Content recognition method and system for microservices

Abstract

Embodiments of the present application provide a content recognition method and system for microservices, obtaining to-be-recognized content data, and determining a content semantic description of the to-be-recognized content data; loading the to-be-recognized content data into each content recognition network respectively, generating a first label mapping parameter associated with each prior content label field; determining a feature matching degree between the content semantic description and each candidate content label feature, generating a second label mapping parameter associated with each candidate content label of the to-be-recognized content data; and determining content label recognition data corresponding to the to-be-recognized content data according to each first label mapping parameter and each second label mapping parameter. Thus, the accuracy of subsequent content recognition is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a content recognition method and system for micro services. BACKGROUND

[0002] With the rapid development of Internet technology and information technology, application software architecture has undergone major changes, and traditional monolithic architecture has been transformed into a new micro service architecture. In the operation process, content recognition is required in many cases, such as recognizing the conversation content of users in micro service applications. The content of micro services can be recognized according to the model of artificial intelligence, and the required information can be obtained from the content. However, the related technical scheme has low content recognition accuracy. SUMMARY

[0003] Therefore, the embodiments of the present application aim to provide a content recognition method and system for micro services, obtain to-be-recognized content data, and determine the content semantic description of the to-be-recognized content data; load the to-be-recognized content data into each content recognition network respectively, generate first label mapping parameters associated with each prior content label field; determine the feature matching degree between the content semantic description and each candidate content label feature, and generate second label mapping parameters associated with each candidate content label of the to-be-recognized content data; and determine the content label recognition data corresponding to the to-be-recognized content data according to each first label mapping parameter and each second label mapping parameter. Thus, the accuracy of subsequent content recognition is improved.

[0004] According to an aspect of the embodiments of the present application, a content recognition method and system for micro services are provided, and the method comprises:

[0005] Obtaining to-be-recognized content data of users in micro service applications, and determining the content semantic description of the to-be-recognized content data;

[0006] Loading the to-be-recognized content data into each content recognition network respectively, and generating first label mapping parameters associated with each prior content label field;

[0007] Determining the feature matching degree between the content semantic description and each candidate content label feature, and generating second label mapping parameters associated with each candidate content label of the to-be-recognized content data; wherein the candidate content label feature is associated with each candidate content label;

[0008] Determining the content label recognition data corresponding to the to-be-recognized content data according to each first label mapping parameter and each second label mapping parameter.

[0009] In an alternative implementation, the step of loading the content data to be identified into each content recognition network and generating a first tag mapping parameter associated with each prior content tag field includes:

[0010] Based on each content recognition network, the content data to be recognized is loaded into the target content recognition network to generate candidate tag mapping parameters for one or more prior content tag fields corresponding to the target content recognition network;

[0011] Based on each prior content tag field, determine one or more candidate tag mapping parameters associated with the target prior content tag field, and perform associated calculations on the one or more candidate tag mapping parameters to generate a first tag mapping parameter corresponding to the target prior content tag field.

[0012] In an alternative implementation, the method further includes:

[0013] Based on each candidate content tag, generate one or more first session content data associated with the target candidate content tag, and determine the content semantic description associated with the first session content data respectively;

[0014] Based on the semantic description association calculation of one or more content corresponding to the same candidate content tag, the candidate content tag features associated with each candidate content tag are determined.

[0015] In an alternative implementation, determining the content tag identification data corresponding to the content data to be identified based on each first tag mapping parameter and each second tag mapping parameter includes:

[0016] Determine a sequence including each prior content tag field and each candidate content tag, wherein the sequence includes one or more sequence nodes;

[0017] Based on each sequence node, the node label associated with the target sequence node is determined, and the first label mapping parameter and the second label mapping parameter of the target sequence node are identified and optimized based on the node label to determine the content label identification data.

[0018] In an alternative implementation, the method further includes:

[0019] If the label mapping parameters of the target sequence node include a first label mapping parameter or a second label mapping parameter, then the node label corresponding to the target sequence node is determined to be the first node label; or, if the label mapping parameters of the target sequence node include a first label mapping parameter and a second label mapping parameter, then the node label corresponding to the target sequence node is determined to be the second node label.

[0020] In an alternative implementation, the step of identifying and optimizing the first and second label mapping parameters of the target sequence nodes based on the node labels to determine the content label identification data includes:

[0021] If each node label is a first node label, then the mapping parameters of each first label and each second label are transformed according to rules to generate a third label mapping parameter corresponding to each sequence node, and the content label identification data corresponding to the content data to be identified is determined based on the third label mapping parameters; or, if each node label includes a second node label, then the first label mapping parameters and the second label mapping parameters of the target sequence node are correlated and calculated to generate a fourth label mapping parameter associated with the target sequence node, and the content label identification data corresponding to the content data to be identified is determined based on the fourth label mapping parameters corresponding to each sequence node.

[0022] In an alternative implementation, the method further includes:

[0023] The aforementioned content recognition networks undergo network knowledge learning, specifically including:

[0024] Obtain the template microservice session content data sequence corresponding to each initialized neural network; wherein, the template microservice session content data sequence includes one or more template microservice session content data, and the template microservice session content data includes second session content data associated with each prior content label field;

[0025] Based on each initialization neural network, the second session content data in the target template microservice session content data corresponding to the target initialization neural network is used as the input of the target initialization neural network, and the prior content tag field is used as the output of the target initialization neural network. The target initialization neural network is iteratively optimized to generate the iteratively optimized target initialization neural network.

[0026] The iteratively optimized target initialization neural network is re-initialized as the target initialization neural network and the above operation is repeated until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network.

[0027] In an alternative implementation, the step of re-initializing the target neural network as the target neural network after iterative optimization and returning to the above operation until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network, includes:

[0028] Retrieve content data from one or more test sessions;

[0029] The test session content data is loaded into the iteratively optimized target initialization neural network, and the prior content label field and corresponding reference label mapping parameters corresponding to each test session content data are output. The iteratively optimized target initialization neural network is then used as the target initialization neural network again.

[0030] Based on the set tag mapping parameters, each reference tag mapping parameter, and the corresponding prior content tag fields, the target session content data is determined from each test session content data;

[0031] The template microservice session content data sequence is enhanced based on the content data of each target session, and the enhanced template microservice session content data sequence is used to return to the step of performing network knowledge learning on the target initialization neural network until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network.

[0032] According to another aspect of the present invention, a content recognition method and system for microservices are provided, the system comprising:

[0033] The acquisition module is used to acquire the content data to be identified by the user in the microservice application and determine the content semantic description of the content data to be identified.

[0034] The first generation module is used to load the content data to be identified into each content recognition network and generate a first tag mapping parameter associated with each prior content tag field.

[0035] The second generation module is used to determine the feature matching degree between the content semantic description and the feature of each candidate content tag, and to generate a second tag mapping parameter that associates the content data to be identified with each candidate content tag; wherein, the feature of the candidate content tag is associated with each candidate content tag;

[0036] The determination module is used to determine the content tag identification data corresponding to the content data to be identified based on each first tag mapping parameter and each second tag mapping parameter.

[0037] According to another aspect of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store a computer program; and the processor is used to implement the content recognition method steps for microservices described above when executing the computer program.

[0038] According to another aspect of the present invention, a readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, can perform the steps of the above-described content recognition method for microservices.

[0039] To make the above-mentioned objects, features and advantages of the embodiments of the present invention more apparent and understandable, a detailed description will be given below in conjunction with the embodiments and the accompanying drawings. Attached Figure Description

[0040] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A schematic diagram of the components of a server provided in an embodiment of the present invention is shown;

[0042] Figure 2 This invention illustrates a flowchart of a content recognition method and system for microservices provided in an embodiment of the present invention.

[0043] Figure 3 The diagram illustrates a functional block diagram of a content recognition system for microservices, as provided in an embodiment of the present invention. Detailed Implementation

[0044] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] The terms “first,” “second,” “third,” etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0046] Figure 1 An exemplary component diagram of server 100 is shown. Server 100 may include one or more processors 104, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. Server 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. Without limitation, for example, storage medium 106 may include any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any storage medium can use any technology to store information. Further, any storage medium may provide volatile or non-volatile retention of information. Further, any storage medium may represent a fixed or removable component of server 100. In one case, server 100 may perform any operation of the associated instructions when processor 104 executes associated instructions stored in any storage medium or combination of storage media. Server 100 also includes one or more drive units 108 for interacting with any storage medium, such as hard disk drive units, optical disk drive units, etc.

[0047] Server 100 also includes input / output 110 (I / O) for receiving various inputs (via input unit 112) and providing various outputs (via output unit 114). A specific output mechanism may include a presentation device 116 and an associated graphical user interface (GUI) 118. Server 100 may also include one or more network interfaces 120 for exchanging data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0048] The communication unit 122 can be implemented in any manner, such as via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, or any combination thereof. The communication unit 122 may include any combination of hardwired links, wireless links, routers, gateway functions, name server 100, etc., governed by any protocol or combination of protocols.

[0049] Figure 2 This diagram illustrates a flowchart of a content recognition method and system for microservices provided by an embodiment of the present invention. The content recognition method and system for microservices can be derived from... Figure 1 The detailed steps of the content recognition method and system for microservices, as shown in the diagram, are described below for execution by server 100.

[0050] Step S110: Obtain the content data to be identified in the user's microservice application, and determine the semantic description of the content data to be identified;

[0051] Step S120: Load the content data to be identified into each content recognition network to generate a first tag mapping parameter associated with each prior content tag field;

[0052] Step S130: Determine the feature matching degree between the content semantic description and the feature of each candidate content tag, and generate a second tag mapping parameter that associates the content data to be identified with each candidate content tag; wherein, the candidate content tag feature is associated with each candidate content tag;

[0053] Step S140: Determine the content tag identification data corresponding to the content data to be identified based on each first tag mapping parameter and each second tag mapping parameter.

[0054] Based on the above steps, this embodiment acquires the content data to be identified and determines the semantic description of the content data; loads the content data to be identified into each content recognition network to generate first tag mapping parameters associated with each prior content tag field; determines the feature matching degree between the content semantic description and each candidate content tag feature, and generates second tag mapping parameters associated with each candidate content tag; and determines the content tag recognition data corresponding to the content data to be identified based on each first tag mapping parameter and each second tag mapping parameter. This improves the accuracy of subsequent content recognition.

[0055] In an alternative implementation, the step of loading the content data to be identified into each content recognition network and generating a first tag mapping parameter associated with each prior content tag field includes:

[0056] Based on each content recognition network, the content data to be recognized is loaded into the target content recognition network to generate candidate tag mapping parameters for one or more prior content tag fields corresponding to the target content recognition network;

[0057] Based on each prior content tag field, determine one or more candidate tag mapping parameters associated with the target prior content tag field, and perform associated calculations on the one or more candidate tag mapping parameters to generate a first tag mapping parameter corresponding to the target prior content tag field.

[0058] In an alternative implementation, the method further includes:

[0059] Based on each candidate content tag, generate one or more first session content data associated with the target candidate content tag, and determine the content semantic description associated with the first session content data respectively;

[0060] Based on the semantic description association calculation of one or more content corresponding to the same candidate content tag, the candidate content tag features associated with each candidate content tag are determined.

[0061] In an alternative implementation, determining the content tag identification data corresponding to the content data to be identified based on each first tag mapping parameter and each second tag mapping parameter includes:

[0062] Determine a sequence including each prior content tag field and each candidate content tag, wherein the sequence includes one or more sequence nodes;

[0063] Based on each sequence node, the node label associated with the target sequence node is determined, and the first label mapping parameter and the second label mapping parameter of the target sequence node are identified and optimized based on the node label to determine the content label identification data.

[0064] In an alternative implementation, the method further includes:

[0065] If the label mapping parameters of the target sequence node include a first label mapping parameter or a second label mapping parameter, then the node label corresponding to the target sequence node is determined to be the first node label; or, if the label mapping parameters of the target sequence node include a first label mapping parameter and a second label mapping parameter, then the node label corresponding to the target sequence node is determined to be the second node label.

[0066] In an alternative implementation, the step of identifying and optimizing the first and second label mapping parameters of the target sequence nodes based on the node labels to determine the content label identification data includes:

[0067] If each node label is a first node label, then the mapping parameters of each first label and each second label are transformed according to rules to generate a third label mapping parameter corresponding to each sequence node, and the content label identification data corresponding to the content data to be identified is determined based on the third label mapping parameters; or, if each node label includes a second node label, then the first label mapping parameters and the second label mapping parameters of the target sequence node are correlated and calculated to generate a fourth label mapping parameter associated with the target sequence node, and the content label identification data corresponding to the content data to be identified is determined based on the fourth label mapping parameters corresponding to each sequence node.

[0068] In an alternative implementation, the method further includes:

[0069] The aforementioned content recognition networks undergo network knowledge learning, specifically including:

[0070] Obtain the template microservice session content data sequence corresponding to each initialized neural network; wherein, the template microservice session content data sequence includes one or more template microservice session content data, and the template microservice session content data includes second session content data associated with each prior content label field;

[0071] Based on each initialization neural network, the second session content data in the target template microservice session content data corresponding to the target initialization neural network is used as the input of the target initialization neural network, and the prior content tag field is used as the output of the target initialization neural network. The target initialization neural network is iteratively optimized to generate the iteratively optimized target initialization neural network.

[0072] The iteratively optimized target initialization neural network is re-initialized as the target initialization neural network and the above operation is repeated until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network.

[0073] In an alternative implementation, the step of re-initializing the target neural network as the target neural network after iterative optimization and returning to the above operation until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network, includes:

[0074] Retrieve content data from one or more test sessions;

[0075] The test session content data is loaded into the iteratively optimized target initialization neural network, and the prior content label field and corresponding reference label mapping parameters corresponding to each test session content data are output. The iteratively optimized target initialization neural network is then used as the target initialization neural network again.

[0076] Based on the set tag mapping parameters, each reference tag mapping parameter, and the corresponding prior content tag fields, the target session content data is determined from each test session content data;

[0077] The template microservice session content data sequence is enhanced based on the content data of each target session, and the enhanced template microservice session content data sequence is used to return to the step of performing network knowledge learning on the target initialization neural network until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network.

[0078] Figure 3 This diagram illustrates a functional block diagram of a content recognition system 200 for microservices according to an embodiment of the present invention. The functions implemented by this content recognition system 200 for microservices correspond to the steps performed by the method described above. This content recognition system 200 for microservices can be understood as the server 100, or the processor of the server 100, or it can be understood as a component that implements the functions of the present invention under the control of the server 100, independent of the server 100 or the processor. Figure 3 As shown below, the functions of each functional module of the content recognition system 200 for microservices will be described in detail.

[0079] The acquisition module 210 is used to acquire the content data to be identified by the user in the microservice application and determine the content semantic description of the content data to be identified.

[0080] The first generation module 220 is used to load the content data to be identified into each content recognition network and generate a first tag mapping parameter associated with each prior content tag field.

[0081] The second generation module 230 is used to determine the feature matching degree between the content semantic description and the feature of each candidate content tag, and to generate a second tag mapping parameter associated with the content data to be identified and each candidate content tag; wherein, the candidate content tag feature is associated with each candidate content tag;

[0082] The determining module 240 is used to determine the content tag identification data corresponding to the content data to be identified based on each first tag mapping parameter and each second tag mapping parameter.

[0083] In an alternative implementation, the first generation module 220 is further configured to:

[0084] Based on each content recognition network, the content data to be recognized is loaded into the target content recognition network to generate candidate tag mapping parameters for one or more prior content tag fields corresponding to the target content recognition network;

[0085] Based on each prior content tag field, determine one or more candidate tag mapping parameters associated with the target prior content tag field, and perform associated calculations on the one or more candidate tag mapping parameters to generate a first tag mapping parameter corresponding to the target prior content tag field.

[0086] In an alternative implementation, the second generation module 230 is further configured to:

[0087] Based on each candidate content tag, generate one or more first session content data associated with the target candidate content tag, and determine the content semantic description associated with the first session content data respectively;

[0088] Based on the semantic description association calculation of one or more content corresponding to the same candidate content tag, the candidate content tag features associated with each candidate content tag are determined.

[0089] In an alternative implementation, the determining module 240 is further configured to:

[0090] Determine a sequence including each prior content tag field and each candidate content tag, wherein the sequence includes one or more sequence nodes;

[0091] Based on each sequence node, the node label associated with the target sequence node is determined, and the first label mapping parameter and the second label mapping parameter of the target sequence node are identified and optimized based on the node label to determine the content label identification data.

[0092] In an alternative implementation, the determining module 240 is further configured to:

[0093] If the label mapping parameters of the target sequence node include a first label mapping parameter or a second label mapping parameter, then the node label corresponding to the target sequence node is determined to be the first node label; or, if the label mapping parameters of the target sequence node include a first label mapping parameter and a second label mapping parameter, then the node label corresponding to the target sequence node is determined to be the second node label.

[0094] In an alternative implementation, the determining module 240 is further configured to:

[0095] If each node label is a first node label, then the mapping parameters of each first label and each second label are transformed according to rules to generate a third label mapping parameter corresponding to each sequence node, and the content label identification data corresponding to the content data to be identified is determined based on the third label mapping parameters; or, if each node label includes a second node label, then the first label mapping parameters and the second label mapping parameters of the target sequence node are correlated and calculated to generate a fourth label mapping parameter associated with the target sequence node, and the content label identification data corresponding to the content data to be identified is determined based on the fourth label mapping parameters corresponding to each sequence node.

[0096] In an alternative implementation, the first generation module 220 is further configured to:

[0097] The aforementioned content recognition networks undergo network knowledge learning, specifically including:

[0098] Obtain the template microservice session content data sequence corresponding to each initialized neural network; wherein, the template microservice session content data sequence includes one or more template microservice session content data, and the template microservice session content data includes second session content data associated with each prior content label field;

[0099] Based on each initialization neural network, the second session content data in the target template microservice session content data corresponding to the target initialization neural network is used as the input of the target initialization neural network, and the prior content tag field is used as the output of the target initialization neural network. The target initialization neural network is iteratively optimized to generate the iteratively optimized target initialization neural network.

[0100] The iteratively optimized target initialization neural network is re-initialized as the target initialization neural network and the above operation is repeated until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network.

[0101] In an alternative implementation, the first generation module 220 is further configured to:

[0102] Retrieve content data from one or more test sessions;

[0103] The test session content data is loaded into the iteratively optimized target initialization neural network, and the prior content label field and corresponding reference label mapping parameters corresponding to each test session content data are output. The iteratively optimized target initialization neural network is then used as the target initialization neural network again.

[0104] Based on the set tag mapping parameters, each reference tag mapping parameter, and the corresponding prior content tag fields, the target session content data is determined from each test session content data;

[0105] The template microservice session content data sequence is enhanced based on the content data of each target session, and the enhanced template microservice session content data sequence is used to return to the step of performing network knowledge learning on the target initialization neural network until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network.

[0106] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0107] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, it is intended that all variations falling within the meaning and scope of equivalents of the claims be included within the present invention.

Claims

1. A content recognition method for microservices, characterized in that, The method includes: Obtain the content data to be identified from the user in the microservice application, and determine the semantic description of the content data to be identified; The content data to be identified is loaded into each content recognition network to generate a first tag mapping parameter associated with each prior content tag field. Determine the feature matching degree between the semantic description of the content and the feature of each candidate content tag, and generate a second tag mapping parameter that associates the content data to be identified with each candidate content tag; wherein, the feature of the candidate content tag is associated with each candidate content tag; Based on each first tag mapping parameter and each second tag mapping parameter, determine the content tag identification data corresponding to the content data to be identified; The step of determining the content tag identification data corresponding to the content data to be identified based on each first tag mapping parameter and each second tag mapping parameter includes: Determine a sequence including each prior content tag field and each candidate content tag, wherein the sequence includes one or more sequence nodes; Based on each sequence node, the node label associated with the target sequence node is determined, and the first label mapping parameter and the second label mapping parameter of the target sequence node are identified and optimized based on the node label to determine the content label identification data.

2. The content recognition method for microservices according to claim 1, characterized in that, The step of loading the content data to be identified into each content recognition network and generating a first tag mapping parameter associated with each prior content tag field includes: Based on each content recognition network, the content data to be recognized is loaded into the target content recognition network to generate candidate tag mapping parameters for one or more prior content tag fields corresponding to the target content recognition network; Based on each prior content tag field, determine one or more candidate tag mapping parameters associated with the target prior content tag field, and perform associated calculations on the one or more candidate tag mapping parameters to generate a first tag mapping parameter corresponding to the target prior content tag field.

3. The content recognition method for microservices according to claim 1, characterized in that, Also includes: Based on each candidate content tag, generate one or more first session content data associated with the target candidate content tag, and determine the content semantic description associated with the first session content data respectively; Based on the semantic description association calculation of one or more content corresponding to the same candidate content tag, the candidate content tag features associated with each candidate content tag are determined.

4. The content recognition method for microservices according to claim 1, characterized in that, Also includes: If the label mapping parameters of the target sequence node include a first label mapping parameter or a second label mapping parameter, then the node label corresponding to the target sequence node is determined to be the first node label. Alternatively, if the label mapping parameters of the target sequence node include a first label mapping parameter and a second label mapping parameter, then the node label corresponding to the target sequence node is determined to be the second node label.

5. The content recognition method for microservices according to claim 4, characterized in that, The step of identifying and optimizing the first and second label mapping parameters of the target sequence nodes based on the node labels to determine content label identification data includes: If each node label is a first node label, then the mapping parameters of each first label and each second label are transformed according to rules to generate a third label mapping parameter corresponding to each sequence node, and the content label identification data corresponding to the content data to be identified is determined based on the third label mapping parameters; or, if each node label includes a second node label, then the first label mapping parameters and the second label mapping parameters of the target sequence node are correlated and calculated to generate a fourth label mapping parameter associated with the target sequence node, and the content label identification data corresponding to the content data to be identified is determined based on the fourth label mapping parameters corresponding to each sequence node.

6. The content recognition method for microservices according to claim 1, characterized in that, Also includes: The content recognition networks are subjected to network knowledge learning, specifically including: Obtain the template microservice session content data sequence corresponding to each initialized neural network; wherein, the template microservice session content data sequence includes one or more template microservice session content data, and the template microservice session content data includes second session content data associated with each prior content label field; Based on each initialization neural network, the second session content data in the target template microservice session content data corresponding to the target initialization neural network is used as the input of the target initialization neural network, and the prior content tag field is used as the output of the target initialization neural network. The target initialization neural network is iteratively optimized to generate the iteratively optimized target initialization neural network. The iteratively optimized target initialization neural network is used as the target initialization neural network again until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network.

7. The content recognition method for microservices according to claim 6, characterized in that, The step of reusing the iteratively optimized target initialization neural network as the target initialization neural network until the weight parameters of the target initialization neural network no longer change, and generating the corresponding content recognition network, includes: Retrieve content data from one or more test sessions; The test session content data is loaded into the iteratively optimized target initialization neural network, and the prior content label field and corresponding reference label mapping parameters corresponding to each test session content data are output. The iteratively optimized target initialization neural network is then used as the target initialization neural network again. Based on the set tag mapping parameters, each reference tag mapping parameter, and the corresponding prior content tag fields, the target session content data is determined from each test session content data; The template microservice session content data sequence is enhanced based on the content data of each target session, and the enhanced template microservice session content data sequence is used to return to the step of performing network knowledge learning on the target initialization neural network until the weight parameters of the target initialization neural network no longer change, thereby generating the corresponding content recognition network.

8. A content recognition system for microservices, characterized in that, include: The acquisition module is used to acquire the content data to be identified by the user in the microservice application and determine the content semantic description of the content data to be identified. The first generation module is used to load the content data to be identified into each content recognition network and generate a first tag mapping parameter associated with each prior content tag field. The second generation module is used to determine the feature matching degree between the content semantic description and the feature of each candidate content tag, and to generate a second tag mapping parameter that associates the content data to be identified with each candidate content tag; wherein, the feature of the candidate content tag is associated with each candidate content tag; The determination module is used to determine the content tag identification data corresponding to the content data to be identified based on each first tag mapping parameter and each second tag mapping parameter; The step of determining the content tag identification data corresponding to the content data to be identified based on each first tag mapping parameter and each second tag mapping parameter includes: Determine a sequence including each prior content tag field and each candidate content tag, wherein the sequence includes one or more sequence nodes; Based on each sequence node, the node label associated with the target sequence node is determined, and the first label mapping parameter and the second label mapping parameter of the target sequence node are identified and optimized based on the node label to determine the content label identification data.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the content recognition method for microservices as described in any one of claims 1-7.

Images