Large model management method and device based on cloud service and storage medium

Abstract

The invention discloses a large model management method and device based on cloud service, electronic equipment and a storage medium, and relates to the field of financial science and technology, and the method comprises the steps: deploying a first large model at a cloud end according to a deployment instruction of the first large model sent by a first user, and displaying an interaction configuration interface to the first user; obtaining a first interactive interface of the first large model through the interactive configuration interface, and deploying the first interactive interface locally; and in response to the obtained calling instruction of the first large model sent by the second user, displaying the first interaction interface to the second user so as to call the first large model through the first interaction interface. According to the technical scheme, deployment and application of the large model are achieved, the application range of the large model is expanded, and the utilization rate of the large model is increased; and meanwhile, the data security of the interactive interface is improved, and the calling security of the large model calling process is ensured.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a large model management method, device, electronic device and storage medium based on cloud services. Background Art

[0002] With the continuous development of Artificial Intelligence Big Model ("big model") technology, financial institutions often develop a variety of big models to meet different needs. Therefore, the effective management of big models has also become an important issue for financial institutions.

[0003] In the existing technology, the use of large models is often limited to a small number of professional and technical personnel. This is because large models require both professional technical knowledge for training and application, and the support of high-performance computers. Ordinary business personnel often find it difficult to use large models due to the lack of these resources and technologies.

[0004] In addition, the developers and users of large models are usually not the same group, which results in the phenomenon that developers do not use them frequently and users do not understand how to use them. As a result, the utilization rate of large models is low and the scope of use is small. Summary of the invention

[0005] The present invention provides a large model management method, device, electronic device and storage medium based on cloud service to solve the problems of low utilization rate and small scope of use of large models.

[0006] According to one aspect of the present invention, a large model management method based on cloud services is provided, comprising:

[0007] According to a deployment instruction of the first large model issued by the first user, the first large model is deployed in the cloud, and an interactive configuration interface is displayed to the first user;

[0008] Obtaining a first interactive interface of the first large model through the interactive configuration interface, and deploying the first interactive interface locally;

[0009] In response to obtaining a calling instruction of the first large model issued by a second user, the first interactive interface is displayed to the second user so as to call the first large model through the first interactive interface.

[0010] The large model management method based on cloud services also includes: in response to obtaining a first supplementary sample for the first large model from a third user, sending the first supplementary sample to the first user, so that the first user can confirm whether to use the first supplementary sample as a training sample for the first large model; if a confirmation instruction from the first user for the first supplementary sample is obtained, iteratively training the first large model through the first supplementary sample.

[0011] After sending the first supplementary sample to the first user so as to confirm through the first user whether to use the first supplementary sample as a training sample for the first large model, the method further includes: if a rejection instruction from the first user for the first supplementary sample is obtained, copying a second large model according to the first large model, deploying the second large model on the cloud, and iteratively training the second large model through the first supplementary sample; and configuring both the source model and the upstream model as the first large model in the label information of the second large model.

[0012] The cloud service-based large model management method also includes: in response to obtaining a fuzzy call instruction issued by a fourth user, determining a matching target large model according to the identity information of the fourth user, and displaying a target interaction interface corresponding to the target large model to the fourth user, so as to call the target large model through the target interaction interface.

[0013] The first major model includes an evaluation management model; after calling the first major model through the first interactive interface, it also includes: obtaining the first filtering instruction of the second user through the first interactive interface; wherein the first filtering instruction includes at least one of comment content, evaluation time, performance object and emotion category; according to the first filtering instruction, based on the preset priority of other display parameters except the filtering parameters, each evaluation information is displayed in turn.

[0014] The first large model includes a customer management model; after calling the first large model through the first interactive interface, it also includes: obtaining a second screening instruction of the second user through the first interactive interface; wherein the second screening instruction includes at least one of customer number, economic status, credit rating and educational information; according to the second screening instruction, based on the preset priority of other display parameters except the screening parameters, each customer information is displayed in turn.

[0015] According to another aspect of the present invention, there is provided a large model management device based on cloud service, comprising:

[0016] A model deployment execution module, configured to deploy the first large model on the cloud according to a deployment instruction of the first large model issued by the first user, and to display an interactive configuration interface to the first user;

[0017] An interface deployment execution module, used for obtaining a first interactive interface of the first large model through the interactive configuration interface, and deploying the first interactive interface locally;

[0018] The model calling execution module is used to display the first interactive interface to the second user in response to obtaining a calling instruction of the first large model issued by the second user, so as to call the first large model through the first interactive interface.

[0019] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the cloud service-based large model management method described in any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the cloud service-based large model management method described in any embodiment of the present invention when executed.

[0024] According to another aspect of the present invention, a computer program product is provided, including a computer program, which, when executed by a processor, implements the cloud service-based large model management method described in any embodiment of the present invention.

[0025] The technical solution of the embodiment of the present invention is to deploy the first large model in the cloud according to the deployment instruction of the first large model issued by the first user, and display the interactive configuration interface to the first user; obtain the first interactive interface of the first large model through the interactive configuration interface, and deploy the first interactive interface locally; in response to obtaining the call instruction of the first large model issued by the second user, display the first interactive interface to the second user, so as to call the first large model through the first interactive interface. In this way, not only the deployment and application of the large model is realized, but also the application scope of the large model is expanded and the utilization rate of the large model is improved; at the same time, the large model deployed in the cloud and the interactive interface deployed locally not only improve the data security of the interactive interface itself, but also ensure the call security of the large model call process.

[0026] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 is a flow chart of a large model management method based on cloud service provided according to the first embodiment of the present invention;

[0029] Figure 2 is a flowchart of another large model management method based on cloud services provided according to the second embodiment of the present invention;

[0030] Figure 3 is a flowchart of another large model management method based on cloud services provided according to Embodiment 3 of the present invention;

[0031] Figure 4 is a structural diagram of a large model management device based on cloud services provided according to a fourth embodiment of the present invention;

[0032] Figure 5 It is a structural diagram of an electronic device that implements the large model management method based on cloud service according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] Figure 1 This is a flowchart of a large model management method based on cloud services provided in the first embodiment of the present invention. This embodiment can be applied to the deployment and application of large models based on cloud services. The method can be executed by a large model management device based on cloud services in any embodiment of the present invention. The large model management device based on cloud services can be implemented in the form of hardware and / or software. The large model management device based on cloud services can be configured in a management system, and the management system can be configured in one or more servers. Figure 1 As shown, the method includes:

[0037] S101. According to a deployment instruction of a first large model issued by a first user, the first large model is deployed on the cloud, and an interactive configuration interface is displayed to the first user.

[0038] After completing the design and development of the big model, the developer uploads the packaged big model to the management system, and the management system deploys the acquired big model on the cloud to facilitate the use and maintenance of the big model; depending on the business type and business objects applicable to the big model, the display parameters in the interactive interface of each big model are often different, and the display parameters actually exist as screening parameters. Therefore, after completing the cloud deployment of the first big model, it is necessary to display the interactive configuration interface to the first user, so as to guide the first user to complete the interactive interface configuration of the first large model through the interactive configuration interface, which is actually the configuration of the display parameters in the interactive interface.

[0039] Taking the first model as an example, the evaluation management model can be used to obtain users' evaluation information on mobile phone software and classify and manage each evaluation information; among them, the display parameters of the evaluation information may include performance objects, comment time, comment content and emotional category; performance objects may include usability, ease of use, robustness, interface aesthetics, process and security, which reflects which performance of the mobile phone software the current review information is evaluating.

[0040] Emotion categories may include positive, neutral, and negative; positive means that the current comment information reflects that the user has a favorable impression of a certain performance, that is, the user has an identification with the performance; neutral means that the current comment information reflects that the user has neither a positive nor a negative attitude toward the performance, with no particular favorable impression nor particular aversion; negative means that the current comment information reflects that the user has an aversion to the performance, that is, the user does not identify with the performance.

[0041] Taking the first large model as an example, the customer management model can be used to manage customer information; wherein, the display parameters of customer information may include customer number, economic status, life cycle, credit rating and educational information, etc.; wherein, the life cycle may include active period, dormant period and churn period, etc., which reflects the current customer's business usage status; thus, the display parameters in the interactive interface of each deployed large model can be configured by the developer of the model; in addition, the model developer can also choose automatic configuration of the interactive interface to reduce the configuration complexity. The management system extracts one or more parameters as display parameters for display based on the feedback information of the large model and the display space of the interactive interface.

[0042] S102. Obtain a first interactive interface of the first large model through the interactive configuration interface, and deploy the first interactive interface locally.

[0043] Compared with the big model itself, the interactive interface has less code, and compared with the iterative update of the big model, the code information of the interactive interface is relatively stable. Therefore, deploying the interactive interface locally will not take up too much storage resources and requires only very little expansion space. At the same time, the big model provides an interface to the outside world, and the interactive interface is based on the big model call implemented by the interface. For example, the big model can be authenticated through the interface identifier of the interactive interface, and only the matching interactive interface is allowed to call it. Therefore, storing the interactive interface locally not only improves the data security of the interactive interface itself, but also has good stability and controllability, and ensures the calling security of the big model calling process.

[0044] S103: In response to obtaining a calling instruction of the first large model issued by a second user, displaying the first interactive interface to the second user so as to call the first large model through the first interactive interface.

[0045] After the first large model and its interactive interface (i.e., the first interactive interface) are deployed, they can be opened to all users with usage permissions; when the management system obtains the call instruction of the first large model issued by the second user, it displays the first interactive interface to the second user, so as to call the first large model through the first interactive interface, and obtain various operation instructions of the second user through the first interactive interface, so as to meet the second user's large model usage needs.

[0046] In addition, the management system will also send the feedback results and model performance data of each user to the developer of the large model, so that the developer can optimize the model and improve the accuracy and efficiency of the large model; at the same time, the management system can update the large model according to the update instructions issued by the developer to achieve improvements such as problem fixing, new function addition and performance improvement; among them, the performance data monitored in real time by the management system may include accuracy and response time, etc., so as to guide the developer to complete the repair in time when the performance of the large model deteriorates or an abnormal situation occurs.

[0047] Optionally, in an embodiment of the present invention, the cloud service-based large model management method further includes: in response to obtaining a first supplementary sample for the first large model from a third user, sending the first supplementary sample to the first user, so as to confirm through the first user whether to use the first supplementary sample as a training sample for the first large model; if a confirmation instruction from the first user for the first supplementary sample is obtained, iteratively training the first large model through the first supplementary sample.

[0048] Specifically, the deployed large model sometimes cannot meet the user's usage requirements, or the user wants to strengthen one or more functions of the large model. At this time, the user (i.e., the third user) can construct supplementary samples that meet his or her own needs and upload the supplementary samples to the management system; the management system sends the above supplementary samples to the creator of the large model (i.e., the first user) to confirm through the first user whether to use the first supplementary sample as a training sample for the first large model; if a rejection instruction is obtained, the first supplementary sample is refused to be used for iterative training of the first large model to ensure that the first large model maintains its original model structure.

[0049] If a confirmation instruction is obtained, the first supplementary sample is used to iteratively train the first large model, thereby realizing the iterative update of the deployed large model based on the actual needs of the user. The inquiry mechanism finally confirmed by the developer ensures the functional enhancement of the large model and avoids arbitrary modification of the model structure, which may cause the model function to deviate from the original construction intention of the developer, thereby ensuring the functional safety of the large model.

[0050] Optionally, in an embodiment of the present invention, after sending the first supplementary sample to the first user so as to confirm through the first user whether to use the first supplementary sample as a training sample for the first large model, it also includes: if a rejection instruction from the first user for the first supplementary sample is obtained, copying a second large model according to the first large model, deploying the second large model on the cloud, and iteratively training the second large model through the first supplementary sample; and configuring both the source model and the upstream model as the first large model in the label information of the second large model.

[0051] Specifically, the management system can determine whether the current user has the authority to deploy the large model based on the user's authority. If the current user does not have the authority to deploy the large model, after obtaining the developer's rejection instruction, the management system does not respond to the training operation of the first supplementary sample. If the current user has the authority to deploy the large model, the management system obtains the second large model copied from the first large model, deploys the second large model on the cloud, and then uses the first supplementary sample to iteratively train the second large model to meet the actual needs of the third user.

[0052] At the same time, the second largest model may also have a wider scope of application, and it can be set by a third user as shared permissions for multiple users to use together; the second largest model may only meet the specific needs of the third user and have a smaller scope of adaptation. It can be set by the third user as exclusive permissions to avoid interfering with the use of other users; in addition, since the second largest model is converted from the first largest model, it is necessary to mark the source information in the label information of the second largest model to facilitate the tracing of the structure and function of the second largest model.

[0053] The upstream model indicates which model the second largest model is directly transformed from, that is, the upper-level model of the second largest model; the source model indicates the initial model of the source of the current large model after a series of model replications, that is, the starting point model; for example, large model B is obtained based on large model A, and large model C is obtained based on large model B, then large model B is the upstream model of large model C, and large model A is the source model of large model C; obviously, in the embodiment of the present invention, the source model and upstream model of the second largest model are both the first largest model. This ensures that the model usage needs of the second user are met, the original structure of the first largest model is maintained, and the source tracing of the second largest model is realized at the same time.

[0054] Optionally, in an embodiment of the present invention, the cloud service-based large model management method further includes: in response to obtaining a fuzzy call instruction issued by a fourth user, determining a matching target large model according to the identity information of the fourth user, and displaying a target interaction interface corresponding to the target large model to the fourth user, so as to call the target large model through the target interaction interface. For users who are not familiar with various large model-related functions, they often cannot know the specific functions of each large model, nor can they accurately call the required large model. Therefore, if the fourth user does not issue a call instruction for a certain large model, but issues a fuzzy call instruction, the management system can compare the identity information of the fourth user with the label information of each deployed large model to obtain a matching target large model.

[0055] For example, if user A is a business personnel of type B business, then in the business type of the label information of each big model, the big model of type B business can be recommended to user A, and then the model selection result of user A can be obtained; thus, after determining the target big model, the corresponding target interaction interface is displayed to the fourth user, so that the target big model can be called through the target interaction interface, so that the user can realize fuzzy matching of the big model without being familiar with the structure and function of the deployed big model, thereby improving the user experience and meeting the user's model usage needs.

[0056] The technical solution of the embodiment of the present invention is to deploy the first large model in the cloud according to the deployment instruction of the first large model issued by the first user, and display the interactive configuration interface to the first user; obtain the first interactive interface of the first large model through the interactive configuration interface, and deploy the first interactive interface locally; in response to obtaining the call instruction of the first large model issued by the second user, display the first interactive interface to the second user, so as to call the first large model through the first interactive interface. In this way, not only the deployment and application of the large model is realized, but also the application scope of the large model is expanded and the utilization rate of the large model is improved; at the same time, the large model deployed in the cloud and the interactive interface deployed locally not only improve the data security of the interactive interface itself, but also ensure the call security of the large model call process.

[0057] Embodiment 2

[0058] Figure 2 This is a flowchart of a large model management method based on cloud services provided in the second embodiment of the present invention. The relationship between this embodiment and the above embodiment is that the first large model is taken as an evaluation management model. Figure 2 As shown, the method includes:

[0059] S201. According to a deployment instruction of a first large model issued by a first user, the first large model is deployed on the cloud, and an interactive configuration interface is displayed to the first user.

[0060] S202, obtaining a first interactive interface of the first large model through the interactive configuration interface, and deploying the first interactive interface locally;

[0061] S203: In response to obtaining a calling instruction of the first large model issued by a second user, displaying the first interactive interface to the second user so as to call the first large model through the first interactive interface.

[0062] S204. Obtaining a first screening instruction of the second user through the first interactive interface; wherein the first screening instruction includes at least one of comment content, evaluation time, performance object, and emotion category.

[0063] S205. According to the first screening instruction, based on the preset priorities of other display parameters except the screening parameters, display each evaluation information in sequence.

[0064] In the interactive interface of the evaluation management model, fixed general function buttons are displayed, including function buttons such as add, delete, download, export, query and reset displayed at the top of the interface, view and edit buttons configured at the end of each evaluation information, and display page configuration buttons, single page quantity configuration buttons and jump page buttons configured at the bottom of the interface; the management system performs corresponding processing operations according to the function buttons triggered by the second user in the interactive interface.

[0065] In addition to the general function buttons, according to the display parameters synchronously configured by the first user in the interactive interface when the first model is deployed to the cloud, the interactive interface also displays parameter items specific to the evaluation information, namely, comment content, evaluation time, performance object and emotion category; the above display parameters are also the filtering parameters of the evaluation information; the first user can use one or more of the comment content, evaluation time, performance object and emotion category as filtering parameters in the interactive interface, and complete the filtering parameter configuration by manual input or manual selection in the corresponding text box.

[0066] After obtaining the first filtering instruction issued by the second user, the matching evaluation information can be first obtained according to the filtering parameters in the first filtering instruction; then, each piece of evaluation information is displayed in turn according to the preset priority of other display parameters other than the filtering parameters; wherein the preset priority represents the sorting priority between different display parameters, and also represents the sorting priority of each sub-parameter in each display parameter, which can be pre-configured by the developer of the first large model, or configured by the management system based on the historical filtering conditions of multiple users. The more times the current display parameter or display sub-parameter is used as a filtering parameter, the higher the preset priority of the current display parameter or display sub-parameter.

[0067] For example, the second user uses the evaluation time and emotion category as filtering parameters. At this time, the performance object and the evaluation content are used as other display parameters in addition to the filtering parameters, and the priority of the performance object is higher than the evaluation content, so the sorting is based on the performance object; among the performance objects, the priorities of negative, neutral and positive decrease in turn, and the evaluation information under each display sub-parameter is displayed according to the above sorting method.

[0068] The technical solution of the embodiment of the present invention obtains a first screening instruction issued by a second user through a first interactive interface, including at least one of the comment content, evaluation time, performance object, and emotion category; then, according to the first screening instruction, based on the preset priority of other display parameters other than the screening parameter, each evaluation information is sequentially displayed. In this way, not only the screening and acquisition of evaluation information is realized, but also the sorting of evaluation information based on the preset priority is realized, which not only meets the user's evaluation information screening needs, but also ensures the priority display of the desired evaluation information.

[0069] Embodiment 3

[0070] Figure 3 This is a flowchart of a large model management method based on cloud services provided in the third embodiment of the present invention. The relationship between this embodiment and the above embodiment is that the first large model is a customer management model as an example. Figure 3 As shown, the method includes:

[0071] S301. According to a deployment instruction of a first large model issued by a first user, the first large model is deployed on the cloud, and an interactive configuration interface is displayed to the first user.

[0072] S302, obtaining a first interactive interface of the first large model through the interactive configuration interface, and deploying the first interactive interface locally;

[0073] S303: In response to obtaining a calling instruction of the first large model issued by a second user, displaying the first interactive interface to the second user so as to call the first large model through the first interactive interface.

[0074] S304. Obtain a second screening instruction of the second user through the first interactive interface; wherein the second screening instruction includes at least one of a customer number, economic status, credit rating, and educational background information.

[0075] S305: According to the second screening instruction, based on the preset priorities of other display parameters except the screening parameters, display the information of each customer in sequence.

[0076] In the interactive interface of the customer management model, fixed general function buttons are also displayed, including function buttons such as add, delete, download, export, query and reset displayed at the top of the interface, view and edit buttons configured at the end of each customer information, and display page configuration buttons, single page quantity configuration buttons and jump page buttons configured at the bottom of the interface; the management system performs corresponding processing operations according to the function buttons triggered by the second user in the interactive interface.

[0077] In addition to the general function buttons, according to the display parameters synchronously configured by the first user in the interactive interface when the first model is deployed to the cloud, the interactive interface also displays parameters specific to customer information, namely, customer number, economic status, credit rating and educational information; the above display parameters are also screening parameters for customer information; the first user can use one or more of the customer number, economic status, credit rating and educational information as screening parameters in the interactive interface, and complete the screening parameter configuration by manual input or manual selection in the corresponding text box.

[0078] After obtaining the second filtering instruction issued by the second user, the matching customer information can be first obtained according to the filtering parameters in the second filtering instruction; then, each piece of customer information is displayed in turn according to the preset priority of other display parameters other than the filtering parameters; the preset priority represents the sorting priority between different display parameters, and also represents the sorting priority of each sub-parameter in each display parameter, which can be pre-configured by the developer of the first large model, or configured by the management system based on the historical filtering conditions of multiple users. The more times the current display parameter or display sub-parameter is used as a filtering parameter, the higher the preset priority of the current display parameter or display sub-parameter.

[0079] The technical solution of the embodiment of the present invention obtains a second screening instruction including at least one of customer number, economic status, credit rating and education information issued by a second user through a first interactive interface; then, according to the second screening instruction, based on the preset priorities of other display parameters other than the screening parameters, each customer information is sequentially displayed. In this way, not only the screening and acquisition of customer information is realized, but also the sorting of customer information based on the preset priority is realized, which not only meets the customer information screening needs of users, but also ensures the priority display of desired customer information.

[0080] Embodiment 4

[0081] Figure 4 : is a structural block diagram of a large model management device based on cloud service provided by the fourth embodiment of the present invention, and the device specifically includes:

[0082] A model deployment execution module 601 is used to deploy the first large model on the cloud according to a deployment instruction of the first large model issued by the first user, and to display an interactive configuration interface to the first user;

[0083] An interface deployment execution module 602 is used to obtain a first interactive interface of the first large model through the interactive configuration interface, and deploy the first interactive interface locally;

[0084] The model calling execution module 603 is used to display the first interactive interface to the second user in response to obtaining the calling instruction of the first large model issued by the second user, so as to call the first large model through the first interactive interface.

[0085] The technical solution of the embodiment of the present invention is to deploy the first large model in the cloud according to the deployment instruction of the first large model issued by the first user, and display the interactive configuration interface to the first user; obtain the first interactive interface of the first large model through the interactive configuration interface, and deploy the first interactive interface locally; in response to obtaining the call instruction of the first large model issued by the second user, display the first interactive interface to the second user, so as to call the first large model through the first interactive interface. In this way, not only the deployment and application of the large model is realized, but also the application scope of the large model is expanded and the utilization rate of the large model is improved; at the same time, the large model deployed in the cloud and the interactive interface deployed locally not only improve the data security of the interactive interface itself, but also ensure the call security of the large model call process.

[0086] Optionally, the large model management device based on cloud services is also used to send the first supplementary sample to the first user in response to obtaining a first supplementary sample for the first large model from a third user, so as to confirm through the first user whether to use the first supplementary sample as a training sample for the first large model; if a confirmation instruction from the first user for the first supplementary sample is obtained, the first large model is iteratively trained through the first supplementary sample.

[0087] Optionally, the large model management device based on cloud services is also used to, if a rejection instruction from the first user regarding the first supplementary sample is obtained, copy the second large model based on the first large model, deploy the second large model on the cloud, and iteratively train the second large model through the first supplementary sample; in the label information of the second large model, configure both the source model and the upstream model as the first large model.

[0088] Optionally, the big model management device based on cloud services is also used to respond to a fuzzy call instruction issued by a fourth user, determine a matching target big model according to the identity information of the fourth user, and display a target interaction interface corresponding to the target big model to the fourth user, so as to call the target big model through the target interaction interface.

[0089] Optionally, the first model includes an evaluation management model;

[0090] The large model management device based on cloud services is also used to obtain the first filtering instruction of the second user through the first interactive interface; wherein the first filtering instruction includes at least one of the comment content, evaluation time, performance object and emotion category; according to the first filtering instruction, based on the preset priority of other display parameters except the filtering parameters, each evaluation information is displayed in turn.

[0091] Optionally, the first model includes a customer management model;

[0092] The large model management device based on cloud services is also used to obtain the second screening instruction of the second user through the first interactive interface; wherein the second screening instruction includes at least one of the customer number, economic status, credit rating and educational information; according to the second screening instruction, based on the preset priority of other display parameters except the screening parameters, each customer information is displayed in turn.

[0093] The above device can execute the large model management method based on cloud service provided by any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the large model management method based on cloud service provided by any embodiment of the present invention.

[0094] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0095] Embodiment 5

[0096] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, electronic devices, blade electronic devices, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0097] like Figure 5 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0098] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0099] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a large model management method based on cloud services.

[0100] In some embodiments, the large model management method based on cloud services may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on a heterogeneous hardware accelerator via a ROM and / or a communication unit. When the computer program is loaded into RAM and executed by a processor, one or more steps of the large model management method based on cloud services described above may be performed. Alternatively, in other embodiments, the processor may be configured to execute the large model management method based on cloud services in any other appropriate manner (e.g., by means of firmware).

[0101] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0102] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or electronic device.

[0103] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0104] To provide interaction with a user, the systems and techniques described herein may be implemented on a heterogeneous hardware accelerator 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) through which a user can provide input to the heterogeneous hardware accelerator. Other types of devices may also be used to provide interaction with a user; for example, the 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, voice input, or tactile input).

[0105] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data electronic device), or a computing system that includes middleware components (e.g., an application electronic device), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0106] The computing system may include a client and an electronic device. The client and the electronic device are generally remote from each other and usually interact through a communication network. The relationship between the client and the electronic device is generated by computer programs running on corresponding computers and having a client-electronic device relationship with each other. The electronic device may be a cloud electronic device, also known as a cloud computing electronic device or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0107] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0108] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A large model management method based on cloud service, characterized in that: include: According to a deployment instruction of the first large model issued by the first user, the first large model is deployed in the cloud, and an interactive configuration interface is displayed to the first user; Obtaining a first interactive interface of the first large model through the interactive configuration interface, and deploying the first interactive interface locally; In response to obtaining a calling instruction of the first large model issued by a second user, the first interactive interface is displayed to the second user so as to call the first large model through the first interactive interface.

2. The method according to claim 1, characterized in that The cloud service-based large model management method further includes: In response to obtaining a first supplementary sample for the first large model from a third user, sending the first supplementary sample to the first user, so as to confirm through the first user whether to use the first supplementary sample as a training sample for the first large model; If a confirmation instruction of the first user for the first supplementary sample is obtained, the first large model is iteratively trained using the first supplementary sample.

3. The method according to claim 2, characterized in that After sending the first supplementary sample to the first user so as to obtain confirmation from the first user whether to use the first supplementary sample as a training sample for the first large model, the method further includes: If a rejection instruction of the first user for the first supplementary sample is obtained, a second large model is obtained by copying the first large model, the second large model is deployed in the cloud, and the second large model is iteratively trained using the first supplementary sample; In the tag information of the second largest model, both the source model and the upstream model are configured as the first largest model.

4. The method according to claim 1, characterized in that The large model management method based on cloud service also includes: In response to obtaining a fuzzy call instruction issued by a fourth user, a matching target large model is determined according to the identity information of the fourth user, and a target interaction interface corresponding to the target large model is displayed to the fourth user so as to call the target large model through the target interaction interface.

5. The method according to claim 1, characterized in that The first major model includes the evaluation management model; After calling the first large model through the first interactive interface, the method further includes: Obtaining, through the first interactive interface, a first screening instruction of the second user; wherein the first screening instruction includes at least one of comment content, evaluation time, performance object, and emotion category; According to the first filtering instruction, each evaluation information is displayed in sequence based on the preset priorities of other display parameters except the filtering parameters.

6. The method according to claim 1, characterized in that The first model includes a customer management model; After calling the first large model through the first interactive interface, the method further includes: Obtaining, through the first interactive interface, a second screening instruction of the second user; wherein the second screening instruction includes at least one of a customer number, economic status, credit rating, and educational background information; According to the second screening instruction, each customer information is displayed in sequence based on the preset priorities of other display parameters except the screening parameters.

7. A large model management device based on cloud service, characterized in that: include: A model deployment execution module, configured to deploy the first large model on the cloud according to a deployment instruction of the first large model issued by the first user, and to display an interactive configuration interface to the first user; An interface deployment execution module, used for obtaining a first interactive interface of the first large model through the interactive configuration interface, and deploying the first interactive interface locally; The model calling execution module is used to display the first interactive interface to the second user in response to obtaining a calling instruction of the first large model issued by the second user, so as to call the first large model through the first interactive interface.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the cloud service-based large model management method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the cloud service-based large model management method according to any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, which, when executed by a processor, implements the cloud service-based large model management method according to any one of claims 1 to 6.

Images