Information query method, apparatus and system

Abstract

The present application relates to the technical field of artificial intelligence. Disclosed are an information query method, apparatus and system. The method comprises: in response to a query request, acquiring, from a knowledge base, first knowledge information which matches knowledge information carried in the query request, wherein the first knowledge information is knowledge information related to the query request; on the basis of the first knowledge information, generating prompt information related to the query request, wherein the prompt information is used for supplementing the query request; and on the basis of the query request and the prompt information, outputting a query result corresponding to the query request. On this basis, a query request can be supplemented and optimized by means of task-related knowledge information, thereby improving the accuracy of a query result during an information query made on the basis of the query request.

Description

Information query method, device and system

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on November 24, 2023, with application number 202311591589.2 and application name “An information query method, device and system”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of artificial intelligence technology, and in particular to an information query method, device, and system. Background Art

[0003] With the development of artificial intelligence, the application scenarios of large network models are becoming increasingly diverse, resulting in higher performance requirements for large network models in various fields. However, due to the huge number of parameters in large network models, the training cost of large network models is expensive, and it is difficult to ensure the stability of the model effect. Based on this, related technologies use pre-training to train large network models and provide external services. During pre-training of large network models, due to the restrictions on the word fragments allowed to be input in a single session control of the large network model, the large network model cannot incorporate relevant information about the task execution environment when executing tasks, resulting in inaccurate execution results of the large network model. The same task needs to be executed repeatedly, which reduces the efficiency and accuracy of the large network model during application.

[0004] Summary of the Invention

[0005] The present application provides an information query method, device and system, which can supplement and optimize query requests through task-related knowledge information, thereby improving the accuracy of query results.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions.

[0007] In a first aspect, the present application provides an information query method, which is applied to an information query system, wherein the information query system includes a knowledge base, wherein the knowledge base includes knowledge information related to one or more query tasks, and the method may include:

[0008] First, in response to a query request, first knowledge information matching the query request is obtained from the knowledge base; this step is mainly used to obtain first knowledge information related to the query request in the knowledge base based on the knowledge information carried in the query request when a query request is received. The first knowledge information is one or more knowledge information in the knowledge base, and the first knowledge information can expand the knowledge information carried in the query request.

[0009] Then, prompt information related to the query request is generated based on the first knowledge information; this step is mainly used to determine prompt information related to the first knowledge information based on the first knowledge information obtained in the previous step. The prompt information may include one or more prompt information, which is used to supplement the query content carried by the query request to make the query content carried in the query request clearer.

[0010] Finally, the query result corresponding to the query request is output according to the query request and the prompt information. This step is mainly used to combine the query request and the prompt information related to the query request to obtain the query result corresponding to the query request and output it.

[0011] As a possible implementation method, the above-mentioned acquisition of the first knowledge information matching the query request from the knowledge base may include: acquiring the first knowledge information matching the query request from the knowledge base according to a first preset condition, wherein the first preset condition is related to one or more of the following: knowledge relevance, time relevance, and type relevance. Based on this, the relevance of the knowledge information in the knowledge base to the query request can be judged from different dimensions through the knowledge information carried by the query request, and the knowledge information with a high relevance to the knowledge information carried by the query request is used as the first knowledge information. When judging the relevance between the knowledge information carried by the query request and the knowledge information in the knowledge base, the judgment can be made by combining one or more of knowledge relevance, time relevance, and type relevance, or it can be adjusted according to the specific business. It should be noted that the relevance can also be judged based on other attributes, and no limitation is made here.

[0012] As a possible implementation, the query request carries query content, and obtaining first knowledge information matching the query request from the knowledge base according to a first preset condition may include: using as the first knowledge information knowledge information whose updated content has a knowledge relevance with the query content greater than or equal to a preset threshold. Based on this, the first knowledge information can be determined based on the knowledge relevance between the knowledge information in the query request and the knowledge information in the knowledge base. Specifically, the first knowledge information can be determined based on the knowledge relevance between the knowledge information in the query request and the knowledge information in the knowledge base. Specifically, the knowledge relevance indicates the degree of semantic similarity between the updated content in the knowledge information in the knowledge base and the query content in the knowledge information in the query request.

[0013] As a possible implementation, the query request carries a query time, and the obtaining of first knowledge information matching the query request from the knowledge base according to a first preset condition includes: using as the first knowledge information knowledge information having a time correlation between the update time of the knowledge information and the query time greater than or equal to a preset threshold. Based on this, the first knowledge information can be determined based on the time correlation between the knowledge information in the query request and the knowledge information in the knowledge base. Specifically, the first knowledge information can be determined based on the time correlation between the knowledge information in the query request and the knowledge information in the knowledge base. Specifically, the knowledge information having a time correlation greater than or equal to a preset threshold can be used as the first knowledge information, wherein the time correlation indicates the degree of temporal proximity between the update time of the knowledge information in the knowledge base and the query time of the knowledge information in the query request.

[0014] As a possible implementation, the query request carries a query type, and the obtaining of first knowledge information matching the query request from the knowledge base according to a first preset condition includes: using as the first knowledge information knowledge information having a type relevance greater than or equal to a preset threshold between the update type of the knowledge information and the query type. Based on this, the first knowledge information can be determined based on the type relevance between the knowledge information in the query request and the knowledge information in the knowledge base, and the knowledge information having a type relevance greater than or equal to a preset threshold can be used as the first knowledge information, wherein the knowledge relevance indicates the degree of type similarity between the update type in the knowledge information in the knowledge base and the query type in the knowledge information in the query request.

[0015] As a possible implementation method, the query request includes a task identifier, the knowledge base includes multiple sub-knowledge bases, and the multiple sub-knowledge bases correspond to different task identifiers. The obtaining of the first knowledge information matching the query request from the knowledge base includes: obtaining the sub-knowledge base matching the query request from the multiple sub-knowledge bases according to the task identifier; obtaining the first knowledge information matching the query request from the sub-knowledge base. Based on this, the knowledge base may include multiple sub-knowledge bases, and the multiple sub-knowledge bases may belong to the same knowledge base and be centrally set up, or they may be distributed in different locations according to task requirements, and the multiple sub-knowledge bases correspond to different task identifiers. The sub-knowledge base corresponding to the task identifier in the query request can be determined, and the first knowledge information can be obtained from the sub-knowledge base corresponding to the task identifier carried in the query request. The correlation between the first knowledge information and the knowledge information carried in the query request is greater than or equal to a preset threshold. Specifically, the standard for obtaining the first knowledge information is the same as that in the aforementioned embodiment and will not be elaborated here.

[0016] As a possible implementation method, the above-mentioned generation of prompt information related to the query request based on the first knowledge information includes: based on a prompt logic algorithm, generating prompt information related to the query request based on the first knowledge information, and the prompt information is used to supplement the query content carried by the query request. Based on this, one or more first knowledge information obtained from the knowledge base is highly relevant to the knowledge information carried by the query request, and the relevant content of the first knowledge information can be converted into prompt information through the prompt logic algorithm, wherein the prompt logic algorithm is used to convert the first knowledge information into simpler prompt information, and the prompt logic algorithm includes a prompt logic function to supplement or limit the query content carried in the query request, so that the query content is clearer and more complete, which is convenient for understanding and querying the query content. For a query request, there can be one or more prompt information corresponding to improve the query content from different levels, which is not limited here.

[0017] As a possible implementation method, the above-mentioned prompt information related to the query request is generated based on the prompt logic algorithm according to the first knowledge information, including: based on the prompt logic algorithm, obtaining multiple candidate prompt information corresponding to the first knowledge information; determining the prompt information from the one or more candidate prompt information, wherein the prompt information is the candidate prompt information among the multiple candidate prompt information whose similarity with the query content is greater than or equal to a preset threshold. Based on this, the first knowledge information can be converted into one or more candidate prompt information according to the logical prompt algorithm. When there is one candidate prompt information, the candidate prompt information can be directly used as the prompt information. When there are multiple candidate prompt information, it is necessary to screen among the multiple candidate prompt information to determine the candidate prompt information with a high degree of match with the query request as the prompt information. In some examples, the corresponding candidate prompt information can be determined as the prompt information by the similarity between the candidate prompt information and the query content in the query request being greater than a preset threshold. The prompt information can be one or more, and different screening criteria for the prompt information can be set according to specific needs. No limitation is made here.

[0018] As a possible implementation method, the query request carries the device identification of the network device that initiated the query request, and the query result corresponding to the query request is output according to the query request and the prompt information, including: obtaining the query result corresponding to the query request according to the query request and the prompt information; and outputting the query result to the network device according to the device identification. Based on this, the query request carries the device identification of the network device that sent the query request, wherein the network device may include a terminal device and a network element device, etc., which are capable of executing the query request, and are not limited here. The query result corresponding to the query request is obtained based on the query content in the knowledge information carried in the query request and the supplement and limitation of the query content by the prompt information, and the query result is returned to the network device that issued the query request according to the device identification carried by the query request.

[0019] As one possible implementation, obtaining a query result corresponding to the query request based on the query request and the prompt information includes: obtaining a query result corresponding to the query request based on the query request and the prompt information based on an information query model. In this regard, the information query model includes a knowledge question-and-answer model, which is used to obtain a query result corresponding to the query request based on the input query content and the prompt information. The prompt information is used to supplement and limit the query content, making the query content easier for the information query model to understand and resulting in more accurate query results.

[0020] As a possible implementation method, the method also includes: in response to a knowledge update request, updating the knowledge base according to the knowledge information carried in the knowledge update request. Based on this, the information in the knowledge base in the above embodiment comes from the received knowledge update request. The knowledge update request can come from a network device, specifically, it can include a terminal device and a network element device, etc., which is not limited here. The network device stores the relevant knowledge information of its own environment, the knowledge information obtained by itself through interaction with other network devices, etc. in the knowledge base by sending a knowledge update request. Specifically, by obtaining the knowledge information carried in the knowledge update request, the knowledge base is updated, so that the relevant knowledge information of the network device's own environment and the knowledge information of interaction with other network devices can be saved in the knowledge base.

[0021] As one possible implementation, the knowledge information includes updated content, and updating the knowledge base according to the knowledge information carried in the knowledge update request includes updating the knowledge base according to the updated content. Based on this, the knowledge information carried in the knowledge update request may include updated content, specifically including the environment of the network device or knowledge information generated with other network devices. When the knowledge update request includes the updated content, the updated content is saved in the knowledge base, and the knowledge information in the knowledge base is updated.

[0022] As a possible implementation, the knowledge information includes an update time, and updating the knowledge base according to the knowledge information carried in the knowledge update request includes updating the knowledge base according to the update time. Based on this, the knowledge update request may include not only the update content but also the update time. In this case, the update content and the update time may be stored together in the knowledge base, wherein there is a corresponding relationship between the update content and the update time, and the update time is used to indicate when the update content is stored in the knowledge base.

[0023] As a possible implementation, the above-mentioned knowledge information includes an update type, and updating the knowledge base according to the knowledge information carried in the knowledge update request includes: updating the knowledge base according to the update type. Based on this, in addition to including the update content, the knowledge update request may also include the update type. In such a case, the update content and the update type can be stored together in the knowledge base, wherein there is a corresponding relationship between the update content and the update type, and the update type is used to indicate that the update content is of a corresponding type. In some examples, the update content corresponding to different update types is stored in different locations to facilitate subsequent search and classification of the knowledge information.

[0024] As a possible implementation method, the above-mentioned knowledge update request includes a task identifier, the knowledge base includes multiple sub-knowledge bases, and the multiple sub-knowledge bases correspond to different task identifiers. The updating of the knowledge base according to the knowledge information carried in the knowledge update request includes: obtaining a sub-knowledge base that matches the knowledge update request from the multiple sub-knowledge bases according to the task identifier; and updating the sub-knowledge base according to the knowledge information carried in the knowledge update request. Based on this, the knowledge base may include multiple sub-knowledge bases, and the multiple sub-knowledge bases may belong to the same knowledge base and be centrally set up, or they may be distributed in different locations according to task requirements, and the multiple sub-knowledge bases correspond to different task identifiers. The sub-knowledge base corresponding to the task identifier in the knowledge update request can be determined, and the knowledge information carried in the knowledge update request can be stored in the sub-knowledge base. The knowledge information carried in the knowledge update request may include update content, update time, update type, etc., and may also carry other information related to the update request as needed, without any limitation here.

[0025] As a possible implementation, the method further includes: in response to a model optimization request, optimizing one or more model parameters in the information query model related to the model optimization request according to the knowledge information carried in the model optimization request. Based on this, for a model optimization request, one or more model parameters in the information query model can be optimized according to the knowledge information in the model optimization request. The information query model can be a knowledge question and answer model. In some examples, when optimizing the information query model according to the knowledge information carried in the model optimization request, the model parameters in the model related to the model optimization request can be optimized, while other parameters remain unchanged, thereby increasing the efficiency of model training while improving the stability of the model.

[0026] As a possible implementation method, the above-mentioned optimization of one or more model parameters related to the model optimization request in the information query model according to the knowledge information carried in the model optimization request includes: matching and obtaining second knowledge information from the knowledge base according to the knowledge information carried in the model optimization request; optimizing one or more model parameters related to the model optimization request in the information query model according to the second knowledge information. Based on this, knowledge information with a high relevance to the knowledge information in the knowledge base can be determined as the second knowledge information according to the knowledge information carried in the model optimization request. Specifically, the standard in the process of determining the second knowledge information can adopt the relevant standard for determining the first knowledge information in the above-mentioned embodiment, or the standard for selecting the second knowledge information can be adjusted according to the specific model training requirements. No limitation is made here.

[0027] As one possible implementation, the information query system includes a knowledge question-and-answer system, the query request includes a question request, and the query result includes an answer result corresponding to the question request. It should be noted that the information query system may include a knowledge question-and-answer system, which responds to the question request and determines first knowledge information in a knowledge base based on the knowledge information carried in the question request, and determines prompt information corresponding to the question request based on the first knowledge information. Based on the question request and the prompt information, the system obtains an answer result corresponding to the question request and outputs it.

[0028] In the second aspect, the present application provides an information query method, which is applied to an information query system, wherein the information query system includes a knowledge base, and the method includes: in response to a knowledge update request, updating the knowledge base according to the knowledge information carried in the knowledge update request. Based on this, the information in the knowledge base in the above embodiment comes from the received knowledge update request, and the knowledge update request can come from a network device, specifically, it can include a terminal device and a network element device, etc., which is not limited here. The network device stores the relevant knowledge information of its own environment, the knowledge information obtained by itself through interaction with other network devices, etc. in the knowledge base by sending a knowledge update request. Specifically, by obtaining the knowledge information carried in the knowledge update request, the knowledge base is updated, so that the relevant knowledge information of the network device's own environment and the knowledge information obtained through interaction with other network devices can be saved in the knowledge base.

[0029] As one possible implementation, the knowledge information includes updated content, and updating the knowledge base according to the knowledge information carried in the knowledge update request includes updating the knowledge base according to the updated content. Based on this, the knowledge information carried in the knowledge update request may include updated content, specifically including the environment of the network device or knowledge information generated with other network devices. When the knowledge update request includes the updated content, the updated content is saved in the knowledge base, and the knowledge information in the knowledge base is updated.

[0030] As a possible implementation, the knowledge information includes an update time, and updating the knowledge base according to the knowledge information carried in the knowledge update request includes updating the knowledge base according to the update time. Based on this, the knowledge update request may include not only the update content but also the update time. In this case, the update content and the update time may be stored together in the knowledge base, wherein there is a corresponding relationship between the update content and the update time, and the update time is used to indicate when the update content is stored in the knowledge base.

[0031] As a possible implementation, the above-mentioned knowledge information includes an update type, and updating the knowledge base according to the knowledge information carried in the knowledge update request includes: updating the knowledge base according to the update type. Based on this, in addition to including the update content, the knowledge update request may also include the update type. In such a case, the update content and the update type can be stored together in the knowledge base, wherein there is a corresponding relationship between the update content and the update type, and the update type is used to indicate that the update content is of a corresponding type. In some examples, the update content corresponding to different update types is stored in different locations to facilitate subsequent search and classification of the knowledge information.

[0032] As a possible implementation method, the above-mentioned knowledge update request includes a task identifier, the knowledge base includes multiple sub-knowledge bases, and the multiple sub-knowledge bases correspond to different task identifiers. The updating of the knowledge base according to the knowledge information carried in the knowledge update request includes: obtaining a sub-knowledge base that matches the knowledge update request from the multiple sub-knowledge bases according to the task identifier; and updating the sub-knowledge base according to the knowledge information carried in the knowledge update request. Based on this, the knowledge base may include multiple sub-knowledge bases, and the multiple sub-knowledge bases may belong to the same knowledge base and be centrally set up, or they may be distributed in different locations according to task requirements, and the multiple sub-knowledge bases correspond to different task identifiers. The sub-knowledge base corresponding to the task identifier in the knowledge update request can be determined, and the knowledge information carried in the knowledge update request can be stored in the sub-knowledge base. The knowledge information carried in the knowledge update request may include update content, update time, update type, etc., and may also carry other information related to the update request as needed, without any limitation here.

[0033] As one possible implementation, the information query system includes a knowledge question-answering system. It should be noted that the information query system may include a knowledge question-answering system, and the knowledge question-answering system may respond to a knowledge update request and store the knowledge information contained in the knowledge update request in a knowledge base. For details, see the information query system's response to a knowledge update request.

[0034] On the third aspect, the present application provides an information query method, which further includes: in response to a model optimization request, optimizing one or more model parameters in the information query model related to the model optimization request according to the knowledge information carried in the model optimization request. Based on this, for a model optimization request, one or more model parameters in the information query model can be optimized according to the knowledge information in the model optimization request. The information query model can be a knowledge question and answer model. In some examples, when optimizing the information query model according to the knowledge information carried in the model optimization request, the model parameters in the model related to the model optimization request can be optimized, while other parameters remain unchanged, thereby increasing the efficiency of model training and improving the stability of the model.

[0035] As a possible implementation method, the above-mentioned optimization of one or more model parameters related to the model optimization request in the information query model according to the knowledge information carried in the model optimization request includes: matching and obtaining second knowledge information from the knowledge base according to the knowledge information carried in the model optimization request; optimizing one or more model parameters related to the model optimization request in the information query model according to the second knowledge information. Based on this, knowledge information with a high relevance to the knowledge information in the knowledge base can be determined as the second knowledge information according to the knowledge information carried in the model optimization request. Specifically, the standard in the process of determining the second knowledge information can adopt the relevant standard for determining the first knowledge information in the above-mentioned embodiment, or the standard for selecting the second knowledge information can be adjusted according to the specific model training requirements. No limitation is made here.

[0036] As one possible implementation, the information query system includes a knowledge question-answering system. It should be noted that the information query system may include a knowledge question-answering system, which can respond to model optimization requests and optimize the knowledge question-answering model in the question-based system based on the knowledge information contained in the model optimization request. In some examples, the knowledge information contained in the model optimization request can be filtered with the knowledge information in the knowledge base to obtain second knowledge information, and the model parameters can be updated based on the second knowledge information. For details, see the response of the information query system to the model optimization request.

[0037] In a fourth aspect, the present application provides a network device, comprising: a transceiver for sending and receiving signals; a memory for storing computer program instructions; and a processor for executing the computer program instructions to support the network device in implementing a method in any possible implementation of the first, second, and third aspects.

[0038] In a fifth aspect, the present application provides an information query system, comprising one or more network devices, wherein the one or more network devices are used to support the information query system to implement a method in any possible implementation manner of the first aspect, the second aspect, and the third aspect.

[0039] In a sixth aspect, the present application provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processing circuit, implement a method as in any possible implementation of the first aspect, the second aspect, or the third aspect.

[0040] In a seventh aspect, the present application provides a computer program product comprising instructions, which, when run on a computer, enables the computer to execute a method in any possible implementation of the first, second, and third aspects.

[0041] In an eighth aspect, the present application provides a chip system, which includes a processing circuit and a storage medium, wherein the storage medium stores computer program instructions; when the computer program instructions are executed by the processing circuit, the method in any possible implementation manner of the first aspect, the second aspect, and the third aspect is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] FIG1 is a schematic diagram of an information query effect provided by related art;

[0043] FIG2 is a schematic diagram of a model training principle provided by related art;

[0044] FIG3 is a schematic diagram of a network system architecture provided by related technology;

[0045] FIG4 is a schematic diagram of an application system architecture of an information query method provided in an embodiment of the present application;

[0046] FIG5 is a schematic diagram of the hardware structure of a network device provided in an embodiment of the present application;

[0047] FIG6 is a flow chart of an information query method provided in an embodiment of the present application;

[0048] FIG7 is a flow chart of another information query method provided in an embodiment of the present application;

[0049] FIG8 is a flow chart of another information query method provided in an embodiment of the present application;

[0050] FIG9 is a schematic diagram of a query effect of an information query method provided in an embodiment of the present application;

[0051] FIG10 is a schematic diagram of an information writing process of an information query method provided in an embodiment of the present application;

[0052] FIG11 is a flow chart showing parameter optimization of an information query method according to an embodiment of the present application;

[0053] FIG12 is a flow chart showing parameter optimization of another information query method according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships can exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0055] Hereinafter, the terms "first," "second," and so on are used solely to distinguish different descriptive objects and have no limiting effect on the position, order, priority, quantity, or content of the described objects. For example, if the described object is a "field," the ordinal number preceding the "field" in "first field" and "second field" does not define the position or order of the "fields." "First" and "second" do not define whether the modified "fields" are in the same message, nor do they restrict the order of the "first field" and "second field." For another example, if the described object is a "level," the ordinal number preceding the "level" in "first level" and "second level" does not define the priority of the "levels." For another example, the number of described objects is not limited by the ordinal number and can be one or more. For example, in the case of "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the described object is a "device," the "first device" and "second device" can be the same type of device or different types of devices. For another example, if the described object is "information," the "first information" and "second information" can be information of the same content or different contents. In short, the use of prefixes such as ordinal numbers to distinguish the described objects in the embodiments of the present application does not constitute a restriction on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary restrictions should be constituted due to the use of such prefixes.

[0056] Furthermore, in the embodiments of the present application, "connection" may be a direct connection or an indirect connection; in addition, it may refer to an electrical connection or a communication connection; for example, the connection between two electrical components A and B may refer to a direct connection between A and B, or may refer to an indirect connection between A and B through other electrical components or connection media, or may refer to an indirect connection between A and B through other communication devices or communication media, as long as communication between A and B can be achieved.

[0057] Currently, with the continuous development of large-scale network models, one of the visions of 6G communications is "intelligent and inclusive." Typical 6G scenarios include the integration of artificial intelligence and communications. The development of large-scale network models has triggered an era of transformation in the network model, and large-scale network models are expected to become the foundational technology for intelligent and inclusive communication. In the future, it is expected that large-scale network models dedicated to wireless networks will be deployed within the network.

[0058] Due to the large number of parameters and high training costs, large network models are typically pre-trained for external service provision. Because they are pre-trained, large network models lack knowledge of the task execution environment (e.g., network elements, terminals, etc.) when executing tasks. For example, they lack relevant contextual information and historical memory of task execution. Therefore, complex tasks often need to be manually split into multiple executions. This leads to inaccurate results and wastes resources. As a solution, large network models can use an external (vector) knowledge base to comprehensively answer questions based on user questions and the external knowledge base. For a specific effect, see Figure 1, which illustrates a schematic diagram of an information query effect provided by related technologies. As shown in Figure 1, the question "What is NAMO in the 6G network architecture?" is directly input into the large network model without processing the question before querying. The large network model then answers the input question, obtaining and outputting the corresponding answer. The resulting interpretation of the keyword NAMO is poorly correlated with the 6G network architecture scenario in the original question, and therefore the answer based on this keyword interpretation is inaccurate and unsatisfactory.

[0059] In related technologies, the training process of large network models generally follows the process of Pre-Training -> STF (supervised fine-tuning) -> RLHF (reinforcement learning from human feedback). Constructing a memory experience pool during the reinforcement learning process is a typical approach. See Figure 2, which shows a schematic diagram of a model training principle provided by related technologies. As shown in Figure 2, the model training process can include the following aspects:

[0060] Random exploration: The neural network model interacts with the simulator. For example, simulator A sends the current state s to the neural network. The neural network model randomly selects action a through the action selection module and outputs action a to simulator B. Simulator B obtains many sets of environment states and environment feedback, and stores the corresponding state transition probability tuples (state, action, reward, nextstate) in memory.

[0061] Experience replay: The model replays the memory with a probability of (1-ε), updates the parameters of the neural network model based on the historical information stored in the memory, and continues to perform random exploration with a probability of ε. The value of ε is reduced after each training iteration (epoch).

[0062] Model convergence: When ε is very small or no longer changes, the model parameters tend to converge and the neural network model training is completed.

[0063] On the other hand, referring to FIG3 , a schematic diagram of a network system architecture provided by related technologies is shown. As shown in FIG3 , in the sixth generation mobile communication technology, the evolution direction of 6G network elements can be that each network element is an agent. A role can include short-range wireless communication (NF) and communication between NFs, communication between terminal devices, and communication between network devices. When training the network large model through business data, the role itself also needs to use reinforcement learning (reinforcement learning). Learning) algorithm is used for training. During this process, the interaction between the role and the environment, and the interaction between roles, will generate rich knowledge information. For example, the interaction between the role and the environment may include the role obtaining environmental parameters, and the interaction between roles may include the sending and receiving of data packets between roles. The knowledge information may include task execution context, task execution history memory, task execution industry background and other information, which is the knowledge information of the agent. These knowledge information are essential for the model parameter training of the role, but cannot be recorded and stored to assist in the parameter training of the network large model, making the network large model's answers inaccurate. Moreover, according to the current storage of vector databases, they are all stored in the cloud. This cannot guarantee that the network element device agent can be in a privacy-protected state. If a user asks the question "Check the current connection status of the network element", since the network large model cannot retrieve the network element's surrounding environment information, configuration command information, etc., the execution result of the network large model will be very inaccurate.

[0064] Based on this, the present application provides an information query method, which can first obtain knowledge information related to the query request from the knowledge base when there is a query request, and then generate prompt information related to the query request based on the knowledge information to supplement the query request, and finally output the query result corresponding to the query request based on the query request and the prompt information. Based on this, the query request can be supplemented and optimized by task-related knowledge information, thereby improving the accuracy of the query result when performing information query based on the query request. Among them, the knowledge information of the terminal device or network element device is stored in the core network or wireless network, and tasks such as model parameter training experience playback and knowledge question and answer can be completed based on the knowledge base to improve the accuracy of the model answer.

[0065] The following will describe in detail the information query method provided in the embodiments of the present application with reference to the accompanying drawings.

[0066] In some examples, see FIG4 , which shows a schematic diagram of the application system architecture of an information query method provided by an embodiment of the present application. As shown in FIG4 , a task knowledge base (TKF) can be set between the network model and the terminal device or the network element device, hereinafter referred to as the knowledge base. There can be one or more TKFs, and TKF is a logical function of the network data analytics function (NWDAF) that can perform data storage and logical judgment. In some examples, TKF can be used as a tool plug-in for the network model, and the parameters corresponding to TKF can be used as parameter plug-ins for the network model.

[0067] In an embodiment of the present application, TKF can support knowledge information update and knowledge information query operations, for example, in response to a query request, knowledge information matching the query request is obtained in TKF.

[0068] As an example, TKF can open an interface to terminal devices / network element devices, which can realize information interaction with terminal devices / network element devices and can receive request messages sent by terminal devices / network element devices, such as query requests, knowledge update requests, model optimization requests, etc.

[0069] As an example, the TKF and the programmable logic controller PLF cooperate with each other to convert the knowledge information into prompt information based on a preset function according to the request message.

[0070] As an example, the network model application programming interface API cooperates with each other to complete the information interaction task with the terminal device / network element device.

[0071] As an example, the TKF may be deployed on a core network or a radio access network (RAN).

[0072] It should be noted that the embodiments of the present application can be applied to communication systems, which may include, for example, 5G communication systems, 6G communication systems, or future evolved communication systems, or other communication systems, without any limitation. In addition, the embodiments of the present application can also be applied to IT (Information Technology System) systems. For example, it can be applied to network architectures including one or more of the following:

[0073] Terminal equipment: User equipment, or mobile stations, can be vehicle-mounted, portable, or handheld. The physical device and mobile user can be completely independent. All user information can be stored on a smart card (SIM card), which can be used on the mobile station. The terminal can directly interact with the base station over the air interface. The terminal can send and / or receive signals.

[0074] For example, the terminal device can be used to send query requests, receive query results corresponding to the query requests, and can also be used to initiate knowledge update requests and model optimization requests.

[0075] Base Station (xNB): A wireless base station in the network, also a type of network element equipment in the wireless access network, responsible for all functions related to the air interface:

[0076] (1) Wireless link maintenance function: maintains the wireless link with the terminal and is responsible for the protocol conversion between wireless link data and IP data quality monitoring;

[0077] (2) Radio resource management functions, including the establishment and release of radio links, scheduling and allocation of radio resources, etc.

[0078] (3) Some mobility management functions, including configuring terminals for measurement, evaluating the quality of terminal radio links, and making decisions on terminal handovers between cells.

[0079] For example, a base station may include a knowledge base for storing and processing knowledge information, or a network model for information query, or may serve as a relay node in the communication process to assist other devices in information transmission.

[0080] Core network equipment (CN): The functions of core network equipment are mainly to provide user connections, user management, and service carrying, and to provide an interface to the external network as a bearer network.

[0081] For example, the core network equipment may include a knowledge base for storing and processing knowledge information, or a network macro model for performing information query.

[0082] General-purpose computer: can be used as a terminal device in the network to send query requests, receive query results corresponding to the query requests, and can also be used to initiate knowledge update requests and model optimization requests.

[0083] In some examples, see Figure 5, which shows a schematic diagram of the hardware structure of a network node (e.g., a terminal device or network element device in the aforementioned embodiments) provided in an embodiment of the present application. As shown in Figure 5, the network device may include a processor 501, a communication line 502, a memory 503, and at least one communication interface (Figure 5 is merely illustrative, taking the communication interface 504 as an example).

[0084] The processor 501 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.

[0085] Communication link 502 may include a pathway for transmitting information between the aforementioned components.

[0086] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, RAN, WLAN, etc.

[0087] In an embodiment of the present application, the communication line 502 and the communication interface 504 can be used to support the creation / modification / deletion of security protocol tunnels between a network device and other network devices (such as a first network device and a second network device), negotiation of the association relationship between the security protocol tunnel and the business instance (such as adding / deleting / updating keys, etc.), transmission of business data, etc.

[0088] The memory 503 may be a read-only memory (ROM) or other static storage device that can store static information and instructions, a random access memory (RAM) or other dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via a communication line 502. The memory may also be integrated with the processor.

[0089] The memory 503 is used to store computer-executable instructions for executing the solution of the present application. The memory 503 can store instructions for implementing two modular functions: sending instructions, receiving instructions, and processing instructions, and is controlled by the processor 501 for execution. The processor 501 is used to execute the computer-executable instructions stored in the memory 503, thereby implementing the methods provided in the following embodiments of the present application. The memory 503 shown in FIG5 is only a schematic diagram. The memory may also include other functional instructions, which are not limited by the present invention.

[0090] Optionally, the computer-executable instructions in this application may also be referred to as application code, which is not specifically limited in this application.

[0091] In a specific implementation, as an embodiment, the processor 501 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 5 .

[0092] It should be noted that FIG5 is only an example of a network device and does not limit the specific structure of the network device. For example, the network device may also include other functional modules.

[0093] In some examples, see Figure 6, which shows a flow chart of an information query method provided by an embodiment of the present application. This method can be applied to an information query system, which includes a knowledge base that includes knowledge information related to one or more query tasks. As shown in Figure 6, the method may include:

[0094] S601: In response to a query request, obtain first knowledge information matching the query request from the knowledge base.

[0095] It should be noted that when a query request is received, first knowledge information related to the query request is obtained from the knowledge base based on the knowledge information carried in the query request. The first knowledge information is one or more pieces of knowledge information in the knowledge base. The first knowledge information can come from a terminal device or a network element device, or can include other network devices that have information interaction with the information query system. The specific first information can include knowledge information generated by the interaction between the terminal device or network element device and the environment, as well as knowledge information generated by the interaction between various devices. These pieces of knowledge information can be matched with the knowledge information carried in the query request during the information query process to obtain the first knowledge information. The first knowledge information can be used to supplement and improve the query request.

[0096] In some embodiments, obtaining the first knowledge information that matches the query request from the above-mentioned knowledge base may include: obtaining the first knowledge information that matches the query request from the knowledge base according to a first preset condition, wherein the first preset condition is related to one or more of the following: knowledge relevance, time relevance, and type relevance. It should be noted that in the process of querying the first knowledge information, the correlation between the knowledge information carried by the query request and the knowledge information in the knowledge base can be judged through different dimensions, and the knowledge information with a high correlation with the knowledge information carried by the query request can be used as the first knowledge information. In particular, when judging the correlation between the knowledge information carried by the query request and the knowledge information in the knowledge base, the judgment can be made by combining one or more of knowledge relevance, time relevance, and type relevance, or by using other dimensions that can reflect the correlation between the two according to the specific task. No limitation is made here.

[0097] In some embodiments, the query request carries query content, and obtaining first knowledge information matching the query request from the knowledge base according to a first preset condition may include: using as the first knowledge information knowledge information the knowledge information's updated content and the query content's knowledge relevance greater than or equal to a preset threshold. Based on this, the first knowledge information can be determined based on the knowledge relevance between the knowledge information in the query request and the knowledge information in the knowledge base. Specifically, the knowledge information whose knowledge relevance is greater than or equal to a preset threshold can be used as the first knowledge information. Exemplarily, the knowledge relevance may indicate the semantic similarity between the updated content in the knowledge information in the knowledge base and the query content in the knowledge information in the query request.

[0098] In some embodiments, the query request carries a query time, and the obtaining of first knowledge information matching the query request from the knowledge base according to a first preset condition includes: using as the first knowledge information knowledge information the time correlation between the update time of the knowledge information and the query time of which is greater than or equal to a preset threshold. Based on this, the first knowledge information can be determined based on the time correlation between the knowledge information in the query request and the knowledge information in the knowledge base. Specifically, the knowledge information with a time correlation greater than or equal to a preset threshold can be used as the first knowledge information. Exemplarily, the time correlation can indicate the degree of temporal proximity between the update time of the knowledge information in the knowledge base and the query time of the knowledge information in the query request.

[0099] In some embodiments, the query request carries a query type, and the obtaining of the first knowledge information matching the query request from the knowledge base according to the first preset condition includes: taking the knowledge information whose update type and query type correlation is greater than or equal to a preset threshold as the first knowledge information. Based on this, the first knowledge information can be determined based on the knowledge relevance between the knowledge information in the query request and the knowledge information in the knowledge base. Specifically, the knowledge information whose knowledge relevance is greater than or equal to a preset threshold can be taken as the first knowledge information. Exemplarily, the knowledge relevance can indicate the degree of type similarity between the update type in the knowledge information in the knowledge base and the query type in the knowledge information in the query request. For example, the type similarity between the two can be determined by judging the cosine correlation between the update type corresponding to the knowledge information in the knowledge base and the query type corresponding to the query request.

[0100] In some embodiments, the query request includes a task identifier, the knowledge base includes multiple sub-knowledge bases, and the multiple sub-knowledge bases correspond to different task identifiers. The obtaining of the first knowledge information matching the query request from the knowledge base includes: obtaining the sub-knowledge base matching the query request from the multiple sub-knowledge bases according to the task identifier; obtaining the first knowledge information matching the query request from the sub-knowledge base. It should be noted that the knowledge base may include multiple sub-knowledge bases, and the multiple sub-knowledge bases may belong to the same knowledge base and be centrally set up, or they may be distributed in different locations according to task requirements, and the multiple sub-knowledge bases correspond to different task identifiers. The sub-knowledge base corresponding to the task identifier in the query request can be determined, and the first knowledge information can be obtained from the sub-knowledge base corresponding to the task identifier carried in the query request. The relevance of the first knowledge information to the knowledge information carried in the query request meets the first preset condition. Specifically, the standard for obtaining the first knowledge information is the same as the method for obtaining the first knowledge information from the knowledge base in the aforementioned embodiment, and will not be elaborated here.

[0101] Exemplarily, refer to Figure 7, which shows a flow chart of another information query method provided by an embodiment of the present application. As shown in Figure 7, when the information query method is specifically a knowledge question and answer method, the method may include: the terminal device or network element device sends a task request based on task network attached storage (T-NAS), and the TCF obtains a sub-knowledge base that matches the task request from the multiple sub-knowledge bases (equivalent to the knowledge base TKF in the aforementioned embodiment) based on the task identifier carried in the task request; exemplarily, based on the task control function (TCF), the first knowledge information that matches the task request can be obtained from the sub-knowledge base according to the task identifier carried in the task request of T-NAS. In some examples, a task session is also established based on the matching task request and sub-knowledge base, and the corresponding task identifier (task ID) is determined. The knowledge base may include multiple sub-knowledge bases. The multiple sub-knowledge bases can be centrally set up in the same knowledge base, or distributed in different locations according to task requirements, and the multiple sub-knowledge bases correspond to different task identifiers. The sub-knowledge base that matches its task identifier can be determined based on the task identifier in the T-NAS task request, and the first knowledge information can be obtained from the sub-knowledge base corresponding to the task identifier carried in the query request. The standard for obtaining the first knowledge information is the same as that in the previous embodiment and will not be repeated here.

[0102] S602: Generate prompt information related to the query request according to the first knowledge information;

[0103] It should be noted that, based on the first knowledge information obtained in the above steps, prompt information related to the first knowledge information is determined. The prompt information may include one or more prompt information. The prompt information is used to supplement and improve the query content carried by the query request to make the query content carried in the query request clearer.

[0104] In some embodiments, the above-mentioned generation of prompt information related to the query request based on the first knowledge information includes: based on a prompt logic algorithm, generating prompt information related to the query request based on the first knowledge information, and the prompt information is used to supplement the query content carried by the query request. It should be noted that the one or more first knowledge information obtained from the knowledge base is highly relevant to the knowledge information carried by the query request. Exemplarily, the relevant content of the first knowledge information can be converted into prompt information through a prompt logic algorithm, wherein the prompt logic algorithm includes a prompt logic function, and the prompt logic function is used to convert the first knowledge information into simpler prompt information, supplement or limit the query content carried in the query request, so that the query content is clearer and complete, and facilitates the understanding and query of the query content. For a query request, there can be one or more prompt information corresponding to improve the query content from different levels, which is not limited here.

[0105] In some embodiments, the above-mentioned prompt information related to the query request is generated based on the first knowledge information based on the prompt logic algorithm, including: based on the prompt logic algorithm, obtaining multiple candidate prompt information corresponding to the first knowledge information; determining the prompt information from the one or more candidate prompt information, wherein the prompt information is the candidate prompt information among the multiple candidate prompt information whose similarity with the query content is greater than or equal to a preset threshold. Based on this, the first knowledge information can be converted into one or more candidate prompt information according to the logical prompt algorithm. For example, when there is one candidate prompt information, the candidate prompt information can be directly used as the prompt information. When the candidate prompt information includes multiple candidates, it is necessary to screen among the multiple candidate prompt information and determine the candidate prompt information with a high degree of match with the query request as the prompt information. In some examples, the prompt information in the candidate prompt information can be determined by the similarity between the candidate prompt information and the query content in the query request. The prompt information can be one or more, and different screening criteria for the prompt information can be set according to specific needs. No limitation is made here.

[0106] In some examples, the information query system may include a knowledge question and answer system, and TKF assists the network model to improve the accuracy of knowledge question and answer. During this process, TKF needs to interact with the prompt logic function (PLF) to obtain candidate prompt information for knowledge question and answer, where there can be one or more candidate prompt information, and prompt information that can provide a complete answer to the query request can be determined from one or more prompt information.

[0107] In some embodiments, referring to FIG7 , during the prompt information selection process, the PLF can directly select appropriate prompt information from one or more candidate prompt information through a prompt logic function. Specifically, the PLF can compare the candidate prompt information with the content information in the query request, select the candidate prompt information with higher similarity or more overlapping fields as the final prompt information, and send it to the knowledge base for supplementing and prompting the question in the query request. In some examples, the method may include the following S1-S5:

[0108] S1: The terminal device / network element device matches the corresponding TKF through TCF and establishes a task session with the TKF.

[0109] S2: Terminal / network element device "knowledge question and answer" task: The terminal / network element device sends a question or query request to the TKF. The query request can include one or more of the following:

[0110] AgentID (i.e., the device ID in the aforementioned embodiment): the key of the Agent;

[0111] TaskID (i.e., the task identifier in the aforementioned embodiment): the ID of the task;

[0112] TaskType (i.e., the query type in the aforementioned embodiment): knowledge question answering;

[0113] TimeStamp (i.e., query time in the aforementioned embodiment): timestamp of task triggering;

[0114] Content (i.e., the query content in the aforementioned embodiment): specific questions.

[0115] S3: TKF retrieves knowledge related to content from the knowledge base, and the scores of Recency and Relevance need to be considered during retrieval.

[0116] It should be noted that the recency score: the more recent the knowledge information is, the higher the score is. The decay rate of knowledge information over time can be set to a floating point number between [0, 1], such as 0.95. An exemplary recency score can be 0.95^(TimeStamp in the query request - TimeStamp in the update request of the last updated knowledge information in the knowledge base).

[0117] Relevance score: The higher the knowledge relevance, the higher the relevance score. The specific relevance score can be expressed as semantic similarity. In some examples, semantic similarity can be determined by precise search according to TaskType, or by calculating the cosine correlation between TaskType and the TaskType of the knowledge in the database.

[0118] In some examples, the scoring algorithm used in knowledge information retrieval combines the relevance score and the recency score, specifically: semantic similarity + decay rate ** elapsed hours. (Where ** represents square)

[0119] In some examples, semantic similarity is represented by the Relevance field, and temporal relevance is represented by the Recency field.

[0120] During the calculation of the Recency score, the decay rate of knowledge information over time can be set to a floating point number between [0,1];

[0121] Specifically, when the decay rate = 0, it means that the Recency score is matched only based on semantic similarity and is independent of time; it can be used to query objective facts that are independent of time, for example, what are the components of the query particle?

[0122] When the decay rate = 1, it means that the maximization of the Recency score is related to time. For example, what are all the recent news?

[0123] When the decay rate is a floating point number between 0 and 1, it means that the knowledge in the knowledge base will gradually become outdated over time. For example, what is the profit of Company A in the most recent year?

[0124] S4: TKF searches for candidate prompt information corresponding to the knowledge information obtained through knowledge retrieval through PLF, searches for Prompt from the candidate prompt information, and returns the prompt information Prompt to TKF. For example, the Prompt returned by PLF can be:

[0125] Your task is to do reading comprehension and answer questions from the following content.

[0126] Content: *** Question: ***

[0127] S5: TKF sends the "question request (i.e. the query request in the aforementioned embodiment) + Prompt" to the network big model API. After the network big model generates the question and answer result, it returns the question and answer result corresponding to the question request to the terminal device / network element device.

[0128] In some examples, a knowledge information query operation is performed on TKF, and the control signaling of the knowledge information query may include the fields: "TaskID+TaskType+Action", where TaskID and TaskType are both implemented in TCF-related technologies.

[0129] In some embodiments, referring to FIG8 , which shows a flow chart of another information query method provided by an embodiment of the present application, as shown in FIG8 , during the selection of prompt information, the PLF can directly send one or more candidate prompt information to the knowledge base, and the knowledge base can select appropriate prompt information from the one or more candidate prompt information. Specifically, by comparing the candidate prompt information with the content information in the query request, the candidate prompt information with higher similarity or more overlapping fields can be selected as the final prompt information, and sent to the knowledge base for supplementing and prompting the questions in the query request. Exemplarily, the method may include S1-S5, wherein steps S1-S3 are the same as the aforementioned steps S1-S3 and are not described in detail here. S4 may include the following S41-S43:

[0130] S41: TKF queries PLF (Prompt Logic Function) for candidate prompt information;

[0131] S42: After the PLF performs prompt information query, it returns candidate prompt information related to multiple question requests from the TKF;

[0132] S43: TKF performs similarity matching on the received multiple candidate prompt information and the Content field, and selects the most suitable Prompt.

[0133] S5 is as follows:

[0134] S5: TKF sends the "question + prompt" to the network model API. After the network model generates an answer, it returns the answer to the terminal / network element device. In some scenarios, the prompt in this embodiment can also be expressed as prefix information.

[0135] S603: Generate a question and answer result corresponding to the question request according to the question request and prompt information, and output a query result corresponding to the question.

[0136] It should be noted that the network large model can combine the query request and the prompt information related to the query request to obtain the query result corresponding to the query request and output it.

[0137] In some embodiments, the query request sent by the terminal device or the network element device carries the device identification of the network device that initiated the query request, and the query result corresponding to the query request is output according to the query request and the prompt information, including: obtaining the query result corresponding to the query request according to the query request and the prompt information; and outputting the query result to the network device according to the device identification. It should be noted that the query request carries the device identification of the network device that sent the query request, wherein the network device may include a terminal device and a network element device, etc., which are capable of executing the query request, and are not limited here. The query result corresponding to the query request is obtained based on the query content in the knowledge information carried in the query request and the supplement and limitation of the query content by the prompt information, and the query result is returned to the network device that issued the query request according to the device identification carried by the query request.

[0138] In some embodiments, obtaining a query result corresponding to the query request based on the query request and the prompt information includes: obtaining a query result corresponding to the query request based on the query request and the prompt information based on an information query model. In this regard, the information query model includes a knowledge question-and-answer model, which is used to obtain a query result corresponding to the query request based on the input query content and the prompt information. The prompt information is used to supplement and limit the query content in the query request, making the query content easier for the information query model to understand and resulting in more accurate query results.

[0139] Based on this, referring to FIG9 , which shows a schematic diagram of a query effect of an information query method provided by an embodiment of the present application. As shown in FIG9 , for the same question request as FIG1 , "What is NAMO in the 6G network architecture?", the prompt information "Task-centric 6G Network AI Architecture" provided by the knowledge base supplements and prompts the original question request, making the application scenario of NAMO for the network macro model more clear. Therefore, the question and answer results corresponding to the question request based on the accurate usage scenario are very detailed and accurate. Compared with the query effect of the related art shown in FIG1 , its accuracy fully demonstrates the technical effect of the embodiment of the present application.

[0140] In some examples, the network big model may include a wireless operation and maintenance expert knowledge question and answer model, a network element operation log query model, and other network big models used for information query. The method provided in the embodiment of the present application is also applicable to the above-mentioned network big models and is not limited here.

[0141] In some embodiments, the TKF can assist in optimizing the large network model itself. Based on this, the method can further include: responding to a knowledge update request, updating the knowledge base based on the knowledge information contained in the knowledge update request. Specifically, in assisting with the optimization of the large network model, the use case can include: the model corresponding to the network element device / terminal device can be the large network model, and the optimization of the large network model is completed by updating the knowledge base based on the knowledge information contained in the knowledge update request.

[0142] It should be noted that the information in the knowledge base in the above embodiment comes from the received knowledge update request, and the knowledge update request can come from the network device, specifically, it can include terminal devices and network element devices, etc., which are not limited here. The network device stores the relevant knowledge information of its own environment, the knowledge information obtained by itself through interaction with other network devices, etc. in the knowledge base by sending a knowledge update request. For example, the knowledge base can be updated by obtaining the knowledge information carried by the knowledge update request, so that the relevant knowledge information of the network device's own environment and the knowledge information such as interaction with other network devices can be saved in the knowledge base.

[0143] In some embodiments, the above-mentioned knowledge information includes updated content, and updating the knowledge base according to the knowledge information carried in the knowledge update request includes: updating the knowledge base according to the updated content. It should be noted that the knowledge information carried in the knowledge update request may include updated content, and the updated content may include the environment of the network device or knowledge information generated with other network devices. When the above-mentioned updated content is included in the knowledge update request, the updated content is saved to the knowledge base, and the knowledge information in the knowledge base is updated.

[0144] In some embodiments, the above-mentioned knowledge information includes an update time, and the updating of the knowledge base according to the knowledge information carried in the knowledge update request includes: updating the knowledge base according to the update time. It should be noted that in addition to the update content, the knowledge update request may also include the update time. In such a case, the update content and the update time may be stored together in the knowledge base, wherein there is a corresponding relationship between the update content and the update time, and the update time is used to indicate the update time when the update content is stored in the knowledge base. In some examples, the update content corresponding to the knowledge information may be updated multiple times, and the update time is used to indicate the time when the update content corresponding to the knowledge information was last updated.

[0145] In some embodiments, the above-mentioned knowledge information includes an update type, and the updating of the knowledge base according to the knowledge information carried in the knowledge update request includes: updating the knowledge base according to the update type. It should be noted that in addition to the update content, the knowledge update request may also include the update type. In such a case, the update content and the update type may be stored together in the knowledge base, wherein there is a corresponding relationship between the update content and the update type, and the update type is used to indicate the type corresponding to the update content. In some examples, the update content corresponding to different update types is stored in different locations to facilitate subsequent search and classification of the knowledge information.

[0146] In some embodiments, the above-mentioned knowledge update request includes a task identifier, the knowledge base includes multiple sub-knowledge bases, and the multiple sub-knowledge bases correspond to different task identifiers. The updating of the knowledge base according to the knowledge information carried in the knowledge update request includes: obtaining a sub-knowledge base that matches the knowledge update request from the multiple sub-knowledge bases according to the task identifier; and updating the sub-knowledge base according to the knowledge information carried in the knowledge update request. Based on this, the knowledge base may include multiple sub-knowledge bases, and the multiple sub-knowledge bases may belong to the same knowledge base and be centrally set up, or they may be distributed in different locations according to task requirements, and the multiple sub-knowledge bases correspond to different task identifiers. The sub-knowledge base corresponding to the task identifier in the knowledge update request can be determined, and the knowledge information carried in the knowledge update request can be stored in the sub-knowledge base. The knowledge information carried in the knowledge update request may include update content, update time, update type, etc., and may also carry other information related to the update request as needed, without any limitation here.

[0147] Specifically, in some embodiments, refer to Figure 10, which shows a schematic diagram of the information writing process of an information query method provided in an embodiment of the present application. As shown in Figure 10, TKF may include multiple sub-knowledge bases, and the multiple sub-knowledge bases correspond to different task identifiers. Exemplarily, updating the knowledge base according to the knowledge information carried in the knowledge update request may include: the terminal or network element device sends a task request based on T-NAS (that is, the knowledge update request in the aforementioned embodiment), and the task request carries a task identifier. TCF obtains a sub-knowledge base that matches the knowledge update request from the multiple sub-knowledge bases based on the task identifier; in some examples, TKF requests confirmation for the task request and establishes a task session corresponding to the terminal device or network element device.

[0148] It should be noted that the knowledge base may include multiple sub-knowledge bases. The multiple sub-knowledge bases can be centrally set up or distributed in different locations according to task requirements, and the multiple sub-knowledge bases correspond to different task identifiers. The sub-knowledge base corresponding to the task identifier in the knowledge update request can be determined, and the knowledge information carried in the knowledge update request can be stored in the sub-knowledge base. The knowledge information carried in the knowledge update request may include update content, update time, update type, etc., and may also carry other update request-related information as needed, without any limitation here.

[0149] In some embodiments, the above method further includes: in response to a model optimization request, optimizing one or more model parameters in the information query model related to the model optimization request based on the knowledge information carried in the model optimization request. For a model optimization request, one or more model parameters in the information query model can be optimized based on the knowledge information in the model optimization request. In some examples, the information query model can be a knowledge question and answer model. When optimizing the information query model based on the knowledge information carried in the model optimization request, the model parameters in the model related to the model optimization request can be optimized, while other parameters remain unchanged, thereby increasing the efficiency of model training while improving the stability of the model.

[0150] In some embodiments, the above-mentioned optimization of one or more model parameters related to the model optimization request in the information query model according to the knowledge information carried in the model optimization request includes: matching and obtaining second knowledge information from the knowledge base according to the knowledge information carried in the model optimization request; and optimizing one or more model parameters related to the model optimization request in the information query model according to the second knowledge information. It should be noted that, based on the model optimization request, knowledge information with a high relevance to the knowledge information in the knowledge base can be determined as the second knowledge information according to the knowledge information carried in the model optimization request. Specifically, the standard in the process of determining the second knowledge information can adopt the relevant standard for determining the first knowledge information in the above-mentioned embodiment, or the standard for selecting the second knowledge information can be adjusted according to the specific model training requirements. No limitation is made here.

[0151] Specifically, in some embodiments, see Figure 11, which shows a parameter optimization process diagram of an information query method provided by an embodiment of the present application. As shown in Figure 11, after the parameter optimization is triggered, the terminal device or network element device sends a parameter optimization request to TKF, performs knowledge retrieval based on the parameter optimization request to obtain task-related knowledge information, such as the second knowledge information, and sends it to the network large model for model training to optimize model parameters. In some examples, see Figure 12, which shows a parameter optimization process diagram of another information query method provided by an embodiment of the present application. As shown in Figure 12, during the model training process, parameters of a part of the parameters that do not need to be optimized can be frozen, and only parameters of the other part of the external parameters that need to be optimized can be trained to improve the efficiency of model training and ensure that the part of the model that is not related to the task remains stable.

[0152] In some examples, when a knowledge base contains one or more sub-knowledge bases, after receiving a parameter optimization request, the sub-knowledge base that matches the parameter optimization request can be determined through TCF and then optimized. The TCF can match the parameter optimization request with the sub-knowledge base through the task identifier. Please refer to the matching method between the knowledge update request and the sub-knowledge base in the above embodiment, which will not be repeated here.

[0153] In some embodiments, the information query system includes a knowledge question-and-answer system, the query request includes a question request, and the query result includes an answer result corresponding to the question request. It should be noted that the information query system may include a knowledge question-and-answer system, which responds to the question request and determines first knowledge information in a knowledge base based on the knowledge information carried in the question request, and determines prompt information corresponding to the question request based on the first knowledge information. Based on the question request and the prompt information, the system obtains a question-and-answer result corresponding to the question request and outputs it.

[0154] In some embodiments, the present application provides an information query method, which is applied to an information query system, wherein the information query system includes a knowledge base, and the method includes: in response to a knowledge update request, updating the knowledge base according to the knowledge information carried in the knowledge update request. Based on this, the knowledge information in the knowledge base in the above embodiment is derived from the received knowledge update request, and the knowledge update request can come from a network device. In some examples, the network device can include a terminal device and a network element device, etc., which are not limited here. The network device stores the relevant knowledge information of its own environment, the knowledge information obtained by itself through interaction with other network devices, etc. in the knowledge base by sending a knowledge update request. For example, the knowledge base can be updated by obtaining the knowledge information carried in the knowledge update request, so that the relevant knowledge information of the network device's own environment and the knowledge information of interaction with other network devices can be stored in the knowledge base.

[0155] In some embodiments, the above-mentioned knowledge information includes update content, and updating the knowledge base according to the knowledge information carried in the knowledge update request includes: updating the knowledge base according to the update content. The knowledge information carried in the knowledge update request may include update content, and the specific update content includes the environment of the network device or knowledge information generated by interaction with other network devices. When the knowledge update request includes update content, the update content is saved to the knowledge base. In some examples, the knowledge information already in the knowledge base can be updated according to the knowledge update request.

[0156] In some embodiments, the above-mentioned knowledge information includes an update time, and the updating of the knowledge base according to the knowledge information carried in the knowledge update request includes: updating the knowledge base according to the update time. Based on this, in addition to the update content, the knowledge update request may also include the update time. In this case, the update content and the update time can be stored together in the knowledge base, wherein there is a corresponding relationship between the update content and the update time, and the update time is used to indicate the time when the update content is stored in the knowledge base. In some examples, when the existing knowledge information in the knowledge base is updated according to the knowledge update request, the update time corresponding to the knowledge information is synchronously updated.

[0157] In some embodiments, the above-mentioned knowledge information includes an update type, and the updating of the knowledge base according to the knowledge information carried in the knowledge update request includes: updating the knowledge base according to the update type. Based on this, in addition to the update content, the knowledge update request may also include the update type. In such a case, the update content and the update type may be stored together in the knowledge base, wherein there is a corresponding relationship between the update content and the update type, and the update type is used to indicate that the update content is of a corresponding type. In some examples, the update content corresponding to different update types is stored in different locations to facilitate subsequent search and classification of the knowledge information. In some examples, when the existing knowledge information in the knowledge base is updated according to the knowledge update request, the update type corresponding to the knowledge information is synchronously updated.

[0158] In some embodiments, the above-mentioned knowledge update request includes a task identifier, the knowledge base includes multiple sub-knowledge bases, and the multiple sub-knowledge bases correspond to different task identifiers. The updating of the knowledge base according to the knowledge information carried in the knowledge update request includes: obtaining a sub-knowledge base that matches the knowledge update request from the multiple sub-knowledge bases according to the task identifier; and updating the sub-knowledge base according to the knowledge information carried in the knowledge update request. It should be noted that a knowledge base may include multiple sub-knowledge bases, and multiple sub-knowledge bases may belong to the same knowledge base and be centrally set up, or they may be distributed in different locations according to task requirements, and multiple sub-knowledge bases correspond to different task identifiers. The sub-knowledge base corresponding to the task identifier in the knowledge update request can be determined, and the knowledge information carried in the knowledge update request can be stored in the sub-knowledge base. The knowledge information carried in the knowledge update request may include update content, update time, update type, etc., and may also carry other information related to the update request as needed, which is not limited here.

[0159] In some embodiments, the information query system may include a knowledge question answering system. The knowledge question answering system may respond to a knowledge update request and store the knowledge information contained in the knowledge update request in a knowledge base. For details, see the response of the information query system to the knowledge update request.

[0160] In some examples, TKF can be used to update knowledge information in a knowledge base and optimize a large network model, and can include the following steps S1-S7:

[0161] S1: The terminal device / network element device matches the corresponding TKF through the TCF and establishes a task session with the TKF.

[0162] S2: After collecting task-related knowledge information, the terminal device / network element device initiates a knowledge update request to the TKF. The knowledge update request contains one or more of the following:

[0163] AgentID (i.e., the device ID in the aforementioned embodiment): the key of the Agent;

[0164] TaskID (i.e., the task identifier in the aforementioned embodiment): the ID of the task;

[0165] TaskType (i.e., the update type in the aforementioned embodiment): task type;

[0166] TimeStamp (i.e., update time in the aforementioned embodiment): timestamp of knowledge update;

[0167] Content (i.e., the updated content in the aforementioned embodiment): detailed knowledge content.

[0168] S3: TKF writes knowledge information persistently into the vector database.

[0169] In some examples, when updating knowledge information of TKF, the control signaling of the corresponding knowledge update request may include the fields: "AgentID+TaskID+TaskType+TimeStamp+Content", where TaskID and TaskType are both implemented in TCF-related technologies.

[0170] In some examples, the method further includes:

[0171] S4: The terminal device / network element device triggers the "parameter optimization" task.

[0172] S5: The terminal device / network element device can initiate a parameter optimization request to the TKF. The parameter optimization request includes one or more of the following:

[0173] TaskID: the ID of the task;

[0174] TaskType: task type;

[0175] Action: Optimize task parameters.

[0176] S6: TKF retrieves the knowledge information related to the parameter optimization request (i.e., the second knowledge information in the aforementioned embodiment). The retrieval may be based on one or more of the following criteria:

[0177] Recency score: The more recent the knowledge information is, the higher the score is. The decay rate of knowledge information over time can be set to a floating point number between [0, 1], such as 0.95. An exemplary recency score can be 0.95^(TimeStamp in the query request - TimeStamp in the update request of the last updated knowledge information in the knowledge base).

[0178] Relevance score: The higher the knowledge relevance, the higher the relevance score. The specific relevance score can be expressed as semantic similarity. In some examples, semantic similarity can be determined by precise search according to TaskType, or by calculating the cosine correlation between TaskType and the TaskType of the knowledge in the database.

[0179] In some examples, the scoring algorithm used in knowledge information retrieval combines the relevance score and the recency score, specifically: semantic similarity + decay rate ** elapsed hours. (Where ** represents square)

[0180] In some examples, semantic similarity is represented by the Relevance field, and temporal relevance is represented by the Recency field.

[0181] During the calculation of the Recency score, the decay rate of knowledge information over time can be set to a floating point number between [0,1];

[0182] Specifically, when the decay rate = 0, it means that the Recency score is matched only based on semantic similarity and is independent of time; it can be used to query objective facts that are independent of time, for example, what are the components of the query particle?

[0183] When the decay rate = 1, it means that the maximization of the Recency score is related to time. For example, what are all the recent news?

[0184] When the decay rate is a floating point number between 0 and 1, it means that the knowledge in the knowledge base will gradually become outdated over time. For example, what is the profit of Company A in the most recent year?

[0185] In some examples, other criteria for determining the relevance of knowledge information may be used to retrieve knowledge information based on the tasks involved in the parameter optimization request to obtain second knowledge information corresponding to the parameter optimization request, which is not limited here.

[0186] S7: TKF sends the retrieved knowledge information to the network big model API to trigger model training of the network big model.

[0187] In some examples, the TKF sends the retrieved knowledge information to the network big model API to trigger model training of the network big model (ie, S7), which may include the following S71-S72:

[0188] S71: TKF sends the retrieved knowledge information to the API of the plug-in parameter.

[0189] S72: The plug-in parameters call the network big model API for repeated interactions, and continuously optimize the plug-in parameters by "freezing the network big model parameters and only training the plug-in parameters".

[0190] When TKF assists the large network model to improve the accuracy of knowledge question answering, TKF and PLF add new interactive signaling. The interactive signaling can include the following fields: "TaskID+TaskType+Task Category+Task Execution Parameters", where TaskID and TaskType have been implemented in TCF-related technologies.

[0191] In some embodiments, the present application provides an information query method, which further includes: in response to a model optimization request, optimizing one or more model parameters in the information query model related to the model optimization request according to the knowledge information carried in the model optimization request. It should be noted that for a model optimization request, one or more model parameters in the information query model can be optimized according to the knowledge information in the model optimization request. The information query model can be a knowledge question and answer model. In some examples, when optimizing the information query model according to the knowledge information carried in the model optimization request, the model parameters in the model related to the model optimization request can be optimized, while other parameters remain unchanged, thereby increasing the efficiency of model training and improving the stability of the model.

[0192] In some embodiments, the above-mentioned optimization of one or more model parameters related to the model optimization request in the information query model according to the knowledge information carried in the model optimization request includes: matching and obtaining second knowledge information from the knowledge base according to the knowledge information carried in the model optimization request; optimizing one or more model parameters related to the model optimization request in the information query model according to the second knowledge information. In some examples, based on the knowledge information carried in the model optimization request, knowledge information in the knowledge base that is highly relevant to the knowledge information can be determined as the second knowledge information, and the second knowledge information is used to supplement and optimize the knowledge information carried in the model optimization request. Specifically, the standard in the process of determining the second knowledge information can adopt the relevant standard for determining the first knowledge information in the above-mentioned embodiment, or the standard for selecting the second knowledge information can be adjusted according to the specific model training requirements. No limitation is made here.

[0193] In some embodiments, the information query system includes a knowledge question answering system. It should be noted that the information query system may include a knowledge question answering system, which can respond to a model optimization request and optimize the knowledge question answering model in the question system based on the knowledge information contained in the model optimization request. In some examples, the knowledge information contained in the model optimization request can be filtered with the knowledge information in the knowledge base to obtain second knowledge information, and the model parameters can be updated based on the second knowledge information. For details, see the response of the information query system to the model optimization request.

[0194] After the TKF function is provided in the embodiment of the present application, the knowledge information generated during the execution of the network element device / terminal device can be stored in the TKF; the model parameter training corresponding to the network element device / terminal device can be assisted by the knowledge information in the TKF; in the knowledge question and answer scenario, the knowledge information of the TKF can improve the accuracy of the question and answer results.

[0195] It should be understood that the various schemes of the embodiments of the present application can be reasonably combined and used, and the explanations or descriptions of the various terms appearing in the embodiments can be referenced or explained with each other in the various embodiments, without limitation to this.

[0196] It should also be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0197] It is understandable that, in order to implement the functions of any of the above-mentioned embodiments, the controller or resource allocation simulation device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0198] The embodiments of the present application can divide the functional modules of a controller or resource allocation simulation device with controller resource allocation capabilities. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0199] It should also be understood that the various modules in the controller or resource allocation simulation device can be implemented in software and / or hardware, without specific limitation. In other words, the electronic device is presented in the form of functional modules. The "module" here can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, an integrated logic circuit, and / or other devices that can provide the above-mentioned functions.

[0200] In an optional manner, when data transmission is implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is implemented in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disk (DVD)), or a semiconductor medium (e.g., a solid state disk (SSD)).

[0201] The steps of the method or algorithm described in conjunction with the embodiments of the present application can be implemented in hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and storage medium can be located in an ASIC. In addition, the ASIC can be located in a controller or a resource allocation simulation device. Of course, the processor and storage medium can also exist as discrete components.

[0202] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

Claims

1. An information query method, characterized in that, Applied to an information query system, the information query system includes a knowledge base, the knowledge base includes knowledge information related to one or more query tasks, the method includes: In response to a query request, acquiring first knowledge information matching the query request from the knowledge base; generating prompt information related to the query request according to the first knowledge information; Outputting a query result corresponding to the query request according to the query request and the prompt information.

2. The method according to claim 1, characterized in that, The acquiring first knowledge information matching the query request from the knowledge base includes: First knowledge information matching the query request is acquired from the knowledge base according to a first preset condition, where the first preset condition is related to one or more of the following: knowledge relevance, time relevance, and type relevance.

3. The method according to claim 2, wherein The query request carries query content, and acquiring first knowledge information matching the query request from the knowledge base according to a first preset condition includes: The knowledge information whose updated content of the knowledge information and the knowledge correlation of the query content is greater than or equal to a preset threshold is used as the first knowledge information.

4. The method according to claim 2 or 3, characterized in that, The query request carries a query time, and acquiring first knowledge information matching the query request from the knowledge base according to a first preset condition includes: The knowledge information whose update time and query time have a time correlation greater than or equal to a preset threshold is used as the first knowledge information.

5. The method according to any one of claims 2-4, characterized in that, The query request carries a query type, and acquiring first knowledge information matching the query request from the knowledge base according to a first preset condition includes: The knowledge information whose update type and query type relevance is greater than or equal to a preset threshold is used as the first knowledge information.

6. The method according to any one of claims 1-5, characterized in that, The query request includes a task identifier, the knowledge base includes multiple sub-knowledge bases, and the multiple sub-knowledge bases correspond to different task identifiers. The acquiring first knowledge information matching the query request from the knowledge base includes: According to the task identifier, acquiring a sub-knowledge base matching the query request from the multiple sub-knowledge bases; The first knowledge information matching the query request is obtained from the sub-knowledge base.

7. The method according to any one of claims 1-6, characterized in that, The generating prompt information related to the query request according to the first knowledge information includes: Based on a prompt logic algorithm, prompt information related to the query request is generated according to the first knowledge information, and the prompt information is used to supplement the query content carried by the query request.

8. The method according to claim 7, wherein The generating of prompt information related to the query request according to the first knowledge information based on the prompt logic algorithm includes: Based on the prompt logic algorithm, obtaining multiple candidate prompt information corresponding to the first knowledge information; The prompt information is determined from the one or more candidate prompt information, where the prompt information is candidate prompt information whose similarity with the query content is greater than or equal to a preset threshold among the multiple candidate prompt information.

9. The method according to any one of claims 1 to 8, characterized in that, The query request carries a device identifier of the network device that initiates the query request, and outputting a query result corresponding to the query request according to the query request and the prompt information includes: Obtain the query result corresponding to the query request according to the query request and the hint information; Output the query result to the network device according to the device identifier.

10. The method according to claim 9, wherein The obtaining the query result corresponding to the query request according to the query request and the hint information includes: Based on the information query model, obtain the query result corresponding to the query request according to the query request and the hint information.

11. The method according to any one of claims 1-10, characterized in that, The method further includes: In response to a knowledge update request, update the knowledge base according to the knowledge information carried in the knowledge update request.

12. The method according to claim 11, wherein The knowledge information includes update content, and the updating the knowledge base according to the knowledge information carried in the knowledge update request includes: Update the knowledge base according to the update content.

13. The method according to claim 12, characterized in that, The knowledge information includes update time, and the updating the knowledge base according to the knowledge information carried in the knowledge update request includes: Update the knowledge base according to the update time.

14. The method according to claim 12 or 13, characterized in that, The knowledge information includes update type, and the updating the knowledge base according to the knowledge information carried in the knowledge update request includes: Update the knowledge base according to the update type.

15. The method according to any one of claims 11 - 14, characterized in that, The knowledge update request includes a task identifier, and the knowledge base includes multiple sub-knowledge bases corresponding to different task identifiers. The updating the knowledge base according to the knowledge information carried in the knowledge update request includes: According to the task identifier, obtain the sub-knowledge base that matches the knowledge update request from the multiple sub-knowledge bases; Update the sub-knowledge base according to the knowledge information carried in the knowledge update request.

16. The method according to any one of claims 10-15, characterized in that, The method further includes: In response to a model optimization request, optimize one or more model parameters related to the model optimization request in the information query model according to the knowledge information carried in the model optimization request.

17. The method according to claim 16, wherein The knowledge information includes an optimization type, and the optimizing one or more model parameters related to the model optimization request in the information query model according to the knowledge information carried in the model optimization request includes: Match the second knowledge information from the knowledge base according to the knowledge information carried in the model optimization request; Optimize one or more model parameters related to the model optimization request in the information query model according to the second knowledge information.

18. The method according to any one of claims 1 to 17, characterized in that, The information query system includes a knowledge Q&A system, the query request includes a question request, and the query result includes the answer result corresponding to the question request.

19. An information query method, characterized in that, Applied to an information query system, the information query system includes a knowledge base, and the method includes: In response to a knowledge update request, update the knowledge base according to the knowledge information carried in the knowledge update request.

20. The method according to claim 19, wherein The knowledge information includes update content, and the updating the knowledge base according to the knowledge information carried in the knowledge update request includes: Update the knowledge base according to the update content.

21. The method according to claim 20, wherein The knowledge information includes update time, and the updating the knowledge base according to the knowledge information carried in the knowledge update request includes: Update the knowledge base according to the update time.

22. The method according to claim 20 or 21, characterized in that, The knowledge information includes update type, and the updating the knowledge base according to the knowledge information carried in the knowledge update request includes: Update the knowledge base according to the update type.

23. The method according to any one of claims 19-22, characterized in that, The knowledge update request includes a task identifier. The knowledge base includes a plurality of sub-knowledge bases, and the plurality of sub-knowledge bases correspond to different task identifiers. Updating the knowledge base according to the knowledge information carried in the knowledge update request includes: Obtain, according to the task identifier, a sub-knowledge base that matches the knowledge update request from the plurality of sub-knowledge bases; Update the sub-knowledge base according to the knowledge information carried in the knowledge update request.

24. An information query method, characterized in that, Applied to an information query system, the information query system includes a knowledge base, and the method includes: In response to a model optimization request, optimize one or more model parameters related to the model optimization request in the information query model according to the knowledge information carried in the model optimization request.

25. The method according to claim 24, characterized in that, The knowledge information includes an optimization type. Optimizing one or more model parameters related to the model optimization request in the information query model according to the knowledge information carried in the model optimization request includes: Match second knowledge information from the knowledge base according to the knowledge information carried in the model optimization request; Optimize one or more model parameters related to the model optimization request in the information query model according to the second knowledge information.

26. A network device, characterized in that, The network device includes: A transceiver for sending and receiving signals; A memory for storing computer program instructions; A processor for executing the computer program instructions to support the network device in implementing the method according to any one of claims 1-18 or 19-23 or 24-25.

27. An information query system, characterized in that, Includes one or more network devices, and the one or more network devices are used to support the information query system in implementing the method according to any one of claims 1-18 or 19-23 or 24-25.

28. A computer-readable storage medium, characterized in that, Computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processing circuit, the method according to any one of claims 1-18 or 19-23 or 24-25 is implemented.

29. A computer program product comprising instructions, characterized in that, When the computer program product runs on a computer, the computer is caused to execute the method according to any one of claims 1-18 or 19-23 or 24-25.

30. A chip system, characterized in that, The chip system includes a processing circuit and a storage medium, and computer program instructions are stored in the storage medium; when the computer program instructions are executed by the processing circuit, the method according to any one of claims 1-18 or 19-23 or 24-25 is implemented.

Images