71 results about "Service model" patented technology

The invention discloses a model deployment method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring an initial deployment strategy group for a service model, wherein the initial deployment strategy group comprises two deployment strategies; inputting the feature code of each deployment strategy in the initial deployment strategy group into a pre-trained proxy model, and determining performance distribution information of each deployment strategy on the processing equipment; adjusting at least one item of input by utilizing preset label distribution, and obtaining an adjusted deployment strategy group under the condition that the difference between the output performance distribution information and the label distribution meets a set requirement; and determining a target deployment strategy in the adjusted deployment strategy group, and deploying the service model based on the target deployment strategy. According to the scheme, the time loss for exploring the model deployment strategy is reduced, and the model deployment efficiency is improved.

The invention provides an information processing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of large models, deep learning and the like. The information processing method comprises the steps that a query statement of a user is acquired, and a model identifier of at least one candidate service model is determined based on the query statement; generating a first cue word based on the query statement and the model identifier, inputting the first cue word into a pre-trained target large model, and outputting screening parameters of the candidate service model by the target large model according to the first cue word; determining a target service model from the candidate service models according to the screening parameters; and inputting the query statement into the target service model to obtain feedback information corresponding to the query statement. Therefore, the target service model can be determined more efficiently and accurately, and the efficiency and accuracy of outputting the feedback information by the target service model are improved by inputting the query statement to the target service model.

The invention provides an artificial intelligence auxiliary judgment method, system and device, a storage medium and a product. The system comprises a scene application layer, a model application layer and a model service layer. And the scene application layer is used for acquiring case information and business scene information of the task. And the model application layer is used for acquiring task configuration parameters of the tasks according to the business scene information. The model service layer is used for acquiring operation state information of a model instance and acquiring case information and task configuration parameters of a task; obtaining case information of the task, an input text vector of task configuration parameters and model capability vectors of different types of service models; according to the input text vector and the model capability vector, obtaining a matching degree between the task and different types of service models; and according to the matching degree and the model instance operation state information, distributing the case information and the task configuration parameters of the task to the corresponding model instance of the service model of the corresponding type for processing, and obtaining a reasoning result of the task.

The invention provides an API automatic generation method and system based on model design, and belongs to the technical field of software development. The method comprises the steps that metadata is extracted based on a service model created by a first user; generating a corresponding API based on the metadata and a preset generation rule; and providing the API for a second user. According to the model design-based API automatic generation method and system provided by the invention, the development efficiency of the API can be improved.

The embodiment of the invention discloses a data processing method and device, a computer, a storage medium and a program product, and the method comprises the steps: carrying out the data enhancement of a source business sample through employing a target business sample, and obtaining a business enhancement feature; predicting a first prediction result of the business enhancement feature through the first initial model, and performing parameter adjustment on the first initial model according to the first prediction result and an initial feature distance between the source business sample and the target business sample to obtain a first business model; predicting a second prediction result of the target service sample through the first service model, predicting a third prediction result of the target service sample through the second initial model, and performing parameter adjustment on the second initial model according to the second prediction result and the third prediction result to obtain a second service model; the first business model and the second business model have the same model structure. According to the invention, the accuracy and efficiency of data processing can be improved.

The invention relates to the technical field of artificial intelligence, in particular to a verbal skill confrontation training generation method and device based on a large model, equipment and a storage medium, and the method comprises the steps: generating a simulation inquiry based on a preset user portrait, then obtaining a response of a service large model, and comprehensively evaluating the response quality; and the specific defect type of the service model in logic understanding or verbal skill expression is diagnosed through the cognitive deviation between the response and the user expectation by another evaluation model, so that a targeted optimization strategy is generated, the service model is finally driven to carry out directional reinforcement learning, and the verbal skill ability of the large service model is iteratively improved. According to the method, an adversarial sample is dynamically generated, and deep diagnosis is carried out in combination with cognitive deviation, so that a service model can understand deep intentions and emotion demands of different user groups fundamentally. Therefore, the strain capacity and the communication accuracy of the service model in a real interaction scene are remarkably improved, and the user satisfaction is effectively improved.

The business travel service management method based on the LLM is applied to a service system constructed based on the LLM. Services provided by the service system for users comprise a plurality of service fields; the service system manages a plurality of service models in one-to-one correspondence with a plurality of service fields; comprising the following steps: receiving a user question related to business travel service input by a user; retrieving target structured knowledge from a target sub-knowledge base related to the user questions in a plurality of sub-knowledge bases in one-to-one correspondence with the plurality of service fields, and acquiring historical context information from historical user questions input by the user; generating a cue word based on the user question, the target structured knowledge and the historical context information, and inputting the cue word to an LLM, so that the LLM generates structured intention description information based on the cue word; and analyzing the intention description information, determining a target service field corresponding to the user intention, and distributing the user question to a target service model corresponding to the target service field.

The invention discloses a code-free application construction method and device based on a multistage service model, and relates to the field of code-free application construction. The method comprises the following steps: receiving a service demand of a user to obtain a demand feature tag; based on the demand feature tags, matching service models meeting conditions to obtain a multi-stage service model set; analyzing and instantiating the multi-stage business model set through a generation engine, and outputting an initial application component; receiving a configuration instruction of a user, and adjusting the initial application component to obtain a target application component; calling a data bridging interface, a permission matrix interface and a cross-component collaboration interface, and establishing a data flow relationship and a permission mapping rule among the components in the target application component to obtain an initial application and integrated link; and verifying the initial application, if the verification result meets the application release condition, deploying the initial application to the target operation environment, and outputting the target application. By implementing the technical scheme provided by the invention, the application construction efficiency and stability can be remarkably improved.

Embodiments of the present application provide a data processing method and a related apparatus. The method comprises: obtaining a plurality of pieces of sample data about a service system, wherein each piece of sample data comprises feature data, label data, and a confidence level; on the basis of a plurality of pieces of first sample data, generating second sample data of which the sample type is "black sample", wherein the first sample data comprises sample data having the confidence level higher than a preset threshold among the plurality of pieces of sample data; and generating a new training sample set on the basis of a historical data training sample set and the second sample data, wherein the training sample set is used for training a service model, and the service model is used for performing sample type prediction on the basis of service data in an operation process of the service system. By using the embodiments of the present application, the quality of the training sample set can be improved, thereby improving the performance index of the trained model.

The invention provides a model training method, a medium, electronic equipment and a program product, and relates to the technical field of machine learning, and the method comprises the steps: sending a business model to a client, enabling the client to train the business model according to the business data of the client, and obtaining a trained first business model, according to the method and the device, the first business model is acquired, the vector representation corresponding to the business data is acquired from the first business model, the vector representation is returned to the server side, the server side trains the business model based on the vector representation, and the trained second business model is acquired, so that the business data can be more effectively acquired on the premise of ensuring the privacy of the business data of the client side. The training of the service model of the server is completed, so that the service model of the server can better provide services to the outside, and the model structures of the service models, used for federated learning, of the server and the client can be kept consistent, so that the cognition of the server and the client on the service models is kept consistent, and the service experience of the client is improved. Therefore, the online service model of the server can have a better effect.

The invention discloses an intelligent low-carbon service model and method based on block chain fusion, particularly relates to the technical field of low-carbon management, and is used for solving the problem that the credible recognition and settlement of carbon behaviors are not clear. According to the method, identity verification, time marking and caliber standardization are carried out on energy consumption and travel multi-source data through a trusted data gateway, a carbon behavior voucher containing a signature and an abstract is generated, minimum disclosure under an index upper chain and an original text chain is adopted, it is ensured that the source and the caliber are verifiable and cannot be tampered, and then merging is carried out through a unified event model; and performing conflict resolution and consistency verification to form a one-event one-key event, attaching a consistency label and a credibility index, performing calculation by a rule base and a scene parameter set, performing intelligent contract accounting, and providing rollback correction by using a unique identifier of the event, enabling the credibility index to participate in integral and right confirmation, performing low-credibility entering and re-verification, and suppressing abnormities. And the fusion accuracy and the auditing efficiency are improved.

The invention discloses a confidence evaluation method and device for a large language model, equipment and a storage medium, and the method comprises the steps: obtaining a cue word set which comprises a plurality of cue words; sequentially inputting a plurality of cue words in the cue word set into the to-be-evaluated large language model to obtain a target sequence generated by the to-be-evaluated large language model based on each cue word, and obtaining the confidence coefficient of each target sequence according to the confidence coefficient of each lexical element in each target sequence; and obtaining a generation number of the target sequences, determining a confidence degree distribution result of the to-be-evaluated large language model according to the confidence degrees of all the target sequences when the generation number reaches a preset number, and generating an evaluation result of the to-be-evaluated large language model according to the confidence degree distribution result. Therefore, the problems that it is difficult for a user to effectively monitor the open source large language service model and it is difficult to provide evidence that the service model has degradation behaviors are solved, and the service quality of the open source large language model can be monitored on the user side.

The embodiment of the invention provides a business model intelligent adjustment method and device, and relates to the technical field of business model adjustment technologies. The method comprises the following steps: acquiring business data and model data; based on the business data and the model data, constructing a model risk potential energy distribution diagram used for indicating risk potential energy distribution in the business model; based on the model risk potential energy distribution diagram, performing model derivation processing on the business model by constructing a directional correction path to obtain a derivation model; and based on analysis of the performance loss of the derivative model, performing stabilization processing on the derivative model to obtain a target business model. According to the method and the device, the problem of low model adjustment efficiency is solved, and the effect of improving the model adjustment precision and efficiency is further achieved.

The present application relates to the technical field of data processing, and discloses a configuration data migration method, device, equipment, storage medium and program product, the configuration data migration method comprises: obtaining first configuration data from a preset database, and determining a data point position for marking the first configuration data; in a manner of dictionary query, determining a control point position corresponding to the data point position, and determining a first control instruction marked by the control point position; encapsulating the first configuration data and the first control instruction as a second control instruction, the second control instruction containing second configuration data; and issuing the second control instruction to a service model in an online running mode, so that the second configuration data takes effect in the service model. The present application transfers the initialization configuration data in the service model in an offline running mode to the service model in an online running mode, thereby overcoming the problems of low efficiency and easy errors in manual input of the initialization configuration data.

The one or more embodiments of the application provide a method, device and storage medium for evaluating running of a privacy computing algorithm, the method comprising: obtaining algorithm running information corresponding to a privacy computing algorithm to be evaluated and device configuration information of a device for running the privacy computing algorithm; inputting the algorithm running information and the device configuration information into a service model of a large language model, to predict, by the service model of the large language model, a running condition of the privacy computing algorithm on the device based on the algorithm running information and the device configuration information; the service model of the large language model being a model obtained by performing supervised fine-tuning training on a base model of the large language model based on training samples including the algorithm running information and the device configuration information and labeled with the running condition; obtaining the running condition of the privacy computing algorithm on the device predicted by the service model of the large language model, and outputting the running condition.

The embodiment of the application discloses a network change-based service model optimization method, device, equipment and medium. The method belongs to the technical field of Internet of Things and comprises the following steps: querying the network access attachment state of a communication module; if the network access attachment state is attachment failure, entering a network access failure abnormal processing scene; if the network access attachment state is attachment success, querying the wireless signal parameter of the communication module, and detecting whether the current coverage scene is a weak coverage scene according to the wireless signal parameter; if it is a weak coverage scene, entering the weak coverage scene; if it is not a weak coverage scene, querying the data sending result of the communication module; if the sending result is sending failure, entering a busy communication scene; optimizing the service model according to the different scenes to obtain a target service model; and executing the target service model. The embodiment of the application can improve the communication success rate, avoid network congestion, reduce network resource waste, and further improve the communication function of the Internet of Things.

A system can comprise a near real-time radio access network intelligent controller that comprises an application and a service model component, wherein the service model component is configured to receive respective indications of supported service models and key performance indicators from respective network nodes of a group of network nodes that is part of a radio access network, wherein the service model component is configured to receive a request from the application for a key performance indicator, wherein the service model component is configured to subscribe to a network node of the group of network nodes for the key performance indicator, wherein the network node supports a service model that is unsupported by the application and that is supported by the service model component, and wherein the key performance indicator is returned to the application via a communications protocol that is supported by the application.

The invention provides a building energy consumption analysis method and system based on an MCP service model and an intelligent agent, and relates to the technical field of building energy saving and artificial intelligence, and the method comprises the steps: constructing and packaging an MCP service model, and abstracting the MCP service model into a standardized function interface after packaging; acquiring and storing operation equipment and equipment operation parameters in the building; an input request of a user is obtained, a task intention in the input request is recognized, the task intention is converted into specific API calling according to the task intention, and the API obtains structured energy consumption data by calling an MCP function interface; combining the structured energy consumption data returned by the MCP with the cue word template, transmitting the combined Agents to the large language model, and outputting to obtain a report; and visualizing or exporting the report. According to the invention, full-automatic generation from complex building energy consumption data to a structured report containing natural language analysis and visual charts is realized.

The present application provides a method, device, electronic device and storage medium for generating a service result, wherein the method for generating a service result includes: responding to a service request sent by a user through a service request end, searching for a general model file that matches the service request; based on the file category to which the general model file belongs, converting the input information carried by the service request into standard input information that satisfies the input format corresponding to the file category; parsing the general model file to obtain a service model corresponding to the general model file, inputting the standard input information into the service model, obtaining the service result output by the service model, and sending the service result to the service request end. The present application can obtain a general model file that matches a service request, generate a service result corresponding to a service request based on the service model obtained by parsing the general model file, and has high efficiency in service model engineering.

The invention relates to a multi-time scale-based RAN (Radio Access Network) slice hierarchical wireless resource management method, which comprises the following steps of: allowing a service model 1 and a service model 2 to transmit on a resource block by utilizing an orthogonal multiple access punching mechanism and a punching mechanism consisting of a power domain non-orthogonal multiple access technology and a spatial domain non-orthogonal multiple access technology; the user of the service model 1 and the user of the service model 2 can utilize the wireless resource more efficiently or share the same wireless resource. On the basis, the invention provides a combination of a high-level control model and an optimal bottom-level control model to form a multi-time-scale wireless resource management strategy, and the strategy is also combined with deep reinforcement learning, so that the multi-time-scale wireless resource management is realized. The problem of solving a target function can be converted into a Gaussian Markov decision process by using an option-approver framework on a large time scale, and different service requirements correspond to sub-targets.

This application relates to the field of communication technologies, and discloses a model training processing method and apparatus, a terminal, and a network side device. The model training processing method in embodiments of this application includes: obtaining, by a first device, first information, the first information including first data; and processing, by the first device, the first data by using a first model to obtain second data, where both the first data and the second data are usable for training a second model, the second model is a service model, and the second data meets at least one of the following: in a case that the first data is unlabeled data, the second data is labeled data; and a data volume of the second data is greater than a data volume of the first data in a case that the first data is labeled data.

An embodiment of this specification discloses a service processing method, apparatus, and device. The method is applied to a service processing device, and the service processing device includes a trusted execution environment, including: obtaining service data for a target service, where the target service corresponds to a service model for processing the service data, the service model is divided into a first sub-model and a second sub-model, the second sub-model includes model parameters to be protected recorded in the model protection rules corresponding to the target service, and the second sub-model is set in the trusted execution environment and can run in the trusted execution environment; inputting the service data into the first sub-model divided from the service model corresponding to the target service to obtain a first output result corresponding to the service data; transmitting the first output result to the trusted execution environment through the application corresponding to the target service, and in the trusted execution environment, inputting the first output result into the second sub-model to obtain a model prediction result corresponding to the service data.

An operation control method includes: in the process of an electronic device running a target application, in response to a target triggering event, launching a first target service model, where the first target service model is configured to provide a target functional service; monitoring the adaptation value between the first target service model and the target application; and, when the adaptation value changes to fall within a target threshold range, controlling the electronic device to switch from running the first target service model to launching a second target service model, where the quality of the functional service provided by the second target service model is better than that of the first target service model, and / or the user experience of the second target service model is better than that of the first target service model.

The invention relates to a business model generation method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring general process information of a target service in each region, and generating a general process tree model based on the general process information; obtaining reference exclusive process information and newly-added exclusive process information corresponding to the target service in each region, and generating exclusive process tree models corresponding to each region based on the reference exclusive process information and the newly-added exclusive process information; and taking the general process tree model as a front-end service model, taking the exclusive process tree model corresponding to each region as a back-end service model, and obtaining a global service model corresponding to the target service in each region based on the front-end service model and each back-end service model. By adopting the method, the business model generation efficiency can be improved.

The invention discloses a model updating method, device, system and equipment, a medium and a product, relates to the technical field of computers, and can give consideration to personalized model training of a business scene and high-precision model training based on high-performance computing power resources. The method comprises the following steps: a client receives a first service model obtained by training of a server; processing the service data of the client by using a first service model obtained by training of the server to obtain a service processing result; displaying the service processing result, and obtaining user feedback information in response to a feedback operation of the user on the service processing result; and under the condition that the user feedback information indicates that the service processing result is incorrect, updating the first service model based on the user correction result to obtain an updated second service model.

The invention relates to a service mode self-recognition and parameter self-tuning method and device and electronic equipment. The method comprises the following steps: receiving archived log data from a source end database and performance index data from an execution engine, performing metadata level analysis on the archived log data, and extracting multi-dimensional service features to construct a dynamic fingerprint vector; inputting the performance index data and the dynamic fingerprint vector into a pre-trained machine learning model, so that the machine learning model outputs a target service mode label corresponding to the current service load according to the performance index data and the dynamic fingerprint vector; generating a target parameter configuration according to the target service mode label and a corresponding parameter generation strategy; and the target parameter configuration is issued to the execution engine, so that the execution engine adjusts the running state of the execution engine according to the target parameter configuration, and the synchronized data change is written into the target database. The technical problem that the service model change cannot be self-adapted in the prior art is solved.

This application discloses a data processing method performed by a computer device. Obtained service data is inputted into a pre-trained model and an initial service model to obtain first fully-connected layer outputs of the pre-trained model and second fully-connected layer outputs of the initial service model. The pre-trained model and the initial service model construct modeling units with different granularities, first modeling units of the pre-trained model are matched with second modeling units of the initial service model, fully-connected layer outputs of the second modeling units have the same sequence length as fully-connected layer outputs of matched target first modeling units so that with the assistance of the pre-trained model, the target service model can be obtained through the initial service model, the knowledge distillation of the models including modeling units with different granularities is realized, thereby effectively improving the service performance of the service model.

Various embodiments of the present technology generally relate to systems and methods for providing a service model engine. In an aspect a method includes identifying, by a service model engine, a swagger file from a network vendor and parsing the swagger file for API endpoints. The service model engine may generate resource specifications based on the API endpoints and may generate delivery actions for each API endpoint. Each delivery action may include delivery parameters for each API endpoint, The service model engine may also map each of the delivery parameters to corresponding characteristics in the resource specifications to generate parameter mappings. The service model engine may generate a service delivery model including the resource specifications, the delivery actions, and the parameter mappings, where the service delivery model is used by a service orchestration system to deliver respective services.

The invention discloses a business processing method and device, equipment and a program product, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring service processing associated data, service processing party data, service processing constraint data and service feedback data of a to-be-processed service, and generating a current multi-dimensional feature vector; a weight calculation routing network is adopted to analyze the current multi-dimensional feature vector, and the current weight of each target service model is obtained; respectively analyzing the current multi-dimensional feature vector by adopting each target service model to obtain a current service detection result of each target service model on the to-be-processed service; and according to the current weight of each target service model, fusing each current service detection result to obtain a target fusion result, and according to the target fusion result, generating a current service processing instruction. According to the technical scheme of the embodiment of the invention, the service processing efficiency and the applicability of the service processing method are improved.

The embodiment of the present application provides a power consumption portrait method, device, data center and storage medium. In the embodiment of the present application, a reference model and a reference service of a new service model can be acquired; a historical power consumption portrait of the reference model running the reference service, a power consumption dictionary of the reference model and a power consumption dictionary of the new model are acquired; further, an initial power consumption portrait of a to-be-tested model running a to-be-tested service (the new service model) can be determined according to the historical power consumption portrait. Further, actual power consumption data generated by the to-be-tested model running the to-be-tested service (the new service model) deployed in a cabinet can be acquired; and the initial power consumption portrait is corrected by using the actual power consumption data, so that adaptive adjustment of the new service model portrait is realized, the obtained power consumption portrait of the new service model is as close as possible to the actual power consumption portrait, and the accuracy of the power consumption portrait is improved.