CN117992349A - Method, device, equipment and storage medium for recommending joint debugging test environment - Google Patents
Method, device, equipment and storage medium for recommending joint debugging test environment Download PDFInfo
- Publication number
- CN117992349A CN117992349A CN202410177998.6A CN202410177998A CN117992349A CN 117992349 A CN117992349 A CN 117992349A CN 202410177998 A CN202410177998 A CN 202410177998A CN 117992349 A CN117992349 A CN 117992349A
- Authority
- CN
- China
- Prior art keywords
- target
- joint debugging
- data
- environment
- scene
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 72
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 13
- 238000004891 communication Methods 0.000 description 10
- 238000011144 upstream manufacturing Methods 0.000 description 10
- 230000003993 interaction Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011981 development test Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The disclosure provides a recommendation method, device, equipment and storage medium of joint debugging test environment, relates to the field of data processing, and particularly relates to the technical fields of big data, big models and the like. The specific implementation scheme is as follows: identifying and obtaining target intention data, wherein the target intention data represents a target joint debugging scene needing joint debugging test; obtaining a target environment topology matched with the target intention data, wherein the target environment topology represents topology information of a joint debugging environment for realizing the target joint debugging scene, the topology information comprises N sub-scenes for realizing the target joint debugging scene and functional modules associated with each sub-scene in the N sub-scenes, and N is a natural number greater than or equal to 2.
Description
Technical Field
The disclosure relates to the technical field of data processing, in particular to the technical field of big data, big models and the like.
Background
The joint debugging test is a program functionality test of an upstream and a downstream multifunctional module which are carried out in the nearest on-line environment situation by communicating the upstream and the downstream environments of all the functional modules on a service line, and is indispensable in a large-scale development test project. At this time, if the joint debugging test of a certain specific service scenario is to be successfully performed, a tester is required to manually select a required functional module and a corresponding upstream and downstream module according to the specific service scenario, and the functional modules required by the joint debugging test of different service scenarios are also different, so that the existing joint debugging test strongly depends on the tester.
Disclosure of Invention
The disclosure provides a recommendation method, device, equipment and storage medium of joint debugging test environment.
According to an aspect of the present disclosure, there is provided a recommendation method of a joint debugging test environment, including:
Identifying and obtaining target intention data, wherein the target intention data represents a target joint debugging scene needing joint debugging test;
Obtaining a target environment topology matched with the target intention data, wherein the target environment topology represents topology information of a joint debugging environment for realizing the target joint debugging scene, the target environment topology comprises N sub-scenes for realizing the target joint debugging scene and functional modules associated with each sub-scene in the N sub-scenes, N is a natural number greater than or equal to 2, at least part of the functional modules associated with the sub-scenes have a dependency relationship, and the functional modules associated with different sub-scenes are different or at least the same.
According to another aspect of the present disclosure, there is provided a recommendation apparatus for a joint debugging test environment, including:
The identifying unit is used for identifying and obtaining target intention data, wherein the target intention data represents a target joint debugging scene which needs joint debugging test;
The matching unit is used for obtaining a target environment topology matched with the target intention data, wherein the target environment topology represents topology information of a joint debugging environment for realizing the target joint debugging scene, the target environment topology comprises N sub-scenes for realizing the target joint debugging scene and functional modules associated with all the sub-scenes in the N sub-scenes, N is a natural number greater than or equal to 2, at least part of the functional modules associated with the sub-scenes have a dependency relationship, and the functional modules associated with different sub-scenes are different or at least the same.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform a method according to any one of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method according to any of the embodiments of the present disclosure.
In this way, the scheme disclosed by the invention can automatically identify and obtain target intention data, automatically recommend a matched target environment topology according to the target intention data, and the target environment topology is matched with a target joint debugging scene indicated in the target intention data, compared with a scheme of manually selecting the environment topology by a tester relying on abundant experience, the scheme disclosed by the invention effectively reduces the dependence on the tester, and simultaneously, improves the overall efficiency of joint debugging test and user experience; moreover, the problem of inaccurate selected environment topology caused by insufficient experience of testers is effectively avoided, and powerful support is provided for successfully executing joint debugging test tasks.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic flow chart diagram one of a recommendation method for a joint debugging test environment according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a topology of a target environment topology in a specific example in accordance with an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart diagram II of a recommendation method for a joint debugging test environment according to an embodiment of the present disclosure;
FIG. 4 is a schematic flow diagram of a recommendation method for a joint debugging test environment in generating target hint statements in an example, according to an embodiment of the present disclosure;
FIG. 5 is a schematic flow chart III of a recommendation method for a joint debugging test environment according to an embodiment of the present disclosure;
FIGS. 6 (a) and 6 (b) are schematic flow diagrams of similarity matching in a recommendation method for a joint debugging test environment according to an embodiment of the present disclosure;
FIG. 7 is an optimized schematic flow chart of a hint word template in a recommendation method of a joint debugging test environment according to an embodiment of the present disclosure;
FIG. 8 is a schematic diagram of a recommendation system architecture for a joint debugging test environment, according to an embodiment of the present disclosure;
FIG. 9 is a schematic diagram of a recommender of a joint debugging environment in accordance with an embodiment of the present disclosure;
Fig. 10 is a block diagram of an electronic device for implementing a recommendation method for a joint debugging test environment in accordance with an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. The term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, e.g., including at least one of A, B, C, may mean including any one or more elements selected from the group consisting of A, B and C. The terms "first" and "second" herein mean a plurality of similar technical terms and distinguishes them, and does not limit the meaning of the order, or only two, for example, a first feature and a second feature, which means that there are two types/classes of features, the first feature may be one or more, and the second feature may be one or more.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be appreciated by one skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
The following description is made on the related art of the embodiments of the present disclosure, and the following related art may be arbitrarily combined with the technical solutions of the embodiments of the present disclosure as an alternative, which all belong to the protection scope of the embodiments of the present disclosure.
The purpose of joint debugging test is to verify whether a certain service scenario is valid end to end and whether there is an impact on other functional modules. In the joint debugging test scenario, there may be more functional modules in the joint debugging system, and more supported service scenarios, at this time, if the joint debugging test of a specific service scenario is to be successfully performed, a tester needs to select a required functional module and a corresponding upstream and downstream module according to the specific service scenario, and the required functional modules are also different in the joint debugging test of different service scenarios.
Related terms of the scheme of the present disclosure are briefly explained as follows:
the functional module refers to: the minimum unit of the business scene is formed, and meanwhile, the minimum unit of the online business scene is also formed.
The joint debugging environment (also referred to as joint debugging topology) refers to: the environment topology of the functional modules of the cross-business scene is used for describing the upstream and downstream relations among the functional modules of the business scene latitude.
Joint debugging scene refers to: and according to the business scene topology constructed by different joint debugging requirements and business scene requirements, describing the upstream and downstream relation of related information (such as functional modules, services and the like) among the business scenes.
Based on the above, the scheme of the present disclosure provides an automatic recommendation method for joint debugging test environment, which can effectively reduce the dependence on testers, improve the overall efficiency of joint debugging test, and simultaneously, improve the user experience.
Specifically, fig. 1 is a schematic flowchart of a recommendation method of a joint debugging test environment according to an embodiment of the present application. The method is optionally applied to electronic equipment, such as personal computers, servers, server clusters and the like.
Further, the method includes at least some of the following. As shown in fig. 1, includes:
step S101: and identifying and obtaining target intention data.
Here, the target intention data characterizes a target joint debugging scene requiring joint debugging test.
Step S102: and obtaining a target environment topology matched with the target intention data.
Here, the target environment topology characterizes topology information of a joint debugging environment for realizing the target joint debugging scene. The target environment topology comprises N sub-scenes (the sub-scenes can refer to service scenes, namely N service scenes) for realizing the target joint debugging scene, and functional modules associated with all the sub-scenes in the N sub-scenes, wherein N is a natural number greater than or equal to 2.
Further, in an example, at least part of the functional modules associated with the sub-scenario (i.e. the service scenario) have a dependency relationship, for example, when performing the joint debugging task, the functional modules associated with the sub-scenario have an upstream and a downstream dependency relationship in execution.
Further, in an example, the functional modules associated with different sub-scenarios are different; or in another example, the functional modules associated with different sub-scenarios are at least partially identical.
In this way, the scheme disclosed by the invention can automatically identify and obtain target intention data, automatically recommend a matched target environment topology according to the target intention data, and the target environment topology is matched with a target joint debugging scene indicated in the target intention data, compared with a scheme of manually selecting the environment topology by a tester relying on abundant experience, the scheme disclosed by the invention effectively reduces the dependence on the tester, and simultaneously, improves the overall efficiency of joint debugging test and user experience; moreover, the problem of inaccurate selected environment topology caused by insufficient experience of testers is effectively avoided, and powerful support is provided for successfully executing joint debugging test tasks.
In addition, the scheme disclosed by the invention does not limit the specific joint debugging scene, so that the application range is wider and the practicability is higher.
In an example, the target environment topology includes topology information as shown in fig. 2, that is, a service scenario a and a service scenario B including a service scenario a implementing a target joint debugging scenario, where the service scenario a includes a function module a, a function module B, a function module C, and a function module D, and the service scenario B includes a function module C, a function module E, and a function module F, respectively; here, the arrow in fig. 2 is used to represent the upstream-downstream dependency relationship, such as that the function module B depends on the function module a upstream, and thus, the environment, scene, and function module required for the target joint debugging scene for joint debugging test are characterized by the topology information as shown in fig. 2.
FIG. 3 is a schematic flow chart diagram II of a recommendation method for a joint debugging test environment according to an embodiment of the application. The method is optionally applied to electronic equipment, such as personal computers, servers, server clusters and the like. For example, in a target vehicle, and further, in an in-vehicle apparatus mounted in the target vehicle.
Further, the method includes at least some of the following. As shown in fig. 3, includes:
Step S301: and obtaining demand data for describing the target joint debugging scene.
In an example, the target object inputs the target joint debugging scene, for example, inputs the requirement data describing the target joint debugging scene, where the requirement data may be a requirement document, or voice data input in a natural language for describing the target joint debugging scene, or the requirement document, the language data, etc., and the specific data form of the requirement data is not limited in the scheme of the present disclosure.
Step S302: and carrying out intention recognition on the demand data based on a large language model to obtain the target intention data.
For instance, in an example, as shown in fig. 3, the target intention data includes an environment name describing the target joint debugging scene, a scene name, a name of a specified functional module, and the like.
In a specific example, the model may be used to perform intent recognition on the demand data, for example, a large model based on a generated artificial intelligence (ARTIFICIAL INTELLIGENCE GENERATED Content, AIGC) technology may be used to perform intent recognition on the demand data, so that recognition efficiency may be effectively improved, and meanwhile, accuracy of a recognition result is improved, so that user experience is further improved. Specifically, the above-mentioned large language model-based intention recognition for the demand data to obtain the target intention data (i.e. step S302) may specifically include:
Step S3021: and acquiring a prompt word template required for identifying the required data.
Here, the hint word template includes a plurality of sub-templates.
Step S3022: and generating a target prompt sentence based on the requirement data and the prompt word template.
Here, in an example, the generated target-alert sentence may also be presented, e.g., in a scenario, the demand data and the target-alert sentence generated based on the demand data are presented using a dialog user interface (Conversation User Interface, CUI), and as such,
And the overall communication understanding efficiency is improved, and meanwhile, a foundation is laid for improving the accuracy of communication understanding.
Further, after the target prompt statement is displayed, the target object can further adjust the target prompt statement, so that the accuracy of the generated target environment topology is further improved, and the user experience is further improved.
In a specific example, the generating the target alert sentence based on the requirement data and the alert word template (i.e. step S3022) may specifically include: obtaining target prompt words of all the sub-templates in the plurality of sub-templates based on the demand data; and generating a target prompt sentence based on the target prompt words of each sub-template in the plurality of sub-templates.
For example, as shown in fig. 4, the requirement data (such as a document in pdf format is input) is obtained, and a prompt word template including a plurality of sub-templates is invoked, where the sub-templates included in the prompt word template may be: "person setup", "task statement", "related knowledge" and "output examples"; further, based on the input demand data, target prompt words of all the sub templates are obtained, then target prompt sentences corresponding to the demand data are generated, and then the target prompt sentences are input into the large model to obtain output results, and the recommended target environment topology is obtained. Thus, the large model and the prompt word template are utilized to adapt to different joint debugging scene application requirements, and further on the basis of effectively improving the efficiency of joint debugging test, the accuracy of the recommendation result is improved, and further the user experience is improved.
Step S3023: and inputting the target prompt statement into a large language model to obtain the target intention data.
Step S303: and obtaining a target environment topology matched with the target intention data.
Here, the target environment topology characterizes topology information of a joint debugging environment for realizing the target joint debugging scene. The target environment topology comprises N sub-scenes (the sub-scenes can refer to service scenes, namely N service scenes) for realizing the target joint debugging scene, and functional modules associated with all the sub-scenes in the N sub-scenes, wherein N is a natural number greater than or equal to 2.
Further, in an example, at least part of the functional modules associated with the sub-scenario (i.e. the service scenario) have a dependency relationship, for example, when performing the joint debugging task, the functional modules associated with the sub-scenario have an upstream and a downstream dependency relationship in execution.
Further, in an example, the functional modules associated with different sub-scenarios are different; or in another example, the functional modules associated with different sub-scenarios are at least partially identical.
In this way, the scheme of the present disclosure provides a recommended specific application scenario of the joint debugging test environment, so that target intention data is identified and obtained through input demand data, and then the matched target environment topology is automatically recommended according to the target intention data, so that the overall efficiency of the joint debugging test is effectively improved, and the user experience is improved; meanwhile, the problem of inaccurate selected environment topology caused by insufficient experience of testers is effectively avoided, and powerful support is provided for successfully executing joint debugging test tasks. In addition, the scheme disclosed by the invention does not limit the specific joint debugging scene, so that the application range is wider and the practicability is higher.
Fig. 5 is a schematic flow chart diagram III of a recommendation method for a joint debugging test environment according to an embodiment of the present application. The method is optionally applied to electronic equipment, such as personal computers, servers, server clusters and the like.
Further, the method includes at least some of the following. As shown in fig. 5, includes:
step S501: and obtaining demand data for describing the target joint debugging scene.
Step S502: and carrying out intention recognition on the demand data based on a large language model to obtain the target intention data.
Step S503: and obtaining a target database.
Here, the target database includes: presetting an environment topology (e.g., recorded by an environment topology list), presetting a joint debugging scene (e.g., recorded by an environment scene list), and presetting a function module (e.g., recorded by a scene module list). Further, the target database further includes a preset environment topology (for example, recorded in a form shown in table 1, and meanwhile, scene tags of each preset joint debugging scene) associated with the preset joint debugging scene, and a functional module (for example, recorded in a form of a table) associated with the preset joint debugging scene. Thus, the target environment topology required by realizing the designated target joint debugging scene is conveniently obtained by utilizing the pre-established target database to quickly match.
TABLE 1
In an example, a target database may be pre-established, for example, to map a historical end-to-end environment application (e.g., a joint debugging environment application) to a different environment topology, where the environment topology includes a joint debugging scene and functional modules required by the joint debugging scene.
In practical application, the environment topology (or joint debugging scene) may be labeled and semantically processed according to the joint debugging scene included in the environment topology to obtain the topology name and the topology label (e.g. the table record shown in table 2) of the environment topology, so as to construct a target database including a plurality of preset environment topologies, a plurality of preset joint debugging scenes and a plurality of preset functional modules.
TABLE 2
Step S504: and matching the similarity between the target joint debugging scene represented by the target intention data and the related data of the target database to obtain a target environment topology matched with the target intention data.
Here, the target environment topology characterizes topology information of a joint debugging environment for realizing the target joint debugging scene. The target environment topology comprises N sub-scenes (the sub-scenes can refer to service scenes, namely N service scenes) for realizing the target joint debugging scene, and functional modules associated with all the sub-scenes in the N sub-scenes, wherein N is a natural number greater than or equal to 2.
Further, in an example, at least part of the functional modules associated with the sub-scenario (i.e. the service scenario) have a dependency relationship, for example, when performing the joint debugging task, the functional modules associated with the sub-scenario have an upstream and a downstream dependency relationship in execution.
Further, in an example, the functional modules associated with different sub-scenarios are different; or in another example, the functional modules associated with different sub-scenarios are at least partially identical.
In another specific example, keywords (such as environment names, scene names) of the target joint debugging scene represented by the target intention data and the like can be subjected to similarity matching with related labels (such as topology labels and joint debugging scene labels) of a target database, so that a target environment topology matched with the target intention data can be obtained quickly.
For example, the similarity matching may be performed in one of two ways:
Mode one: as shown in fig. 6 (a), the topology names or topology labels in the target database are compared with the similarity between strings (for example, comparing the distances between different characters between strings) with the target intention data output by the large model, and all the topology names or topology labels in the target database are traversed to obtain the environment topology with the highest similarity, which is the target environment topology matched with the target intention data.
Here, the distance is calculated by a method including, but not limited to, column Wen Shentan (normalized, weighted, up to Mei Luo), gu Luo-Winkelle, gu Kade index, euclidean distance, hamming distance, and the like.
Mode two: as shown in fig. 6 (b), a vectorization (embeding) interface of the large model is called to vectorize the topology name or topology label and the like in the target database and the target intention data, and vector similarity matching is performed to obtain an environment topology with the highest similarity, wherein the environment topology with the highest similarity is the target environment topology matched with the target intention data.
In this way, the proposal of the present disclosure provides a recommended specific proposal of the joint debugging test environment, in the proposal, after target intention data is identified, a target environment topology required for realizing a designated target joint debugging scene can be obtained by utilizing quick matching of a pre-established target database, thus further improving the overall efficiency of the joint debugging test and further improving the user experience; moreover, because the target database is pre-established based on the historical data, the problem of inaccurate selected environment topology caused by insufficient experience of testers can be further effectively avoided, and powerful support is further provided for successfully executing joint debugging test tasks.
Further, in a specific example, after the target environment topology is obtained, a target environment required by the joint debugging scene for joint debugging test can be further constructed based on the target environment topology matched with the target intention data, so that the joint debugging test on the target joint debugging scene can be conveniently performed by utilizing the functional module in the target environment topology, the joint debugging test can be completed quickly, and further user experience is further improved.
Or in another specific example, after the target environment topology is obtained, the target environment topology matched with the target intention data can be adjusted, and then the target environment required by the target joint debugging scene of the joint debugging test is constructed based on the adjusted target environment topology, so that the joint debugging test is conveniently carried out on the target joint debugging scene by utilizing the functional module in the target environment topology, the joint debugging test is completed quickly, and further the user experience is further improved.
In a specific example of the scheme of the present disclosure, in order to ensure the accuracy of the joint debugging environment recommendation, user experience is improved, after the target object adjusts the target environment topology, the data flywheel design is performed based on the adjusted target environment topology, so that the accuracy of the joint debugging environment recommendation is further improved. Specifically, in the case of recognizing the target intention data using a large language model, after obtaining a target environment topology that matches the target intention data and after adjusting the target environment topology, the prompt word module may be adjusted based on the adjusted target environment topology, where the target intention data is obtained by inputting a target prompt sentence generated based on the prompt word module into the large language model.
For example, as shown in fig. 7, the adjusted target environment topology and the target environment topology before adjustment (i.e., the target environment topology recommended by the large language model) are analyzed, for example, the environment topology, the joint debugging scene, the function module and other tag data of the two are compared to obtain the result that does not meet the requirement, for example, the tag data of the function module and other tag data that does not meet the requirement are obtained, the prompt word template (for example, the keywords of the sub-templates of the prompt word template are adjusted) is adjusted based on the result that does not meet the requirement, the tag data is adjusted, and the test of the prompt word template is performed, for example, the new target environment topology of the large language model is obtained, and the obtained new target environment topology is further analyzed with the adjusted target environment topology, so cycle is performed, thereby realizing the calibration of the prompt word template and improving the recommendation accuracy.
FIG. 8 presents a system architecture diagram implementing the disclosed aspects, as shown in FIG. 8, including a model layer (e.g., containing a hint word template and a large language model for intent recognition), a service layer (for invoking the model to obtain target intent data and generating a target environment topology in conjunction with a pre-built target database), and an interface layer (for interface presentation). Here, the Interface layer may be specifically a User Interface (UI), such as a User interaction Interface including a combination of a graphical User Interface (GRAPHICAL USER INTERFACE, GUI) and a conversational User interaction User Interface Conversational User Interface, CUI.
In summary, the scheme disclosed by the disclosure combines the latest AIGC technology, automatically recommends the topology information of the joint debugging environment for realizing the target joint debugging scene through semantic recognition, and the process realizes the application flow of the dynamic topology environment more semantically, and the recommended topology information summarizes the needed scene or the additionally needed functional module, so that the dependence of the joint debugging scene on testers is reduced, further, the joint debugging test efficiency is improved, and meanwhile, the user experience is also improved.
Moreover, the scheme of the disclosure can further adjust and optimize a prompt word template (a prompt template) based on a recommendation result (namely, target environment topology), so that a data flywheel is realized, and the accuracy of environment establishment and recommendation is further improved through a data tag.
The disclosed scheme also provides a recommendation device for joint debugging test environment, as shown in fig. 9, comprising:
the identifying unit 901 is configured to identify and obtain target intention data, where the target intention data represents a target joint debugging scene that needs joint debugging test;
The matching unit 902 is configured to obtain a target environment topology matched with the target intention data, where the target environment topology characterizes topology information of a joint debugging environment for implementing the target joint debugging scene, and includes N sub-scenes for implementing the target joint debugging scene, and functional modules associated with each sub-scene in the N sub-scenes, where N is a natural number greater than or equal to 2, at least part of the functional modules associated with the sub-scenes have a dependency relationship, and functional modules associated with different sub-scenes are different, or at least part of the functional modules associated with different sub-scenes are the same.
In a specific example of the present disclosure, the apparatus further includes: a first acquisition unit; wherein,
The first acquisition unit is used for acquiring demand data for describing the target joint debugging scene;
The recognition unit is specifically configured to perform intent recognition on the demand data based on a large language model, so as to obtain the target intent data.
In a specific example of the present disclosure, the first obtaining unit is specifically configured to obtain a prompt word template required for identifying the requirement data; the prompt word template comprises a plurality of sub templates; generating a target prompt sentence based on the demand data and the prompt word template; and inputting the target prompt statement into a large language model to obtain the target intention data.
In a specific example of the solution of the present disclosure, the first obtaining unit is specifically configured to:
Obtaining target prompt words of all the sub-templates in the plurality of sub-templates based on the demand data;
and generating a target prompt sentence based on the target prompt words of each sub-template in the plurality of sub-templates.
In a specific example of the present disclosure, the apparatus further includes: a second acquisition unit; wherein,
The second obtaining unit is configured to obtain a target database, where the target database includes: presetting an environment topology, presetting a joint debugging scene and presetting a functional module;
the matching unit is specifically configured to perform similarity matching on the target joint debugging scene represented by the target intention data and related data of the target database, so as to obtain a target environment topology matched with the target intention data.
In a specific example of the present disclosure, the apparatus further includes: a first configuration unit; wherein,
The first configuration unit is configured to construct a target environment required by the joint debugging scene for joint debugging test based on a target environment topology matched with the target intention data, so as to perform joint debugging test on the target joint debugging scene by using a functional module in the target environment topology.
In a specific example of the present disclosure, the apparatus further includes: an adjusting unit and a second configuration unit; wherein,
The adjusting unit is used for adjusting the target environment topology matched with the target intention data;
The second configuration unit is further configured to construct a target environment required by the target joint debugging scene of the joint debugging test based on the adjusted target environment topology, so that the joint debugging test is performed on the target joint debugging scene by using a functional module in the target environment topology.
In a specific example of the solution of the present disclosure, the adjusting unit is further configured to:
And under the condition that the target intention data are obtained by utilizing the large language model recognition, adjusting the prompt word module based on the adjusted target environment topology, wherein the target intention data are obtained by inputting target prompt sentences generated based on the prompt word module into the large language model.
Descriptions of specific functions and examples of each unit of the apparatus in the embodiments of the present disclosure may refer to related descriptions of corresponding steps in the foregoing method embodiments, which are not repeated herein.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 10 shows a schematic block diagram of an example electronic device 1000 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile apparatuses, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing apparatuses. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.
Various components in device 1000 are connected to I/O interface 1005, including: an input unit 1006 such as a keyboard, a mouse, and the like; an output unit 1007 such as various types of displays, speakers, and the like; a storage unit 1008 such as a magnetic disk, an optical disk, or the like; and communication unit 1009 such as a network card, modem, wireless communication transceiver, etc. Communication unit 1009 allows device 1000 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks.
The computing unit 1001 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 1001 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the respective methods and processes described above, for example, the recommended method of the joint debugging test environment. For example, in some embodiments, the recommended methods of the joint debugging environment may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1000 via ROM 1002 and/or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by computing unit 1001, one or more steps of the recommended method of the joint debugging test environment described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform the recommended method of the joint debugging test environment in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions, improvements, etc. that are within the principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (19)
1. A recommendation method of a joint debugging test environment comprises the following steps:
Identifying and obtaining target intention data, wherein the target intention data represents a target joint debugging scene needing joint debugging test;
Obtaining a target environment topology matched with the target intention data, wherein the target environment topology represents topology information of a joint debugging environment for realizing the target joint debugging scene, the topology information comprises N sub-scenes for realizing the target joint debugging scene and functional modules associated with each sub-scene in the N sub-scenes, and N is a natural number greater than or equal to 2.
2. The method of claim 1, wherein the identifying results in target intent data, comprising:
acquiring demand data for describing the target joint debugging scene;
and carrying out intention recognition on the demand data based on a large language model to obtain the target intention data.
3. The method of claim 2, wherein the intent recognition of the demand data based on the large language model to obtain the target intent data comprises:
Acquiring a prompt word template required for identifying the required data; the prompt word template comprises a plurality of sub templates;
generating a target prompt sentence based on the demand data and the prompt word template;
and inputting the target prompt statement into a large language model to obtain the target intention data.
4. The method of claim 3, wherein the generating a target hint statement based on the demand data and the hint word template comprises:
Obtaining target prompt words of all the sub-templates in the plurality of sub-templates based on the demand data;
and generating a target prompt sentence based on the target prompt words of each sub-template in the plurality of sub-templates.
5. The method of any of claims 1-4, wherein the deriving a target environment topology that matches the target intent data comprises:
Obtaining a target database, wherein the target database comprises: presetting an environment topology, presetting a joint debugging scene and presetting a functional module;
And matching the similarity between the target joint debugging scene represented by the target intention data and the related data of the target database to obtain a target environment topology matched with the target intention data.
6. The method of any of claims 1-5, further comprising:
and constructing a target environment required by the joint debugging scene based on the target environment topology matched with the target intention data so as to perform joint debugging test on the target joint debugging scene by utilizing a functional module in the target environment topology.
7. The method of any of claims 1-6, further comprising:
Adjusting a target environment topology matched with the target intention data;
Constructing a target environment required by the target joint debugging scene of the joint debugging test based on the adjusted target environment topology, so as to perform the joint debugging test on the target joint debugging scene by utilizing a functional module in the target environment topology.
8. The method of claim 7, further comprising:
And under the condition that the target intention data are obtained by utilizing the large language model recognition, adjusting the prompt word module based on the adjusted target environment topology, wherein the target intention data are obtained by inputting target prompt sentences generated based on the prompt word module into the large language model.
9. A recommendation device for a joint debugging test environment, comprising:
The identifying unit is used for identifying and obtaining target intention data, wherein the target intention data represents a target joint debugging scene which needs joint debugging test;
The matching unit is used for obtaining a target environment topology matched with the target intention data, wherein the target environment topology represents topology information of a joint debugging environment for realizing the target joint debugging scene, the matching unit comprises N sub-scenes for realizing the target joint debugging scene and functional modules associated with all sub-scenes in the N sub-scenes, and N is a natural number greater than or equal to 2.
10. The apparatus of claim 9, further comprising: a first acquisition unit; wherein,
The first acquisition unit is used for acquiring demand data for describing the target joint debugging scene;
The recognition unit is specifically configured to perform intent recognition on the demand data based on a large language model, so as to obtain the target intent data.
11. The apparatus of claim 10, wherein the first obtaining unit is specifically configured to obtain a prompt word template required for identifying the requirement data; the prompt word template comprises a plurality of sub templates; generating a target prompt sentence based on the demand data and the prompt word template; and inputting the target prompt statement into a large language model to obtain the target intention data.
12. The apparatus of claim 11, wherein the first acquisition unit is specifically configured to:
Obtaining target prompt words of all the sub-templates in the plurality of sub-templates based on the demand data;
and generating a target prompt sentence based on the target prompt words of each sub-template in the plurality of sub-templates.
13. The apparatus of any of claims 9-12, further comprising: a second acquisition unit; wherein,
The second obtaining unit is configured to obtain a target database, where the target database includes: presetting an environment topology, presetting a joint debugging scene and presetting a functional module;
the matching unit is specifically configured to perform similarity matching on the target joint debugging scene represented by the target intention data and related data of the target database, so as to obtain a target environment topology matched with the target intention data.
14. The apparatus of any of claims 9-13, further comprising: a first configuration unit; wherein,
The first configuration unit is configured to construct a target environment required by the joint debugging scene for joint debugging test based on a target environment topology matched with the target intention data, so as to perform joint debugging test on the target joint debugging scene by using a functional module in the target environment topology.
15. The apparatus of any of claims 9-14, further comprising: an adjusting unit and a second configuration unit; wherein,
The adjusting unit is used for adjusting the target environment topology matched with the target intention data;
The second configuration unit is further configured to construct a target environment required by the target joint debugging scene of the joint debugging test based on the adjusted target environment topology, so that the joint debugging test is performed on the target joint debugging scene by using a functional module in the target environment topology.
16. The apparatus of claim 15, wherein the adjustment unit is further configured to:
And under the condition that the target intention data are obtained by utilizing the large language model recognition, adjusting the prompt word module based on the adjusted target environment topology, wherein the target intention data are obtained by inputting target prompt sentences generated based on the prompt word module into the large language model.
17. An electronic device, comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.
19. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410177998.6A CN117992349A (en) | 2024-02-08 | 2024-02-08 | Method, device, equipment and storage medium for recommending joint debugging test environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410177998.6A CN117992349A (en) | 2024-02-08 | 2024-02-08 | Method, device, equipment and storage medium for recommending joint debugging test environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117992349A true CN117992349A (en) | 2024-05-07 |
Family
ID=90893856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410177998.6A Pending CN117992349A (en) | 2024-02-08 | 2024-02-08 | Method, device, equipment and storage medium for recommending joint debugging test environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117992349A (en) |
-
2024
- 2024-02-08 CN CN202410177998.6A patent/CN117992349A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220027611A1 (en) | Image classification method, electronic device and storage medium | |
| CN112926306B (en) | Text error correction method, device, equipment and storage medium | |
| CN115982376B (en) | Method and device for training model based on text, multimode data and knowledge | |
| WO2021218069A1 (en) | Dynamic scenario configuration-based interactive processing method and apparatus, and computer device | |
| WO2023142451A1 (en) | Workflow generation methods and apparatuses, and electronic device | |
| CN113657483A (en) | Model training method, target detection method, device, equipment and storage medium | |
| CN115099239B (en) | Resource identification method, device, equipment and storage medium | |
| US20220027766A1 (en) | Method for industry text increment and electronic device | |
| CN114818736B (en) | Text processing method, chain finger method and device for short text and storage medium | |
| CN115048523B (en) | Text classification method, device, equipment and storage medium | |
| CN114118049B (en) | Information acquisition method, device, electronic equipment and storage medium | |
| CN113360672B (en) | Method, apparatus, device, medium and product for generating knowledge graph | |
| CN115374063A (en) | File processing method, device, equipment and storage medium | |
| CN115329132A (en) | Method, device and equipment for generating video label and storage medium | |
| CN117992349A (en) | Method, device, equipment and storage medium for recommending joint debugging test environment | |
| CN114880498A (en) | Event information display method and device, equipment and medium | |
| CN114218431A (en) | Video searching method and device, electronic equipment and storage medium | |
| CN113850072A (en) | Text emotion analysis method, emotion analysis model training method, device, equipment and medium | |
| CN113344405B (en) | Method, device, equipment, medium and product for generating information based on knowledge graph | |
| CN113642294B (en) | Method, apparatus, device, medium and product for generating meeting summary | |
| CN115982466B (en) | Method, device, equipment and storage medium for retrieving data | |
| CN116127948B (en) | Recommendation method and device for text data to be annotated and electronic equipment | |
| CN113705206B (en) | Emotion prediction model training method, device, equipment and storage medium | |
| CN117131197B (en) | Method, device, equipment and storage medium for processing demand category of bidding document | |
| CN115965018B (en) | Training method of information generation model, information generation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |