029] Figure 2 The flowchart of the feature parsing method provided by the present application is shown in Figure 1 , which includes but is not limited to steps S1, S2, S3 and S4.

[0030] Step S1, obtaining meta information of each feature to be parsed; the meta information includes feature name, parser and dependency parameter.

[0031] The following will be illustrated by taking each meta information in Figure 1 as an example.

[0032] Step S2, merging each meta information with the same parser.

[0033] Figure 1 The parser of meta information A and C in is ParserUser, so the meta information obtained after merging meta information A and C is: { "name":["User.A","User.C"] "parser":"ParserUser", "dependency":[ "context:userID" ], "cacheable":false };(named as meta information AC) The parser of meta information D and E in is ParserAccount, so the meta information obtained after merging meta information D and E is: { "name":["User.D","User.E"] "parser":"ParserAccount", "dependency":[ "User.C" "User.B" ], "cacheable":false };(named as meta information DE)

[0034] Therefore, the final meta information AC, B, DE, F and O are obtained.

[0035] Step S3, establishing a feature dependency tree containing each meta information; the feature name of the parent node in the feature dependency tree corresponds to the dependency parameter of the child node. Figure 3 The feature dependency tree established in step S3 is shown in

[0036] .

[0037] The feature name User.D of parent node DE corresponds to the dependency parameter User.D of child node O, and the feature name User.A of parent node AC corresponds to the dependency parameter User.A of child node O.

[0038] The feature name Order.A of parent node O corresponds to the dependency parameter Order.A of child node F, and the feature name User.E of parent node DE corresponds to the dependency parameter User.E of child node F.

[0039] Step S4: Based on the topological order of the feature dependency tree, call the parser of each node to obtain the features corresponding to each node.

[0040] In one embodiment, the present invention invokes the parser of each node to obtain the features corresponding to each node, which may specifically include: Call the parser of the parent node to obtain the features corresponding to the parent node; Determine the dependency parameters of the child node from the features corresponding to the parent node; The parser of the child node is invoked based on the dependency parameters of the child node to obtain the features corresponding to the child node.

[0041] Specifically, based on Figure 3 Based on the topological order, the parser ParserUser of the parent node AC is called to obtain the features User.A and User.C corresponding to the parent node AC. The dependency parameter User.C of the child node DE is determined from the features User.A and User.C corresponding to the parent node AC. The parser ParserUserIdentity of the parent node B is called to obtain the feature User.B corresponding to the parent node B. The feature User.B corresponding to the parent node B is used as the dependency parameter User.B of the child node DE. Based on the dependency parameters User.B and User.C of the child node DE, the parser ParserAccount of the child node DE is called to obtain the features User.D and User.E corresponding to the child node DE.

[0042] Determine the dependency parameter User.A of child node O from the features User.A and User.C corresponding to parent node AC, and determine the dependency parameter User.D of child node O from the features User.D and User.E corresponding to parent node DE; call the parser ParserOrder of child node O based on the dependency parameters User.A and User.D of child node O to obtain the feature Order.A corresponding to child node O.

[0043] The dependent parameter User.E of the child node F is determined in the features User.D and User.E corresponding to the parent node DE, and the feature Order.A corresponding to the parent node O is taken as the dependent parameter Order.A of the child node F; the parser ParserOrderCount of the child node F is called based on the dependent parameters User.E and Order.A of the child node F, and the feature User.F corresponding to the child node F is obtained.

[0044] It can be seen that the present application only calls the parser ParserUser once, the parser ParserUserIdentity once, the parser ParserAccount once, the parser ParserOrder once, and the parser ParserOrderCount once, and the total number of calls of the parser is reduced from 9 times to 5 times.

[0045] It can be seen from the above that the feature analysis method of the present application combines each feature meta information of the same parser, establishes a more simplified feature dependency tree, calls the parser of each node based on the topological order of the feature dependency tree, and reduces the total number of calls of the parser, so that the time consumption of the feature acquisition stage can be reduced.

[0046] In one embodiment, in step S4, the parser of each node is called to obtain the feature corresponding to each node, which can specifically include: The parsers of each node at the same level are called in parallel to obtain the features corresponding to each node at the same level.

[0047] For example, Figure 3 The node AC and the node B are at the same level, so the parser ParserUser and the parser ParserUserIdentity can be called in parallel, so that the feature acquisition efficiency can be improved.

[0048] In one embodiment, the present application determines the dependent parameter of the child node in the feature corresponding to the parent node, which can specifically include: If the feature corresponding to the parent node is only one, the feature corresponding to the parent node is directly taken as the dependent parameter of the child node; If the feature corresponding to the parent node has multiple, the feature corresponding to the parent node is taken as an index, and the same feature as the index is found in the dependent parameters of the child node as the dependent parameter of the child node.

[0049] Specifically, the features corresponding to the parent node AC are User.A and User.C, so User.A and User.C are taken as an index, and User.C is found in the dependent parameters User.B and User.C of the child node DE as the dependent parameter of the child node DE.

[0050] The parent node B corresponds to the feature User.B, and directly takes User.B as the dependent parameter of the child node DE.

[0051] The parent node AC corresponds to the features User.A and User.C, and takes User.A and User.C as indexes to find User.A as the dependent parameter of the child node O in the dependent parameters User.A and User.D of the child node O.

[0052] The parent node DE corresponds to the features User.D and User.E, and takes User.D and User.E as indexes to find User.D as the dependent parameter of the child node O in the dependent parameters User.A and User.D of the child node O.

[0053] The parent node DE corresponds to the features User.D and User.E, and takes User.D and User.E as indexes to find User.E as the dependent parameter of the child node F in the dependent parameters User.E and Order.A of the child node F.

[0054] The parent node O corresponds to the feature Order.A, and directly takes Order.A as the dependent parameter of the child node F.

[0055] In this way, the dependent parameters of the child nodes can be determined in the features corresponding to the parent nodes by indexing.

[0056] In one embodiment, before step S4, the feature parsing method of the present application can further include: obtaining context information; taking the context information as the dependent parameter of the root node of the feature dependency tree.

[0057] Considering that Figure 3 the root nodes AC and B in the above example, the parser call is based on the context information uesrID, so the context information uesrID needs to be obtained first, and the context information uesrID is taken as the dependent parameter of the root nodes AC and B, so as to realize the call of the parsers ParserUser and ParserUserIdentity.

[0058] In one embodiment, after step S4, the feature parsing method of the present application can further include: If the cache identifier indicates that the feature is enabled for caching, the obtained feature is stored in the cache.

[0059] If the cache identifier of the node is true, the obtained feature can be stored in the cache, and the feature can be directly extracted from the cache next time, so as to improve the feature acquisition efficiency.

[0060] After the resolver of each node is invoked, the features and dependent parameters corresponding to the nodes are associated, as shown in Figure 4 The features corresponding to the nodes are associated to form a feature tree, and the nodes of the feature tree are traversed to obtain a row of features input to the recommendation model.

[0061] As shown in Figure 5 , first, the context information uesrID is added to the feature tree Feature Tree, then the features User.A, User.B and User.C are taken as the child nodes of the node uesrID to realize the association of uesrID and the features User.A, User.B and User.C; the features User.D and User.E are taken as the child nodes of the nodes User.B and User.C to realize the association of the features User.B, User.C and the features User.D and User.E; the feature Order.A is taken as the child node of the nodes User.A and User.D to realize the association of the feature Order.A and the features User.A and User.D; the feature User.F is taken as the child node of the nodes Order.A and User.E to realize the association of the feature User.F and the features Order.A and User.E.

[0062] In this way, the memory consumption in the feature association stage can be reduced.

[0063] As shown in Figure 6 , the feature analysis device provided by the application comprises: The acquisition module is configured to acquire the meta information of each feature to be analyzed, wherein the meta information comprises a feature name, a resolver and a dependent parameter; The merging module is configured to merge each meta information with the same resolver; The establishing module is configured to establish a feature dependency tree comprising the meta information, wherein the feature name of a parent node in the feature dependency tree corresponds to the dependent parameter of a child node; The analysis module is configured to invoke the resolver of each node based on the topological order of the feature dependency tree to obtain the feature corresponding to each node.

[0064] The analysis module can also be configured to: Invoke the resolvers of the nodes at the same level in parallel to obtain the features corresponding to the nodes at the same level.

[0065] The analysis module can also be configured to: Invoke the resolver of the parent node to obtain the feature corresponding to the parent node; Determine the dependent parameter of the child node in the feature corresponding to the parent node; Invoke the resolver of the child node based on the dependent parameter of the child node to obtain the feature corresponding to the child node.

[0066] The analysis module can also be used for: If the parent node corresponds to only one feature, the feature corresponding to the parent node is directly used as the dependent parameter of the child node; If the parent node corresponds to multiple features, the feature corresponding to the parent node is used as an index, and the same feature as the index is searched in the dependent parameter of the child node as the dependent parameter of the child node.

[0067] The acquisition module can also be used to acquire context information. The establishment module can also be used to use the context information as the dependent parameter of the root node of the feature dependency tree.

[0068] The feature analysis device can also include a storage module for storing the obtained feature in the cache if the cache identifier indicates that the feature is enabled for caching.

[0069] It should be noted that the feature analysis device provided by the present application can execute the feature analysis method described in any of the above embodiments during actual operation, and this embodiment will not be described here.

[0070] Figure 7 is a structural diagram of an electronic device provided by the present application, as Figure 7 As shown, the electronic device can include a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete mutual communication through the communication bus. The processor can call the logical instructions in the memory to execute the feature analysis method, which includes: acquiring the meta information of each to-be-analyzed feature; the meta information includes the feature name, the parser and the dependent parameter; merging each meta information with the same parser; establishing a feature dependency tree containing each meta information; the feature name of the parent node in the feature dependency tree corresponds to the dependent parameter of the child node; based on the topological order of the feature dependency tree, calling the parser of each node to obtain the feature corresponding to each node.

[0071] In addition, the logic instructions in the above-mentioned memory can be realized in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0072] In another aspect, the present application also provides a computer program product, which comprises a computer program stored on a non-transitory computer readable storage medium, and the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute the feature analysis method provided by the above-mentioned embodiments, and the method comprises: obtaining meta information of each feature to be analyzed; the meta information comprises a feature name, an analyzer and a dependent parameter; merging each meta information with the same analyzer; establishing a feature dependency tree comprising each meta information; the feature name of the parent node in the feature dependency tree corresponds to the dependent parameter of the child node; based on the topological order of the feature dependency tree, calling the analyzer of each node to obtain the feature corresponding to each node.

[0073] In another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the feature analysis method provided by the above-mentioned embodiments, and the method comprises: obtaining meta information of each feature to be analyzed; the meta information comprises a feature name, an analyzer and a dependent parameter; merging each meta information with the same analyzer; establishing a feature dependency tree comprising each meta information; the feature name of the parent node in the feature dependency tree corresponds to the dependent parameter of the child node; based on the topological order of the feature dependency tree, calling the analyzer of each node to obtain the feature corresponding to each node.

[0074] The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0075] Those skilled in the art can clearly understand the implementation of the various embodiments by means of software and necessary general hardware platforms through the description of the above embodiments, and of course, the embodiments can also be implemented by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in the various embodiments or some parts of the embodiments.

[0076] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for some technical features thereof; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A feature parsing method, characterized in that, include: Obtain the metadata of each feature to be parsed; The metadata includes feature name, parser, and dependency parameters; Merge the metadata that are identical in the parser; Construct a feature dependency tree containing all the aforementioned meta-information; The feature name of the parent node in the feature dependency tree corresponds to the dependency parameter of the child node; Based on the topological order of the feature dependency tree, the parser of each node is invoked to obtain the features corresponding to each node.

2. The feature parsing method according to claim 1, characterized in that, The process of calling the parser of each node to obtain the features corresponding to each node includes: The parsers of each node at the same level are invoked in parallel to obtain the features corresponding to each node at the same level.

3. The feature parsing method according to claim 1, characterized in that, The process of calling the parser of each node to obtain the features corresponding to each node includes: The parser of the parent node is invoked to obtain the features corresponding to the parent node; The dependency parameters of the child node are determined from the features corresponding to the parent node; The parser of the child node is invoked based on the dependency parameters of the child node to obtain the features corresponding to the child node.

4. The feature parsing method according to claim 3, characterized in that, Determining the dependency parameter of the child node from the features corresponding to the parent node includes: If the parent node has only one feature, then the feature corresponding to the parent node is directly used as the dependency parameter of the child node. If the parent node has multiple features, then the feature corresponding to the parent node is used as an index, and the feature with the same index is searched in the dependency parameters of the child node as the dependency parameter of the child node.

5. The feature parsing method according to claim 1, characterized in that, Before invoking the parser of each node based on the topological order of the feature dependency tree to obtain the features corresponding to each node, the method further includes: Obtain context information; The context information is used as the dependency parameter of the root node of the feature dependency tree.

6. The feature parsing method according to claim 1, characterized in that, The metadata also includes a cache identifier; After obtaining the features corresponding to each node by calling the parser of each node based on the topological order of the feature dependency tree, the process further includes: If the cache identifier indicates that caching is enabled for the feature, then the obtained feature will be stored in the cache.

7. A feature parsing device, characterized in that, include: The acquisition module is used to acquire the metadata of each feature to be parsed; The metadata includes feature name, parser, and dependency parameters; The merging module is used to merge the metadata that are identical in the parser; A module is established to build a feature dependency tree containing the various metadata. The feature name of the parent node in the feature dependency tree corresponds to the dependency parameter of the child node; The parsing module is used to call the parser of each node based on the topological order of the feature dependency tree to obtain the features corresponding to each node.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the feature parsing method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the feature parsing method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the feature parsing method as described in any one of claims 1 to 6.

Images