Query statement processing method and device, vehicle and storage medium

Abstract

The invention provides a query statement processing method and device, a vehicle and a storage medium, relates to the technical field of vehicles, is used for solving the problem of low query statement processing efficiency in related technologies, and comprises the following steps: obtaining a query statement input by a user, and determining a semantic analysis result and a distribution tag of the query statement; based on the distribution label of the query statement and the distribution mapping relation, determining a distribution rule of the semantic analysis result; wherein the distribution mapping relation is a mapping relation between a distribution label and a distribution rule of the query statement; the distribution rule is at least used for indicating a distributed target information source from a plurality of information sources; based on a distribution rule, sending the semantic analysis result to the target information source; obtaining feedback information of the target information source for an execution result of the semantic analysis result; and based on the feedback information, the distribution mapping relationship is optimized, so that the processing efficiency of the query statement is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a query statement processing method and device, a vehicle and a storage medium. BACKGROUND

[0002] Traditional semantic parsing systems usually rely on rules and predefined templates, which are difficult to handle complex and diverse natural language inputs. With the development of deep learning and big data technology, large model-based semantic parsing systems have gradually emerged. These systems can understand the context and handle complex tasks such as multi-intention expression and fuzzy semantic reasoning, greatly breaking through the limitations of traditional methods.

[0003] In related technologies, a large language model is used to understand and analyze input text in multiple dimensions, more accurately understand the meaning of input text in a specific context, and accurately extract the required parameters of the user, thereby completing the structured analysis of the user's intention, which can greatly improve the understanding ability in part of the traditional voice interaction process. However, the above method needs to parse parameters to determine the distributable intention queue when distributing intentions. The distributable intention in the distributable intention queue can be distributed through the agreed calling method. This method has low distribution efficiency, resulting in an increase in the time consumption of the whole process from input to obtaining the processing result of the query statement.

[0004] Therefore, how to improve the processing efficiency of the query statement is a problem to be solved at present. SUMMARY

[0005] The present application provides a query statement processing method, device, vehicle and storage medium to solve the problem of low processing efficiency of query statements in related technologies.

[0006] To achieve the above purpose, the technical scheme adopted by the present application is as follows: In a first aspect, a query statement processing method is provided, comprising: obtaining a query statement input by a user, determining a semantic parsing result of the query statement and a distribution label; determining a distribution rule of the semantic parsing result based on the distribution label of the query statement and a distribution mapping relationship; wherein the distribution mapping relationship is a mapping relationship between the distribution label of the query statement and the distribution rule; the distribution rule is used at least to indicate a target source of distribution from a plurality of sources; based on the distribution rule, the semantic parsing result is sent to the target source; obtaining feedback information of an execution result of the semantic parsing result by the target source; based on the feedback information, optimizing the distribution mapping relationship.

[0007] The beneficial effects of the present application are: by determining the distribution label of the query statement, determining the distribution rule of the semantic analysis result through the mapping of the distribution label and the distribution rule, and realizing the distribution of the semantic analysis result to the target source, this distribution process does not need to judge which source needs to be called, avoids distributing the semantic analysis result to irrelevant sources, thereby shortening the time from input to distribution of the query statement, when the source capacity, user demand and the like change, the distribution mapping relationship is adjusted through feedback information, thereby improving the accuracy of the target source, and further improving the processing efficiency of the query statement by shortening the time from input to distribution of the query statement and improving the accuracy of the target source.

[0008] Further, the above determining the semantic analysis result of the query statement comprises: determining the characteristics of the query statement; searching whether there is a target semantic analysis rule matched with the characteristics of the query statement from a plurality of semantic analysis rules; in the case of searching the target semantic analysis rule, determining the semantic analysis result of the query statement based on the target semantic analysis rule.

[0009] According to the above technical means, by matching the target semantic analysis rule according to the characteristics of the query statement, the matched analysis rule can be quickly determined, invalid calculation is reduced, and the semantic analysis efficiency of the query statement is improved.

[0010] Further, the above determining the semantic analysis result of the query statement further comprises: in the case of not searching the target semantic analysis rule, detecting whether the query statement is complete; in the case of the complete query statement, distributing the query statement to a corresponding vertical field small model for semantic analysis processing according to the field to which the query statement belongs, to obtain the semantic analysis result; in the case of the incomplete query statement, performing semantic analysis processing on the query statement by a large model to obtain the semantic analysis result.

[0011] According to the above technical means, in the case of not searching the target semantic analysis rule, by judging whether the query statement is complete, the corresponding query statement is processed by the appropriate model, the complete query statement is processed by the vertical field small model, the analysis efficiency of the semantic analysis result and the accuracy of the semantic analysis result in the specific field can be improved, and the incomplete query statement is processed by the large model, and the reasonable semantic analysis result is obtained by means of the context understanding and fuzzy semantic reasoning capability of the large model.

[0012] Further, the above detecting whether the query statement is complete in the case of not searching the target semantic analysis rule comprises: in the case of not searching the target semantic analysis rule, detecting whether the query statement is valid; in the case of invalid query statement, adding a recognition label to the query statement, the recognition label is used to represent that the query statement is not subjected to semantic analysis; in the case of valid query statement, detecting whether the query statement is complete.

[0013] According to the above technical means, the query statement can be semantically parsed on the premise that the query statement is valid. By detecting whether the query statement is valid, invalid query statements can be filtered out in advance, avoiding the waste of parsing resources caused by invalid query statements entering the subsequent semantic parsing process.

[0014] Further, the query statement is distributed to the corresponding vertical field small model for semantic parsing processing according to the field to which the query statement belongs, and the semantic parsing result is obtained, including: in the case that the field to which the query statement belongs is multiple, the query statement is distributed to multiple vertical field small models for semantic parsing processing, and the output results of the multiple vertical field small models are obtained; the output results of the multiple vertical field small models are fused to obtain the semantic parsing result.

[0015] According to the above technical means, the focus of different vertical field small models is different, and correspondingly, the processing results generated are also different. By fusing the output results of the multiple vertical field small models, a consistent semantic parsing result is obtained, thereby improving the accuracy of the semantic parsing result.

[0016] Further, the semantic parsing result is obtained by performing the following operations on the query statement by the large model: performing semantic decomposition on the query statement to obtain multiple sub-statements of the query statement; performing semantic association on the multiple sub-statements to obtain a semantic association result; and performing semantic reconstruction on the semantic association result to obtain the semantic parsing result.

[0017] According to the above technical means, complex query statements can be decomposed into simple sub-statements through semantic decomposition, reducing the difficulty of semantic parsing. The sub-statements are associated and reconstructed, and the sub-statements are integrated into complete language expressions, which not only reflect the real logic of the query statement, but also provide structured input for subsequent processing of the query statement, thereby improving the accuracy of the processing result of the query statement.

[0018] Further, the method further includes: obtaining a confidence degree of the semantic parsing result; and the optimization of the distribution mapping relationship based on the feedback information includes: jointly optimizing the distribution mapping relationship and model parameters of a model used to generate the semantic parsing result based on the feedback information and the confidence degree.

[0019] According to the above technical means, by jointly optimizing the distribution mapping relationship and the model parameters of the model used to generate the semantic parsing result, the problems of inaccurate model parsing and unmatched distribution are solved, thereby adjusting and maintaining the dynamic balance between accurate semantic understanding and accurate source distribution through the cooperative optimization of parsing and distribution, and further improving the processing efficiency and quality of the query statement.

[0020] Further, the determining the distribution label of the query statement comprises: determining the distribution label of the query statement based on the semantic analysis result of the query statement.

[0021] According to the technical means, the distribution label is generated based on the semantic analysis result, so that the label is highly matched with the query intention, and the accuracy of the target information source is ensured.

[0022] In a second aspect, a processing apparatus for a query statement is provided, comprising: a determining unit configured to obtain a query statement input by a user, determine a semantic analysis result and a distribution label of the query statement; a processing unit configured to determine a distribution rule of the semantic analysis result based on the distribution label of the query statement and a distribution mapping relationship; wherein the distribution mapping relationship is a mapping relationship between the distribution label of the query statement and the distribution rule; the distribution rule is used at least for indicating a target information source for distribution from a plurality of information sources; the semantic analysis result is sent to the target information source based on the distribution rule; feedback information of an execution result of the semantic analysis result by the target information source is obtained; and the distribution mapping relationship is optimized based on the feedback information.

[0023] In a third aspect, an electronic device is provided, comprising: a processor and a memory; the memory is configured to store processor-executable instructions; and the processor is configured to execute the instructions to implement the method of the first aspect and any possible implementation thereof.

[0024] In a fourth aspect, a vehicle is provided, comprising: the electronic device of the third aspect.

[0025] In a fifth aspect, a computer-readable storage medium is provided, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method of the first aspect and any possible implementation thereof.

[0026] In a sixth aspect, a computer program product is provided, the computer program product comprises computer instructions, when the computer instructions are run on an electronic device, the electronic device performs the method of the first aspect and any possible implementation thereof.

[0027] The beneficial effects of the present application are as follows: (1) By determining the distribution label of the query statement, the distribution rule of the semantic analysis result is determined through the mapping of the distribution label and the distribution rule, the semantic analysis result is distributed to the target information source, the distribution process does not need to determine which information source needs to be called, the semantic analysis result is avoided to be distributed to irrelevant information sources, so that the time from input to distribution of the query statement is shortened, when the information source capacity, user demand and the like change, the distribution mapping relationship is adjusted through the feedback information, so that the accuracy of the target information source is improved, and the processing efficiency of the query statement is improved by shortening the time from input to distribution of the query statement and improving the accuracy of the target information source.

[0028] (2) By matching the target semantic analysis rule according to the characteristics of the query statement, the matched analysis rule can be quickly determined, invalid calculation is reduced, and the semantic analysis efficiency of the query statement is improved.

[0029] (3) In the case where the target semantic analysis rule is not retrieved, by judging whether the query statement is complete, the corresponding query statement is processed by a suitable model, the complete query statement is processed by a small model in a vertical field, the analysis efficiency of the semantic analysis result and the accuracy of the semantic analysis result in a specific field are improved, and the incomplete query statement is processed by a large model, with the help of the context understanding and fuzzy semantic reasoning ability of the large model, a reasonable semantic analysis result is obtained.

[0030] (4) The premise for the query statement to be semantically analyzed is that the query statement is valid, by detecting whether the query statement is valid, invalid query statements can be filtered out in advance, and the waste of analysis resources caused by invalid query statements entering the subsequent semantic analysis process is avoided.

[0031] (5) Different small models in different vertical fields have different focuses, and the generated processing results are also different, by fusing the output results of multiple small models in different vertical fields, a consistent semantic analysis result is obtained, and the accuracy of the semantic analysis result is improved.

[0032] (6) By semantic decomposition, a complex query statement can be decomposed into simple sub-statements, the difficulty of semantic analysis is reduced, the sub-statements are associated and reconstructed, and the sub-statements are integrated into a complete language expression, which not only reflects the real logic of the query statement, but also provides a structured input for the subsequent processing of the query statement, thereby improving the accuracy of the processing result of the query statement.

[0033] (7) By jointly optimizing the model parameters of the model for distributing the mapping relationship and generating the semantic analysis result, the problems of inaccurate model analysis and unmatched distribution are solved, thereby adjusting and maintaining the dynamic balance between semantic understanding accuracy and source distribution accuracy through the cooperative optimization of analysis and distribution, and the processing efficiency and quality of the query statement are improved.

[0034] (8) By generating a distribution tag based on the semantic analysis result, it can be ensured that the tag is highly matched with the query intent, thereby ensuring the accuracy of the target source. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 A flowchart of a query statement processing method provided by an embodiment of the application (I); Figure 2 A flowchart of a query statement processing method provided by an embodiment of the application (II); Figure 3 A flowchart of a query statement processing method provided by an embodiment of the present application (three); Figure 4 An architectural diagram of a query statement processing method provided by an embodiment of the present application; Figure 5 A flowchart of a query statement processing method provided by an embodiment of the present application (four); Figure 6 A flowchart of a method for determining whether a query statement is complete; Figure 7 A structural diagram of a query statement processing device provided by an embodiment of the present application; Figure 8 A structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0036] Other advantages and effects of the present application can be easily understood by those skilled in the art from the disclosure of the present specification. The present application can also be implemented or applied in other different specific embodiments, and various modifications or changes can be made to the details in the present specification based on different views and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, but not for limiting the protection scope of the present application.

[0037] It should be noted that the diagrams provided in the following embodiments only schematically illustrate the basic concept of the present application, and only the components related to the present application are shown in the diagrams, but not the number, shape and size of the components when actually implemented. The actual implementation of each component may be randomly changed in shape, number and proportion, and the layout pattern of the components may also be more complex.

[0038] Traditional semantic parsing systems usually rely on rules and predefined templates, which are difficult to handle complex and diverse natural language inputs. With the development of deep learning and big data technology, large model-based semantic parsing systems have gradually emerged. These systems can handle complex tasks such as multi-intention expression and fuzzy semantic reasoning by leveraging contextual understanding capabilities, greatly breaking through the limitations of traditional methods.

[0039] In the related art, by guiding a large language model to perform multi-dimensional understanding analysis on input text, the meaning of the input text in a specific context is more accurately understood, and the parameters required by the user are accurately extracted, so as to complete the structured analysis of the user's intention, thereby greatly improving the understanding ability in the process of part of the traditional voice interaction. However, when the above method is used for intention distribution, it is necessary to analyze parameters to determine a distributable intention queue. The distributable intention in the distributable intention queue can be distributed through an agreed calling mode. This mode has low distribution efficiency, which increases the time consumption of the whole process from input to obtaining the processing result of the query statement.

[0040] Therefore, how to improve the processing efficiency of the query statement is a problem to be solved at present.

[0041] Therefore, how to improve the processing efficiency of the query statement is a problem to be solved at present.

[0041] Based on this, the present application provides a query statement processing method, device, vehicle and storage medium, comprising: obtaining a query statement input by a user, determining a semantic analysis result of the query statement and a distribution label; determining a distribution rule of the semantic analysis result based on the distribution label of the query statement and a distribution mapping relationship; wherein the distribution mapping relationship is a mapping relationship between the distribution label of the query statement and the distribution rule; the distribution rule is used at least for indicating a target source of distribution from a plurality of sources; and sending the semantic analysis result to the target source based on the distribution rule. By determining the distribution label of the query statement, the distribution rule of the semantic analysis result is determined through the mapping of the distribution label and the distribution rule, the semantic analysis result is distributed to the target source, this distribution process does not need to judge which source needs to be called, avoids distributing the semantic analysis result to irrelevant sources, thereby shortening the time from input to distribution of the query statement, when the source capability, user demand and the like change, the distribution mapping relationship is adjusted through feedback information, thereby improving the accuracy of the target source, and further improving the processing efficiency of the query statement by shortening the time from input to distribution of the query statement and improving the accuracy of the target source.

[0042] In some embodiments, the execution subject of the query statement processing method provided by the embodiments of the present application can be a query statement processing device. The query statement processing device can be deployed in an electronic device. The electronic device can be a server cluster composed of multiple servers, or a single server, or a computer, or a processor or processing chip in a server or computer, or any device or equipment that has a query statement processing function, which is not limited by the embodiments of the present application.

[0043] In some embodiments, the query statement processing device or electronic device provided by the embodiments of the present application can be applied to a vehicle. The vehicle can be a fuel vehicle, a pure electric vehicle or a hybrid vehicle, which is not limited herein.

[0044] Exemplarily, during vehicle driving, the user input query statement can be semantically ambiguous, and the query statement processing method provided by the embodiment of the present application can enable the vehicle to obtain a semantic analysis result by accurately analyzing the query statement, thereby enhancing the understanding of the user driving intention by the vehicle and improving the driving experience of the user.

[0045] In addition, as the number of vehicle function modules increases, accurate matching of the target source can reduce false triggering of functions and improve the reliability of vehicle function responses.

[0046] As shown in Figure 1 The query statement processing method of the present application comprises the following steps: S101, acquiring a query statement input by a user, determining a semantic analysis result of the query statement and a distribution label.

[0047] The query statement represents a request proposed by the user, for example, the query statement can be "please generate a navigation route from location A to location B". The query statement can be input in the form of text, image into the search box of an application or system, or can be input in the form of voice into an interactive interface with voice recognition function.

[0048] The semantic analysis result represents processing of the query statement, thereby representing the true meaning of the query statement as structured machine language. For example, the query statement is "please generate a navigation route from location A to location B", and the corresponding semantic analysis result is "starting point A", "ending point B" and structured data with the intention of "generating a navigation route".

[0049] As a possible implementation, the determination of the semantic analysis result of the query statement can be implemented as follows: determining the characteristics of the query statement; searching whether there is a target semantic analysis rule matching the characteristics of the query statement from a plurality of semantic analysis rules; in the case of searching for the target semantic analysis rule, determining the semantic analysis result of the query statement based on the target semantic analysis rule. By matching the target semantic analysis rule according to the characteristics of the query statement, the matching analysis rule can be quickly determined, invalid calculation is reduced, and the semantic analysis efficiency of the query statement is improved.

[0050] The characteristics of the query statement are the basis for searching the target semantic analysis rule, which can be the user intention, keywords, entity information, etc. reflected by the query statement. For example, the query statement is "what is the weather in location A tomorrow", and the corresponding characteristics can include intention, location and time.

[0051] In a possible implementation, a rule matching function is determined, the rule matching function traverses all semantic analysis rules, and checks one by one whether there is a target semantic analysis rule. If there is, the semantic analysis result determined by the target semantic analysis rule is returned.

[0052] As another possible implementation method, the above-mentioned determination of the semantic parsing result of the query statement can also be implemented as follows: by establishing a deep learning model, the query statement is input into the deep learning model to obtain the semantic parsing result of the query statement. Since the deep learning model can directly map the query statement into the semantic parsing result, it is highly efficient.

[0053] Distribution tags represent the classification results of semantic parsing and are used to match distribution rules. Distribution tags can be determined based on the query intent. For example, if the semantic parsing result is to generate a navigation route, it can be labeled as a route planning tag. They can also be determined based on the domain of the query. For example, if the semantic parsing result is in the fields of finance, healthcare, etc., it can be labeled as a finance, healthcare, etc. distribution tag.

[0054] A query can have one or more distribution tags, depending on the query's complexity. If the query is relatively simple, meaning its intent is clear, a single distribution tag may be sufficient. However, if the query contains multiple intents and covers multiple domains, multiple distribution tags may be needed to describe it.

[0055] As a possible implementation method, the above-mentioned determination of the distribution label of the query statement can be implemented as follows: determining the distribution label of the query statement based on the semantic parsing result of the query statement, and generating the distribution label through the semantic parsing result can ensure that the label is highly matched with the query intent, thereby ensuring the accuracy of the target source.

[0056] In a possible implementation, determining the distribution label of the query statement based on the semantic parsing result of the query statement can be implemented by directly generating the distribution label of the query statement through rule matching based on key features of the semantic parsing result.

[0057] Among them, the key feature can be the query intent, and the key feature can also be the attribute of the query object, such as the query object itself and the restriction condition.

[0058] In one possible implementation, the above-mentioned determination of the distribution label of the query statement based on the semantic parsing result of the query statement can be implemented by training a classification model (such as a decision tree, a neural network) based on historical semantic parsing results and corresponding distribution labels, inputting the current semantic parsing result into the trained classification model, and automatically generating the corresponding distribution label.

[0059] S102: Determine a distribution rule for the semantic parsing result based on the distribution label and distribution mapping relationship of the query statement.

[0060] The distribution mapping relationship is a mapping relationship between a distribution label of a query statement and a distribution rule, and the distribution rule is used to indicate a target source for distribution from a plurality of sources. The source refers to an information source that can be invoked when processing the query statement, for example, different databases, external API interfaces, search engines, user interfaces, and the like.

[0061] As a possible implementation, when the distribution label is one, the distribution mapping relationship is traversed based on the distribution label of the query statement to obtain the distribution rule of the semantic analysis result.

[0062] As another possible implementation, when the distribution label is a plurality, the distribution labels have a priority order, and the distribution mapping relationship can be traversed according to the priority order of the distribution labels to obtain the distribution rule of the semantic analysis result.

[0063] When the distribution label is a plurality, the distribution labels have a dependency relationship, and the distribution mapping relationship can be traversed according to the dependency relationship of the distribution labels to obtain the distribution rule of the semantic analysis result.

[0064] It should be noted that in addition to being used to determine the target source, the distribution rule can also be used to determine the priority of the target source when the target source is a plurality, that is, the distribution order of the target source, and can also define a re-distribution rule when the semantic analysis result distribution fails.

[0065] S103, based on the distribution rule, sending the semantic analysis result to the target source.

[0066] As a possible implementation, after the target source receives the semantic analysis result, the target source processes according to the content of the semantic analysis result and returns a processing result. Illustratively, the semantic analysis result is: "time: tomorrow, place A, intent: check the weather", the target source can be a weather query website, the target source processes according to the received analysis result (such as querying a database, calculating a result), and finally returns a result "tomorrow place A will have light rain.

[0067] S104, obtaining feedback information of an execution result of the target source for the semantic analysis result.

[0068] The feedback information can reflect the performance of the target source processing the semantic analysis result, and generally includes two types of data. One is objective data, for example, which can include: execution success rate, execution time, completeness of execution result. The other is subjective data, for example, user satisfaction.

[0069] S105, based on the feedback information, optimizing the distribution mapping relationship.

[0070] As a possible implementation, based on the feedback information, the priority of the target source in the distribution rule determined by the optimization of the distribution mapping relationship can be implemented as follows: based on the feedback information, the priority of the target source in the distribution rule determined by the optimization of the distribution mapping relationship.

[0071] In a possible implementation, the priority of the target source can be represented by the weight of the target source. Specifically, the priority of the target source in the distribution rule determined by the optimization of the distribution mapping relationship based on the feedback information can be implemented as follows: determining an initial weight of the target source, and correcting the initial weight of the target source based on the execution success rate and the satisfaction degree to obtain a target weight of the target source, and then adjusting the distribution rule according to the target weight of the target source, so as to adjust the distribution mapping relationship.

[0072] In a possible implementation, the target weight of the target source obtained by correcting the initial weight of the target source based on the execution success rate and the satisfaction degree can be implemented as follows: multiplying the initial weight, the execution success rate and the satisfaction degree to obtain the target weight.

[0073] For example, when querying a route between a place A and a place B, the priority (weight) of the first map application in the current distribution rule is higher than that of the second map application. If the user is not satisfied with the route generated by the first map application, or the execution success rate of the first map application is low, the priority (weight) of the first map application can be reduced.

[0074] In a possible implementation, after calculating the target weight of the target source, whether to adjust the priority of the target source again can be determined by a weight adjustment model. Specifically, the priority of the target source in the distribution rule determined by the optimization of the distribution mapping relationship based on the feedback information can be implemented as follows: determining a weight adjustment model, inputting the execution success rate and the satisfaction degree of the target source into the weight adjustment model, if the result obtained is that the priority of the target source does not need to be updated, the distribution mapping relationship is not adjusted. If the result obtained is that the priority of the target source needs to be updated, the adjustment is performed based on the target weight.

[0075] Therefore, by determining the distribution tag of the query statement, determining the distribution rule of the semantic analysis result through the mapping of the distribution tag and the distribution rule, and implementing the distribution of the semantic analysis result to the target source, this distribution process does not need to determine which source needs to be called, avoids distributing the semantic analysis result to irrelevant sources, and thus shortens the time from inputting the query statement to distributing. When the source capability, user demand and the like change, the distribution mapping relationship is adjusted through the feedback information, so as to improve the accuracy of the target source, and further improve the processing efficiency of the query statement by shortening the time from inputting the query statement to distributing and improving the accuracy of the target source.

[0076] In some embodiments, for a query statement without a matching target semantic parsing rule, the parsing of this type of query statement can be implemented by a vertical domain small model or a large model, as shown in Figure 2 As shown in S101, the following steps are included: S201, in the case where the target semantic parsing rule is not retrieved, detecting whether the query statement is complete.

[0077] As a possible implementation, in the case where the target semantic parsing rule is not retrieved, detecting whether the query statement is valid; in the case where the query statement is invalid, adding a rejection label to the query statement, the rejection label being used to represent that the query statement is not subjected to semantic parsing; in the case where the query statement is valid, detecting whether the query statement is complete.

[0078] It should be understood that the premise for a query statement to be subjected to semantic parsing is that the query statement is valid, by detecting whether the query statement is valid, invalid query statements can be filtered in advance, so as to avoid the invalid query statements from entering the subsequent semantic parsing process, thereby avoiding the waste of parsing resources.

[0079] S202, in the case where the query statement is complete, distributing the query statement to a corresponding vertical domain small model according to the domain to which the query statement belongs, for semantic parsing processing, to obtain a semantic parsing result.

[0080] The vertical domain small model has a more accurate understanding of the professional terms, sentence structures, and semantic logic in the domain to which it belongs. Compared with a general model, it can more accurately extract the domain-specific nouns and terms, reduce parsing bias, and thus improve the accuracy of the semantic parsing result. In addition, the parameter size of the vertical domain small model is small, for the same query statement, the inference speed is fast, the required computing resources are less, and the processing link is shorter, thereby improving the parsing speed of the semantic parsing result.

[0081] As a possible implementation, the domain to which the query statement belongs can be determined according to a machine learning model, for example, the machine learning model can be a text classification model. The vertical domain small model corresponding to the domain to which the query statement belongs can be determined based on a decision tree or a rule system.

[0082] As a possible implementation, in the case where the domain to which the query statement belongs is multiple, the query statement is distributed to multiple vertical domain small models for semantic parsing processing, to obtain the output results of the multiple vertical domain small models; the output results of the multiple vertical domain small models are fused, to obtain a semantic parsing result.

[0083] In a possible implementation, the fusing of the output results of the plurality of vertical field small models to obtain the semantic parsing result can be implemented as follows: the output results of the plurality of vertical field small models are checked to determine whether the output results of the plurality of vertical field small models are consistent, in the case where the output results of the plurality of vertical field small models are consistent, the output results of the plurality of vertical field small models are determined as the output result of any vertical field small model, and in the case where the output results of the plurality of vertical field small models are inconsistent, the output results of the plurality of vertical field small models are weighted and summed to obtain the semantic parsing result.

[0084] The weight of each output result of each vertical field small model can be determined according to the weight of each vertical field small model.

[0085] For example, the domain to which the query statement belongs is medical and financial, the query statement is sent to the vertical field small models corresponding to medical and financial respectively, 2 output results are obtained, if the 2 output results are inconsistent, the 2 output results are fused by weighting according to the weights of the vertical field small models, and the semantic parsing result corresponding to the query statement is obtained.

[0086] It should be understood that different vertical field small models have different focuses, and correspondingly, the generated processing results are also different. By fusing the output results of the plurality of vertical field small models, a consistent semantic parsing result is obtained, thereby improving the accuracy of the semantic parsing result.

[0087] S203, in the case where the query statement is incomplete, the query statement is processed by the large model for semantic parsing to obtain a semantic parsing result.

[0088] In the case where the query statement is incomplete, the large model can reasonably complete the missing content based on common sense, context association or user historical interaction information, thanks to its powerful context understanding and fuzzy semantic reasoning capability, thereby avoiding parsing failure caused by missing information and ensuring that an incomplete query can also obtain a reasonable semantic parsing result.

[0089] It should be noted that the large model is a model obtained by fusing a multi-modal / multi-field large model, and the multi-modal / multi-field is fused to solve the bottleneck of the traditional large model in long context reasoning and implicit semantic parsing, thereby improving the depth understanding capability of the semantic.

[0090] As a possible implementation, the following operations are performed by the large model to obtain the semantic parsing result: the query statement is semantically decomposed to obtain a plurality of sub-statements of the query statement; the plurality of sub-statements are semantically associated to obtain a semantic association result; and the semantic association result is semantically reconstructed to obtain the semantic parsing result.

[0091] In a possible implementation, the semantic decomposition of the query statement to obtain the plurality of sub-statements of the query statement can be implemented as follows: based on the intention reflected by the query statement, the query statement is semantically decomposed to obtain the plurality of sub-statements of the query statement. For example, the query statement is "please generate a route from location A to location B, and determine whether the weather tomorrow is suitable for travel", which can be split into two sub-statements "generate a route from location A to location B", and "whether the weather tomorrow is suitable for travel".

[0092] In a possible implementation, the semantic association of the plurality of sub-statements to obtain the semantic association result can be implemented as follows: in combination with an external knowledge base or context information, the semantic association result between the sub-statements is determined.

[0093] It should be understood that the complex query statement can be decomposed into simple sub-statements through semantic decomposition, which reduces the difficulty of semantic analysis, and the sub-statements are associated and reconstructed, and the sub-statements are integrated into a complete language expression, which not only reflects the real logic of the query statement, but also provides a structured input for subsequent processing of the query statement, thereby improving the accuracy of the processing result of the query statement.

[0094] Therefore, in the case where the target semantic parsing rule is not retrieved, by judging whether the query statement is complete, the corresponding query statement is processed by a suitable model, the complete query statement is processed by a vertical domain small model, the parsing efficiency of the semantic parsing result and the accuracy of the semantic parsing result in a specific domain can be improved, and the incomplete query statement is processed by a large model, and a reasonable semantic parsing result is obtained by means of the context understanding and fuzzy semantic reasoning capability of the large model.

[0095] In some embodiments, when the target source processes the query statement, there can be a low accuracy of the semantic parsing result itself, even if the target source is highly matched, the execution result of the target source for the semantic parsing result still does not meet the user's demand, and in Figure 1 the basis, as shown in Figure 3 the method further includes: S301, obtaining the confidence of the semantic parsing result.

[0096] The S105 includes: S302, based on the feedback information and the confidence, jointly optimizing the distribution mapping relationship and the model parameters of the model used to generate the semantic parsing result.

[0097] As a possible implementation, based on the feedback information and the confidence of the semantic parsing result, the semantic parsing result is classified, so that according to the type of the semantic parsing result, the distribution mapping relationship and the model parameters of the model used to generate the semantic parsing result are jointly optimized.

[0098] In a possible implementation, for a semantic analysis result with high confidence, low execution success rate and low satisfaction, only the distribution mapping relationship can be optimized. The process of optimizing the distribution mapping relationship can refer to the description in the above embodiments, which will not be described here.

[0099] In a possible implementation, for a high-confidence semantic analysis result corresponding to the same distribution label, if there are both low execution success rate and low satisfaction and high execution success rate and high satisfaction, the distribution mapping relationship can be refined, that is, the distribution mapping relationship corresponding to the high execution success rate and high satisfaction is retained, and the distribution mapping relationship corresponding to the low execution success rate and low satisfaction is adjusted.

[0100] In a possible implementation, for a semantic analysis result with low confidence, low execution success rate and low satisfaction, the query statement can be re-labeled, and the model parameter of the model for generating the semantic analysis result is adjusted. For a semantic analysis result with high confidence, low execution success rate and low satisfaction, the matching degree of the semantic analysis result and the target source is analyzed, and if the matching degree is low, the semantic analysis result of the target source requirement is included in the model training, so that the semantic analysis result is more suitable for the target source.

[0101] Therefore, by jointly optimizing the distribution mapping relationship and the model parameter of the model for generating the semantic analysis result, both the problem of inaccurate model analysis and the problem of mismatched distribution are solved, so that the dynamic balance between accurate semantic understanding and accurate source distribution is adjusted and maintained through the cooperative optimization of analysis and distribution, and the processing efficiency and quality of the query statement are improved.

[0102] In some embodiments, as shown in Figure 4 The processing architecture of the query statement of the present application includes a pre-processing layer, a semantic processing layer, a distribution mapping layer and a three-party source layer.

[0103] The pre-processing layer includes a semantic integrity judgment model, a semantic recognition model and a rule management module. The semantic integrity judgment model is used to evaluate the integrity of the query statement and determine the complexity of subsequent processing. The semantic recognition model is used to identify and filter query statements that do not meet the system processing capability, to ensure that the system does not process invalid or meaningless inputs. The rule management module is used to store a plurality of semantic analysis rules and quickly determine the target semantic analysis rule matching the query statement of the user.

[0104] The semantic processing layer includes a complex semantic understanding fusion large model and a vertical domain distribution small model. The complex semantic understanding fusion large model is used to process complex and incomplete query statements and perform deep semantic analysis. The vertical domain distribution small model is used to process query statements according to the requirements of a specific domain and provide fine processing results.

[0105] The distribution mapping layer comprises a semantic fusion module and a semantic distribution mapping table. The semantic fusion module is configured to fuse output results of the complex semantic understanding fusion large model and the vertical domain distribution small model to generate unified output. The semantic distribution mapping table is configured to store distribution mapping relationships and distribution rules.

[0106] The three-party source layer comprises a basic source and a large model source. The number of each type of source can comprise multiple, for example, basic source 1, basic source 2, large model source 1, and large model source 2.

[0107] In some embodiments, the processing architecture of the query statement further comprises an input data management module configured to receive the query statement of the user and perform preliminary preprocessing such as formatting processing, noise filtering, and the like.

[0108] In some embodiments, the processing architecture of the query statement can be represented as a directed graph G=(V, E), wherein V represents each module, and E represents the data flow direction between the modules.

[0109] As shown in Figure 5 The present application proposes another processing method of a query statement, comprising the following steps: After the start of the flow, the following steps are performed: S501, obtaining the query statement input by the user.

[0110] S502, the rule management module determines whether there is a target semantic parsing rule. If yes, S508 is performed, and if no, S503 is performed.

[0111] S503, the semantic recognition model determines whether the query statement is valid. If yes, S504 is performed, and if no, the flow is ended.

[0112] S504, the semantic integrity judgment model determines whether the query statement is complete. If yes, S505 is performed, and if no, S506 is performed.

[0113] S505, determining the semantic parsing result based on the vertical domain distribution small model.

[0114] S506, determining the semantic parsing result based on the complex semantic understanding fusion large model.

[0115] S507, the semantic fusion module fuses the output results of the models.

[0116] S508, determining the distribution rule of the semantic parsing result based on the semantic distribution mapping table.

[0117] S509, determining the target source based on the distribution rule.

[0118] S510, the target source outputs the processing result of the query statement.

[0119] The flow ends.

[0120] As shown in the figure, the method for determining whether the query statement is complete includes the following steps: Figure 6 S601, obtaining the query statement input by the user. S602, searching for the target semantic parsing rule matched with the characteristics of the query statement from the plurality of semantic parsing rules, and determining the semantic parsing result of the query statement based on the target semantic parsing rule.

[0121] S603, if the target semantic parsing rule does not exist, determining whether the query statement is valid, and directly returning the rejection result if the query statement is invalid.

[0122] S604, determining whether the query statement that is not rejected is complete.

[0123] The above mainly describes the scheme provided by the embodiment of the application from the perspective of the method. In order to realize the above functions, the query statement processing device or the electronic device contains the hardware structure and / or software module 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 in the present application, the application can be realized in the form of hardware or the combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0124] The embodiment of the application can divide the functional modules of the query statement processing device or the electronic device according to the above method, for example, the query statement processing device or the electronic device can include each functional module corresponding to each functional division, or two or more functions can be integrated in one processing module. The above integrated module can be realized in the form of hardware or in the form of software functional module. It should be noted that the division of the modules in the embodiment of the application is illustrative, and is only a logical functional division. When actually implemented, there can be another division method.

[0125] In some embodiments, with reference to

[0126] the query statement processing device 700 provided by the embodiment of the application includes a determination unit 701 and a processing unit 702. Figure 7 The determination unit 701 is configured to obtain the query statement input by the user, determine the semantic parsing result of the query statement, and distribute the label.

[0127] The processing unit 702 is configured to determine whether the query statement is valid based on the semantic parsing result and the label, and if the query statement is valid, determine whether the query statement is complete.

[0128] The processing unit 702 is configured to determine a distribution rule of the semantic analysis result based on the distribution label of the query statement and a distribution mapping relationship. The distribution mapping relationship is a mapping relationship between the distribution label of the query statement and the distribution rule. The distribution rule is used to indicate a target source of distribution from a plurality of sources. The semantic analysis result is sent to the target source based on the distribution rule. Feedback information of an execution result of the semantic analysis result by the target source is obtained. The distribution mapping relationship is optimized based on the feedback information.

[0129] In some embodiments, the processing unit 702 is further configured to obtain feedback information of an execution result of the semantic analysis result by the target source, and optimize the distribution mapping relationship based on the feedback information.

[0130] In some embodiments, the determining unit 701 is specifically configured to determine a feature of the query statement, search whether there is a target semantic analysis rule matched with the feature of the query statement from a plurality of semantic analysis rules, and in a case where the target semantic analysis rule is searched, determine the semantic analysis result of the query statement based on the target semantic analysis rule.

[0131] In some embodiments, the determining unit 701 is further configured to, in a case where the target semantic analysis rule is not searched, detect whether the query statement is complete, in a case where the query statement is complete, distribute the query statement to a corresponding vertical small model according to a field to which the query statement belongs for semantic analysis processing to obtain the semantic analysis result, and in a case where the query statement is not complete, perform semantic analysis processing on the query statement by a large model to obtain the semantic analysis result.

[0132] In some embodiments, the determining unit 701 is specifically configured to, in a case where the target semantic analysis rule is not searched, detect whether the query statement is valid, in a case where the query statement is invalid, add a recognition rejection label to the query statement, the recognition rejection label being used to represent that the query statement is not subjected to semantic analysis, and in a case where the query statement is valid, detect whether the query statement is complete.

[0133] In some embodiments, the determining unit 701 is specifically configured to, in a case where the field to which the query statement belongs is a plurality of fields, distribute the query statement to a plurality of vertical small models for semantic analysis processing to obtain output results of the plurality of vertical small models, and fuse the output results of the plurality of vertical small models to obtain the semantic analysis result.

[0134] In some embodiments, the determining unit 701 is specifically configured to perform the following operations by the large model to obtain the semantic analysis result: performing semantic decomposition on the query statement to obtain a plurality of sub-statements of the query statement, performing semantic association on the plurality of sub-statements to obtain a semantic association result, and performing semantic reconstruction on the semantic association result to obtain the semantic analysis result.

[0135] In some embodiments, the processing unit 702 is further configured to obtain a confidence level of the semantic parsing result; and jointly optimize the distribution mapping relationship and the model parameter of the model used for generating the semantic parsing result based on the feedback information and the confidence level.

[0136] In some embodiments, the determining unit 701 is specifically configured to determine the distribution label of the query statement based on the semantic parsing result of the query statement.

[0137] As shown in Figure 8 The electronic device 800 provided by the embodiments of the present application includes but is not limited to a processor 801 and a memory 802.

[0138] The memory 802 is configured to store executable instructions of the processor 801. It can be understood that the processor 801 is configured to execute the instructions to implement the method in the above embodiments.

[0139] It should be noted that those skilled in the art can understand Figure 8 that the electronic device structure shown in the above embodiments does not constitute a limitation on the electronic device, and the electronic device can include more or fewer components than those shown in the above embodiments, or combine certain components, or different component arrangements. Figure 8

[0140] The processor 801 is the control center of the electronic device, which connects each part of the electronic device through various interfaces and lines, executes the software programs and / or modules stored in the memory 802 and calls the data stored in the memory 802, performs various functions of the electronic device and processes data, and thus monitors the whole electronic device. The processor 801 can include one or more processing units. Optionally, the processor 801 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the modem processor can also not be integrated into the processor 801.

[0141] The memory 802 can be used to store software programs and various data. The memory 802 can mainly include a program storage area and a data storage area, wherein the program storage area can store the operating system, the application programs (such as the determining unit, the processing unit, etc.) required by at least one functional module, etc. In addition, the memory 802 can include a high-speed random access memory, and can also include a non-volatile memory, for example, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device.

[0142] In the exemplary embodiments, a vehicle is also provided, which includes the electronic device described above and is used to implement the method in the above embodiments.​

[0143] In an example embodiment, a computer readable storage medium including instructions, for example, the memory 802 including instructions, is also provided, which can be executed by the processor 801 of the electronic device 800 to implement the method in the above embodiment.

[0144] In actual implementation, Figure 7 The functions of the determination unit 701 and the processing unit 702 in the example embodiment can be implemented by Figure 8 The processor 801 in the example embodiment can call the computer program stored in the memory 802 to implement. The specific execution process can refer to the description of the method part in the above embodiment, and will not be described here.

[0145] Optionally, the computer readable storage medium can be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium can be a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), a magnetic tape, a floppy disk and an optical data storage device, etc.

[0146] In an example embodiment, the embodiment of the present application also provides a computer program product including one or more instructions, which can be executed by the processor of the electronic device to complete the method in the above embodiment.

[0147] It should be noted that the instructions in the above computer readable storage medium or the one or more instructions in the computer program product are executed by the processor of the electronic device to implement each process of the above method embodiment, and can achieve the same technical effect as the above method. To avoid repetition, it will not be described here.

[0148] Through the description of the above embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of functional modules is taken as an example for illustration. In actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0149] In several embodiments provided by the present application, it should be understood that the disclosed apparatus and method can be implemented in other manners. For example, the division of the apparatus embodiments is merely an example, and for other division manners, the functions disclosed as belonging to a certain apparatus can be implemented in other manners or integrated into other apparatuses. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electric, mechanical or other forms.

[0150] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, i.e., may be located in one place or distributed in multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0151] In addition, each functional unit in the various embodiments of the present application can be integrated into a processing unit, or each unit can be a physically separate unit, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0152] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The software product is stored in a storage medium, and includes a number of instructions for causing an apparatus (which can be a single-chip microcomputer, a chip, etc.) or a processor to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, and various storage media that can store program codes.

[0153] The above embodiments are merely preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Any equivalent replacement or transformation made by those skilled in the art based on the present application is within the protection scope of the present application.

Claims

1. A method for processing a query statement, characterized in that: The method comprises: Obtaining a query statement input by a user, determining a semantic parsing result of the query statement and a distribution label; Determining a distribution rule for the semantic parsing result based on the distribution tag and distribution mapping relationship of the query statement; wherein the distribution mapping relationship is a mapping relationship between the distribution tag of the query statement and the distribution rule; the distribution rule is used to indicate a target information source for distribution from multiple information sources; Based on the distribution rule, the semantic parsing result is sent to the target information source; Obtaining feedback information of the target source on the execution result of the semantic parsing result; the feedback information includes objective data and subjective data, and the objective data includes at least one of the following: execution success rate, execution time, and completeness of execution result; Optimizing the distribution mapping relationship based on the feedback information; Determining the semantic parsing result of the query statement includes: determining characteristics of the query statement; Retrieve from a plurality of semantic parsing rules whether there is a target semantic parsing rule that matches the features of the query statement; If the target semantic parsing rule is not retrieved, detecting whether the query statement is complete; When the query statement is complete, the query statement is distributed to the corresponding vertical domain small model for semantic parsing according to the domain to which the query statement belongs, to obtain the semantic parsing result; In the case that the query statement is incomplete, the query statement is semantically parsed using a large model to obtain the semantic parsing result.

2. The method according to claim 1, characterized in that Determining the semantic parsing result of the query statement includes: When the target semantic parsing rule is retrieved, a semantic parsing result of the query statement is determined based on the target semantic parsing rule.

3. The method according to claim 1, characterized in that In the case where the target semantic parsing rule is not retrieved, detecting whether the query statement is complete includes: If the target semantic parsing rule is not retrieved, detecting whether the query statement is valid; If the query statement is invalid, adding a rejection tag to the query statement, wherein the rejection tag is used to indicate that semantic parsing of the query statement is not to be performed; If the query statement is valid, whether the query statement is complete is detected.

4. The method according to claim 1, wherein The query statement is distributed to the corresponding vertical domain model for semantic parsing according to the domain to which the query statement belongs, to obtain the semantic parsing result, including: In the case where the query statement belongs to multiple fields, the query statement is issued to multiple vertical field small models for semantic parsing, and output results of the multiple vertical field small models are obtained; The output results of the multiple vertical field small models are integrated to obtain the semantic parsing result.

5. The method according to claim 1, wherein The semantic parsing of the query statement by the large model to obtain the semantic parsing result includes: The semantic parsing result is obtained by performing the following operations on the large model: Semantically decomposing the query statement to obtain multiple sub-statements of the query statement; Performing semantic association on the multiple sub-sentences to obtain a semantic association result; Semantic reconstruction is performed on the semantic association result to obtain the semantic parsing result.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining the confidence level of the semantic parsing result; The optimizing the distribution mapping relationship based on the feedback information includes: Based on the feedback information and the confidence level, the distribution mapping relationship and the model parameters of the model used to generate the semantic parsing result are jointly optimized.

7. The method according to claim 1, characterized in that The determining the distribution label of the query statement includes: Based on the semantic parsing result of the query statement, a distribution label of the query statement is determined.

8. A query statement processing device, characterized in that: include: A determination unit, configured to obtain a query statement input by a user, determine a semantic parsing result of the query statement, and distribute a label; A processing unit is configured to determine a distribution rule for the semantic parsing result based on the distribution tag and distribution mapping relationship of the query statement; wherein the distribution mapping relationship is a mapping relationship between the distribution tag of the query statement and the distribution rule; the distribution rule is used to indicate at least a target information source for distribution from a plurality of information sources; based on the distribution rule, the semantic parsing result is sent to the target information source; feedback information on the execution result of the semantic parsing result by the target information source is obtained; the feedback information includes objective data and subjective data, the objective data including at least one of the following: execution success rate, execution time, and completeness of execution result; based on the feedback information, the distribution mapping relationship is optimized; The determination unit is specifically used to determine the characteristics of the query statement; retrieve from multiple semantic parsing rules whether there is a target semantic parsing rule that matches the characteristics of the query statement; if the target semantic parsing rule is not retrieved, detect whether the query statement is complete; if the query statement is complete, distribute the query statement to the corresponding vertical field small model for semantic parsing processing according to the field to which the query statement belongs, and obtain the semantic parsing result; if the query statement is incomplete, perform semantic parsing processing on the query statement through the large model to obtain the semantic parsing result.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 7.

10. A vehicle, characterized in that: include: The electronic device according to claim 9.

11. A computer-readable storage medium, characterized in that When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the method according to any one of claims 1 to 7.

Images