Data retrieval method, device, equipment and storage medium based on human-computer interaction

Abstract

The present disclosure provides a data retrieval method, device, equipment and storage medium based on human-computer interaction, which relates to the field of artificial intelligence, especially to the field of human-computer interaction. The specific implementation scheme is: obtaining the user's question information, and determining the graph to be retrieved from the preset knowledge graph based on the question information; wherein the preset knowledge graph includes multiple nodes, each node represents a vocabulary unit, the graph to be retrieved is a subgraph in the preset knowledge graph, and the graph to be retrieved represents the question information and information related to the question information; according to the vocabulary units represented by the nodes in the graph to be retrieved, the graph to be retrieved is cropped to obtain a target graph; the reply information corresponding to the question information is determined from the target graph, and the reply information is sent to the user. By cropping the knowledge graph, unnecessary calculations are reduced, the efficiency and accuracy of the retrieval are improved, and the user experience is enhanced.

Description

Technical Field

[0001] The present disclosure relates to the field of human-computer interaction in the field of artificial intelligence, and in particular to a data retrieval method, apparatus, device and storage medium based on human-computer interaction. Background Art

[0002] With the development of artificial intelligence technology, users can query various information according to their needs. For example, users can input the questions they want to query through human-computer interaction and quickly get the answers to their questions through data retrieval.

[0003] Current retrieval methods can search through a pre-set knowledge graph to find information relevant to user needs and respond to the user. However, this method is computationally intensive, and the efficiency and accuracy of retrieval are low, affecting the user experience. Summary of the Invention

[0004] The present disclosure provides a data retrieval method, apparatus, device and storage medium based on human-computer interaction.

[0005] According to a first aspect of the present disclosure, a data retrieval method based on human-computer interaction is provided, comprising:

[0006] Obtaining user question information, and determining a to-be-searched graph from a preset knowledge graph based on the question information; wherein the preset knowledge graph includes a plurality of nodes, each node representing a vocabulary unit, and the to-be-searched graph is a subgraph in the preset knowledge graph, and the to-be-searched graph represents the question information and information related to the question information;

[0007] According to the vocabulary units represented by the nodes in the to-be-searched graph, the to-be-searched graph is trimmed to obtain a target graph;

[0008] Determine reply information corresponding to the question information from the target graph, and send the reply information to the user.

[0009] According to a second aspect of the present disclosure, a data retrieval device based on human-computer interaction is provided, comprising:

[0010] an acquisition unit, configured to acquire a user's question information and, based on the question information, determine a graph to be retrieved from a preset knowledge graph; wherein the preset knowledge graph includes a plurality of nodes, each node representing a vocabulary unit, and the graph to be retrieved is a subgraph in the preset knowledge graph, and the graph to be retrieved represents the question information and information related to the question information;

[0011] A clipping unit, configured to clip the graph to be searched according to the vocabulary units represented by the nodes in the graph to be searched, to obtain a target graph;

[0012] A reply unit is used to determine reply information corresponding to the question information from the target map and send the reply information to the user.

[0013] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0014] at least one processor; and

[0015] a memory communicatively coupled to the at least one processor;

[0016] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect of the present disclosure.

[0017] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method according to the first aspect of the present disclosure.

[0018] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements the steps of the method described in the first aspect of the present disclosure when executed by a processor.

[0019] The technology disclosed herein improves the efficiency and accuracy of data retrieval and enhances user experience.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0022] Figure 1 This is a flow chart of a data retrieval method based on human-computer interaction provided according to an embodiment of the present disclosure;

[0023] Figure 2 is a schematic diagram of a knowledge graph provided according to an embodiment of the present disclosure;

[0024] Figure 3 This is a flow chart of a data retrieval method based on human-computer interaction provided according to an embodiment of the present disclosure;

[0025] Figure 4 This is a flow chart of a data retrieval method based on human-computer interaction provided according to an embodiment of the present disclosure;

[0026] Figure 5 This is a structural block diagram of a data retrieval device based on human-computer interaction provided according to an embodiment of the present disclosure;

[0027] Figure 6 This is a structural block diagram of a data retrieval device based on human-computer interaction provided according to an embodiment of the present disclosure;

[0028] Figure 7 is a block diagram of an electronic device for implementing the data retrieval method based on human-computer interaction according to an embodiment of the present disclosure;

[0029] Figure 8 The block diagram is a block diagram of an electronic device for implementing the data retrieval method based on human-computer interaction according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0031] When users provide query requirements, large language models may affect the user experience due to shallow or lack of specificity in their answers. The RAG (Retrieval Augmented Generation) model can alleviate this problem to a certain extent by retrieving relevant text information. However, due to the variable length of relevant text information and the flexibility of natural language expression of text, RAG has difficulty emphasizing the influence relationship between entity words in the text. The graph retrieval enhanced language model uses the clear entity and relationship representations in the graph data and can provide more accurate answer information by supplementing and optimizing keyword recall.

[0032] Current data retrieval methods can determine the response information to users through full-text search, vector search, and graph search. Full-text search primarily relies on comprehensive scanning and matching of text content, accurately searching for keywords, phrases, or sentences within the text to locate relevant documents or information. However, full-text search can be inefficient when processing large datasets, and its ability to determine semantic relevance is limited. Vector search utilizes machine learning techniques to convert text content into vector representations and evaluate the relevance between texts by calculating the similarity between vectors. While this approach can capture the semantic characteristics of text and achieve high retrieval efficiency when processing large datasets, it may not accurately capture the user's true intent when processing complex queries. Graph-based retrieval methods represent text content as nodes and edges in a graph, traversing and searching the graph to locate relevant documents or information. This approach can capture the relevance and context between texts and is highly capable of handling complex queries. However, graph construction and maintenance are costly, and there is a lack of precise mathematical models to evaluate the relevance between nodes.

[0033] The present disclosure provides a data retrieval method, apparatus, device and storage medium based on human-computer interaction, which are applied to the human-computer interaction field in the field of artificial intelligence to improve the efficiency and accuracy of data retrieval and enhance user experience.

[0034] It should be noted that the data in this embodiment is not targeted at a specific user and does not reflect the personal information of a specific user. It should be noted that the data in this embodiment comes from a public data set.

[0035] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0036] In order to make readers more deeply understand the implementation principle of this disclosure, the following Figures 1-8 The embodiment is further refined.

[0037] Figure 1 The flowchart of a data retrieval method based on human-computer interaction provided in accordance with an embodiment of the present disclosure is shown in FIG. Figure 1 As shown, the method includes the following steps:

[0038] S101. Obtain the user's question information, and determine the graph to be retrieved from the preset knowledge graph based on the question information; wherein the preset knowledge graph includes multiple nodes, each node represents a vocabulary unit, the graph to be retrieved is a subgraph in the preset knowledge graph, and the graph to be retrieved represents the question information and information related to the question information.

[0039] For example, a user can ask a question through human-computer interaction, for example, by inputting voice or text, and the user's input is determined as the question. The question represents the user's query. For example, if a user wants to find movies set in a park, the user's input question might be "What are some movies set in a park?" The user's question is the user's query, and the user's query can be obtained in real time.

[0040] A pre-built knowledge graph can be structured as a topological graph. The knowledge graph includes multiple nodes, each corresponding to a lexical unit. Nodes can be connected by edges. Lexical units can be words of any part of speech, such as quantifiers, nouns, and pronouns. Figure 2 A schematic diagram of the knowledge graph. Figure 2 There are ten nodes in , and if there is an edge connection between two nodes, it means that there is an association relationship between the two nodes. For example, Figure 2 There is an edge connection between the "Movie" node and the "Actor A" node, indicating that there is a certain relationship between actor A and the movie.

[0041] Based on the question information, the knowledge graph can be clipped to obtain a portion of the knowledge graph. That is, a subgraph can be clipped from the knowledge graph to serve as the search graph. The search graph can include multiple nodes and can represent the question information and information related to the question information. In other words, the portion of the knowledge graph related to the question information can be clipped to serve as the search graph.

[0042] For example, if the question is "What are the movies with park scenes?", you can search the knowledge graph for the nodes of "park" and "movie", and then determine the multiple nodes that are connected to "park" by edges, as well as the multiple nodes that are connected to "movie" by edges. These determined nodes and connection relationships will be determined as the graph to be retrieved.

[0043] S102. Crop the graph to be searched according to the vocabulary units represented by the nodes in the graph to be searched to obtain a target graph.

[0044] For example, in the graph to be searched, each node corresponds to its own lexical unit. The lexical unit represented by each node in the graph to be searched is determined. Based on the lexical units represented by each node in the graph to be searched, the graph to be searched is cropped to obtain a target graph. That is, the target graph is a subgraph of the graph to be searched.

[0045] In this embodiment, the graph to be searched can be trimmed according to the semantics of the vocabulary units represented by the nodes in the graph to be searched. Specifically, the vocabulary units represented by the nodes in the graph to be searched can be semantically analyzed to determine the semantics of the vocabulary units. The nodes are sorted according to the semantics of the vocabulary units. For example, the semantic richness of the vocabulary units can be calculated, and the nodes are sorted according to the richness, with the nodes with greater richness being placed in front. In this embodiment, there is no specific limitation on the method of calculating the semantic richness. For example, the vocabulary units include "yes" and "high-tech", and the semantic richness of "high-tech" is greater than the semantic richness of "yes". After sorting the nodes, the nodes ranked in the last few places can be trimmed in the graph to be searched to obtain the target graph.

[0046] S103: Determine the reply information corresponding to the question information from the target graph, and send the reply information to the user.

[0047] For example, after obtaining the target graph, the reply information corresponding to the question information is determined according to the target graph, that is, the answer to the user's query is determined, and the reply information is sent to the user to complete the data retrieval process.

[0048] The target graph can include multiple nodes. The lexical units represented by the nodes in the target graph can be combined, and the resulting sentence can be sent to the user as a reply message. Alternatively, the lexical units represented by the nodes in the target graph can be first determined, and then text information related to these lexical units can be retrieved from a preset database, and the retrieved information can be sent to the user as a reply message. The preset database can store a large amount of text information. For example, the target graph can be traversed through the nodes to search for documents related to each node.

[0049] In this embodiment, reply information corresponding to the question information is determined from the target graph, including: determining the semantic information of the vocabulary units represented by each node in the target graph; based on the semantic information of the vocabulary units represented by each node in the target graph, semantic splicing processing is performed on the vocabulary units represented by each node in the target graph to obtain reply information corresponding to the question information.

[0050] Specifically, semantic recognition processing is performed on the vocabulary unit represented by each node in the target graph to obtain semantic information of the vocabulary unit represented by the node. In this embodiment, the process of semantic recognition is not specifically limited.

[0051] Based on the semantic information of the lexical units represented by each node in the target graph, semantic splicing processing is performed on the lexical units represented by each node in the target graph. That is, a sentence can be generated based on the lexical units, and the generated sentence can be used as the response information corresponding to the question information. For example, based on the semantic information, the order of the lexical units can be adjusted, or the sentences between the lexical units can be supplemented to obtain a complete and coherent sentence as the response information.

[0052] After obtaining semantic information, the vocabulary units can be scored and the nodes in the target graph can be filtered based on the scoring results, thereby filtering out nodes with unimportant semantics. The vocabulary units of the remaining nodes are spliced ​​together to obtain the response information corresponding to the question information. For example, the vocabulary units can be scored based on semantic information, with the richer the semantics, the higher the score. Alternatively, the semantic relevance between vocabulary units can be determined, with the higher the relevance, the higher the score.

[0053] The beneficial effect of this setting is that reply information is automatically generated based on the vocabulary units in the target graph, which improves the flexibility of determining reply information. There is no need to extract text content from documents with fixed content as reply information, which increases the diversity of reply information and enhances user experience.

[0054] In the embodiment of the present disclosure, the knowledge graph is first pruned based on the user's question information to obtain a graph to be retrieved. Then, the graph to be retrieved is pruned a second time based on the vocabulary units represented by the nodes in the graph to be retrieved to obtain a target graph. Based on the target graph, the reply information corresponding to the question information is determined and sent to the user. By pruned irrelevant or redundant subgraphs during the graph retrieval process, unnecessary computation is effectively reduced, thereby further focusing on the reply information related to the user's needs, improving the accuracy and efficiency of data retrieval, and enhancing the user experience.

[0055] Figure 3 A flowchart of a data retrieval method based on human-computer interaction provided in an embodiment of the present disclosure.

[0056] In this embodiment, based on the question information, a graph to be retrieved is determined from a preset knowledge graph, including: segmenting the question information to obtain vocabulary units in the question information; and determining the graph to be retrieved from the preset knowledge graph based on the vocabulary units in the question information.

[0057] This embodiment is based on the above embodiment. Figure 3 As shown, the method includes the following steps:

[0058] S301: Obtain user's question information, and segment the question information to obtain vocabulary units in the question information.

[0059] For example, the question information sent by the user is obtained in real time. When the user sends the question information, the user can send it in the form of voice or text. After obtaining the content sent by the user, it can be uniformly converted into text form, that is, the question information containing text content can be obtained.

[0060] The question information is segmented, that is, the text content representing the user's needs is segmented. The segmentation process can refer to word segmentation of the question information to obtain multiple vocabulary units in the question information, and the vocabulary units are the components of the question information. For example, the question information is "XX is a high-tech company". After segmentation, the vocabulary units obtained include "XX", "is", "a", "high-tech", and "company". In this embodiment, the word segmentation method is not specifically limited. For example, semantic recognition can be performed on the question information, and the vocabulary units contained in the question information can be determined based on the recognized semantics.

[0061] S302: Determine a graph to be searched from a preset knowledge graph based on the vocabulary units in the question information.

[0062] Exemplarily, the nodes where the vocabulary units in the question information are located are searched from the preset knowledge graph, and the nodes that are connected to the nodes of these vocabulary units by edges can also be searched. The graph formed by these nodes found is used as the graph to be searched. For example, if the vocabulary unit in the question information is "high-tech", then the node where "high-tech" is located is searched from the knowledge graph, and there are eight nodes that are connected to the node by edges, then these nine nodes and their connection relationships are used as the graph to be searched. In this embodiment, full-text retrieval can be used to comprehensively scan and match the vocabulary units in the question information, and the relevant nodes in the knowledge graph can be located by accurately searching for vocabulary units such as keywords and phrases.

[0063] In this embodiment, the user's query is parsed and multiple vocabulary units can be extracted from the query, so that the knowledge graph can be tailored according to the vocabulary units, realizing the combination of full-text retrieval, semantic retrieval, and graph retrieval, so that the graph to be searched can focus on the user's query, improving the efficiency and accuracy of data retrieval.

[0064] In this embodiment, based on the vocabulary units in the question information, the graph to be retrieved is determined from the preset knowledge graph, including: determining the part-of-speech information of the vocabulary units in the question information; based on the part-of-speech information of the vocabulary units in the question information, determining the graph to be retrieved from the preset knowledge graph.

[0065] Specifically, for each lexical unit in the question information, the part-of-speech information of the lexical unit is determined, that is, the lexical unit in the question information is analyzed. A preset part-of-speech analysis tool can be used. In this embodiment, the part-of-speech analysis tool is not specifically limited. Different parts of speech can correspond to their own labels. Table 1 is an introduction to parts of speech.

[0066] Table 1 Parts of speech introduction

[0067]

[0068] Determine the part-of-speech information of each vocabulary unit in the question information, and use corresponding labels to mark the vocabulary units in the question information. According to the part-of-speech information of each vocabulary unit in the question information, determine the graph to be retrieved from the preset knowledge graph. For example, the vocabulary units in the question information can be screened according to the part-of-speech information, and the vocabulary units with the preset part-of-speech can be screened out. According to the retained vocabulary units, the knowledge graph is trimmed to obtain the graph to be retrieved. Alternatively, different part-of-speech information corresponds to different trimming ranges, and the trimming range refers to the degree of the trimmed edge connection, that is, the length of the edge connection. For example, for the vocabulary unit of a noun, the edge connection of the vocabulary unit to two degrees outward can be trimmed. Two degrees refers to determining the node that has an edge connection with the vocabulary unit, and the node that has an edge connection with the node. According to the part-of-speech information of the vocabulary unit, the edge connection of the vocabulary unit is trimmed to different lengths to obtain the graph to be retrieved.

[0069] The beneficial effect of this setting is that by performing part-of-speech analysis on the vocabulary units in the question information, different parts of speech can be targetedly cropped in the knowledge graph, thereby improving the effectiveness of cropping and thus improving the accuracy and efficiency of data retrieval.

[0070] In this embodiment, based on the part-of-speech information of the vocabulary units in the question information, a graph to be retrieved is determined from a preset knowledge graph, including: based on the part-of-speech information of the vocabulary units in the question information, a first weight of the vocabulary units in the question information is determined based on a preset first association relationship; wherein the first weight represents the importance of the vocabulary unit, and the preset first association relationship represents the association relationship between the part-of-speech information and the weight; based on the first weight of the vocabulary units in the question information, a graph to be retrieved is determined from a preset knowledge graph.

[0071] Specifically, a first association relationship is pre-set, which can represent the association relationship between part-of-speech information and a first weight, and the first weight can represent the importance of the vocabulary unit in the sentence. For each vocabulary unit in the question information, a first weight corresponding to the part-of-speech information of the vocabulary unit can be determined based on the preset first association relationship, that is, the first weight corresponding to the vocabulary unit can be obtained. For example, the first weight of an organization name is 3, the first weight of a verb is 0, the first weight of a quantifier is 1, and the first weight of a noun is 2.

[0072] The lexical units in the question information are sorted based on the first weights of the lexical units. For example, the lexical units can be sorted in descending order of first weight. Based on the sorting results, unimportant lexical units are filtered out. For example, lexical units with first weights less than 1 can be filtered out. Based on the retained lexical units, a graph to be searched is determined from the preset knowledge graph.

[0073] The beneficial effect of this setting is that the knowledge graph can be tailored according to the importance of lexical units of different parts of speech, avoiding the cutting of unimportant data into the graph to be retrieved, thereby improving the accuracy of data retrieval.

[0074] In this embodiment, a graph to be retrieved is determined from a preset knowledge graph based on the first weight of the vocabulary unit in the question information, including: determining a target vocabulary from the question information based on the first weight of the vocabulary unit in the question information; wherein the target vocabulary is a key vocabulary unit in the question information; and determining a graph to be retrieved from the preset knowledge graph based on the target vocabulary.

[0075] Specifically, based on the first weights of the vocabulary units in the question information, the vocabulary units in the question information are screened out, thereby determining the target vocabulary from the vocabulary units in the question information. The target vocabulary is a key vocabulary unit in the question information, and there can be one or more target vocabulary units. For example, a weight threshold can be preset, and the first weight of each vocabulary unit is compared with the preset weight threshold. If the first weight is greater than the weight threshold, the vocabulary unit with the first weight is determined to be the target vocabulary.

[0076] The node where the target vocabulary is located is searched from the preset knowledge graph, and the graph to be searched is cut out based on the node where the target vocabulary is located. A cutting range can be preset, and the node where the target vocabulary is located is used as the center. According to the preset cutting range, the knowledge graph is cut out to obtain the graph to be searched. For example, if the preset cutting range is 10 degrees, then the node where each target vocabulary is located can be used as the center, and each target vocabulary is searched for 10-degree edge connections outward, that is, the node where the target vocabulary is located is determined as the target vocabulary node, and the nodes that have direct and indirect edge connections with the target vocabulary node are determined. These nodes can form branches extending from the target vocabulary node, and each branch has ten nodes in addition to the target vocabulary node.

[0077] For each target vocabulary node, a subgraph can be cut out from the knowledge graph. Each subgraph typically contains duplicate nodes. Based on these duplicate nodes, the subgraphs corresponding to each target vocabulary node can be concatenated to obtain the query information's searchable graph. If two subgraphs do not contain duplicate nodes, the closest nodes in the knowledge graph can be connected to obtain the merged searchable graph.

[0078] The beneficial effect of this setting is that, based on the size of the first weight, the more important vocabulary units in the question information are determined, and only the subgraphs corresponding to the important vocabulary units are extracted, thereby improving the accuracy of determining the graph to be retrieved, avoiding computational redundancy, and improving the accuracy and efficiency of data retrieval.

[0079] S303: Crop the graph to be searched according to the vocabulary units represented by the nodes in the graph to be searched to obtain a target graph.

[0080] For example, this step may refer to the above-mentioned step S102 and will not be described in detail.

[0081] S304: Determine the reply information corresponding to the question information from the target graph, and send the reply information to the user.

[0082] For example, this step may refer to the above-mentioned step S103 and will not be described in detail.

[0083] In the embodiment of the present disclosure, the knowledge graph is first pruned based on the user's question information to obtain a graph to be retrieved. Then, the graph to be retrieved is pruned a second time based on the vocabulary units represented by the nodes in the graph to be retrieved to obtain a target graph. Based on the target graph, the reply information corresponding to the question information is determined and sent to the user. By pruned irrelevant or redundant subgraphs during the graph retrieval process, unnecessary computation is effectively reduced, thereby further focusing on the reply information related to the user's needs, improving the accuracy and efficiency of data retrieval, and enhancing the user experience.

[0084] Figure 4 A flowchart of a data retrieval method based on human-computer interaction provided in an embodiment of the present disclosure.

[0085] In this embodiment, the graph to be searched is cropped according to the vocabulary units represented by the nodes in the graph to be searched to obtain a target graph, including: determining the vocabulary type to which the vocabulary units represented by the nodes in the graph to be searched belong, which is the type to be searched; wherein the vocabulary type represents the meaning of the vocabulary unit; determining the second weight corresponding to the type to be searched according to a preset second association relationship; wherein the preset second association relationship represents the association relationship between the vocabulary type and the weight, and the second weight represents the importance of the vocabulary type; according to the second weight corresponding to the type to be searched, the graph to be searched is cropped to obtain a target graph.

[0086] This embodiment is based on the above embodiment. Figure 4 As shown, the method includes the following steps:

[0087] S401. Obtain the user's question information, and determine the graph to be retrieved from the preset knowledge graph based on the question information; wherein the preset knowledge graph includes multiple nodes, each node represents a vocabulary unit, the graph to be retrieved is a subgraph in the preset knowledge graph, and the graph to be retrieved represents the question information and information related to the question information.

[0088] For example, this step may refer to the above-mentioned step S101 and will not be described in detail.

[0089] S402: Determine the vocabulary type to which the vocabulary unit represented by the node in the to-be-searched graph belongs, which is the to-be-searched type; wherein the vocabulary type represents the meaning of the vocabulary unit.

[0090] Exemplarily, the vocabulary units represented by each node in the to-be-searched graph are determined. The vocabulary units in the to-be-searched graph may include vocabulary units in the question information, and may also include vocabulary units not in the question information.

[0091] Each vocabulary unit has its own vocabulary type. The vocabulary types of different vocabulary units can be the same or different. For each vocabulary unit in the to-be-searched graph, the vocabulary type of the vocabulary unit is determined as the to-be-searched type. The vocabulary type can represent the meaning of the vocabulary unit. For example, if the vocabulary units are City A and City B, the vocabulary types of these two vocabulary units are place names; if the vocabulary units are Zhang San and Li Si, the vocabulary types of these two vocabulary units are people.

[0092] You can preset the vocabulary units contained in different vocabulary types. After obtaining the vocabulary units in the search graph, you can search for the corresponding vocabulary types as the search types. You can also perform semantic recognition on the vocabulary units in the search graph to determine the semantics represented by the vocabulary units, and then determine the search type based on the represented semantics.

[0093] S403: Determine a second weight corresponding to the type to be retrieved based on a preset second association relationship; wherein the preset second association relationship represents the association relationship between the vocabulary type and the second weight, and the second weight represents the importance of the vocabulary type.

[0094] Exemplarily, a second association relationship is pre-set, and the second association relationship represents the association relationship between the vocabulary type and the second weight, and the second weight represents the importance of the vocabulary type. After determining the type to be retrieved of each vocabulary unit in the to-be-retrieved graph, the second weight corresponding to each type to be retrieved is determined according to the preset second association relationship. For example, the nodes in the to-be-retrieved graph include vocabulary units representing movies and vocabulary units representing characters, and the types to be retrieved include movie types and character types. The second weight corresponding to the movie type is 3, and the second weight corresponding to the character type is 2.

[0095] S404: Crop the graph to be searched according to the second weight corresponding to the type to be searched to obtain a target graph.

[0096] Exemplarily, the second weights corresponding to the types to be searched are determined, and the target graph is cropped based on the second weights corresponding to the types to be searched. After cropping, the target graph is obtained. That is, the target graph is a subgraph of the target graph. For example, lexical units of lexical types with smaller weights can be screened out from the target graph, and the remaining portion is determined as the target graph.

[0097] In this embodiment, the importance of the vocabulary units in the graph to be retrieved is determined based on the vocabulary types in the graph to be retrieved, and the graph is trimmed again based on the importance, further focusing the information in the graph to content related to the user's question information, thereby improving the accuracy of the recalled content, reducing the amount of calculation, and improving the efficiency and accuracy of data retrieval.

[0098] In this embodiment, the graph to be searched is cropped according to the second weight corresponding to the type to be searched to obtain a target graph, including: determining a target type from the type to be searched according to the second weight corresponding to the type to be searched; wherein the target type is a key vocabulary type in the type to be searched; and according to the target type, the graph to be searched is cropped to obtain a target graph.

[0099] Specifically, the search types are sorted according to the second weights corresponding to the search types to obtain a sorting result. Based on the sorting result, the search types are filtered. For example, the second weights can be sorted from large to small, and the search types ranked at the bottom are filtered out.

[0100] The remaining search types are identified as target types. The target type is a relatively important vocabulary type among the search types. For example, a second weight threshold can be preset, and the second weight of each search type can be compared with the threshold. If the second weight is greater than the threshold, the search type corresponding to the second weight is the target type.

[0101] After obtaining the target type, the graph to be searched can be pruned based on the target type. For example, only the target type vocabulary units and the nodes that have edge connections to the vocabulary unit's nodes can be retained to obtain the target graph. Alternatively, non-target vocabulary units and the nodes that have edge connections to the vocabulary unit's nodes can be pruned, and the remaining portion can be determined as the target graph.

[0102] The beneficial effect of such a setting is that, according to the size of the second weight, important vocabulary types are determined, key information is retained from the graph to be retrieved, redundant information is reduced, and the accuracy of data retrieval is improved.

[0103] In this embodiment, the graph to be searched is cropped according to the target type to obtain the target graph, including: determining the node where the vocabulary unit belonging to the target type is located in the graph to be searched as the target node; according to the position of the target node in the graph to be searched, the graph to be searched is cropped to obtain the target graph.

[0104] Specifically, a lexical unit of the target type is determined in the graph to be searched, and the node where the lexical unit is located is determined as the target node. The position of the target node in the graph to be searched is determined, and the graph to be searched is cropped based on the position of the target node in the graph to be searched to obtain a cropped target graph. For example, the target node and nodes near the target node in the graph to be searched can be retained to obtain the target graph.

[0105] The beneficial effect of this setting is that it can crop according to the position of the target node, retain important information in the graph to be retrieved, improve the correlation between the recalled content and the question information, and the recalled content can be used as reply information, thereby improving the accuracy and efficiency of the reply information.

[0106] In this embodiment, the graph to be retrieved is cropped according to the position of the target node in the graph to be retrieved to obtain the target graph, including: according to a preset cropping range, the graph to be retrieved is cropped with the position of the target node in the graph to be retrieved as the center to obtain a cropped graph corresponding to the target node; wherein the cropped graph is a subgraph of the graph to be retrieved, and the target node corresponds to the cropped graph one-to-one; the cropped graphs corresponding to the target nodes are spliced ​​to obtain the target graph.

[0107] Specifically, a clipping range of the target graph is pre-set, and the clipping range can refer to the degree of edge connection. For each target node in the to-be-searched graph, the to-be-searched graph is clipped according to the preset clipping range, with the target node's position as the center. The clipping range can be the maximum clipping length of each branch extending from the target node. For example, if the clipping range is 2 degrees, then for each branch of the target node, only two nodes other than the target node are retained, that is, the two nodes closest to the target node are retained. In other words, there are two edge connections on each branch.

[0108] For each target node, it is cropped according to the cropping range. Each target node corresponds to a subgraph cropped from the graph to be retrieved, and the subgraph corresponding to the target node is determined as the cropped graph. That is, the cropped graph is a subgraph of the graph to be retrieved, and the target node corresponds to the cropped graph one-to-one. The cropped graphs corresponding to each target node are spliced ​​to obtain a complete target graph. For example, a node for connection can be found from each of the two cropped graphs, and the two nodes are edge-connected to complete the splicing of the cropped graphs. The nodes for connection can be found randomly, or the nodes for connection can be determined based on the distance between the nodes in the two cropped graphs in the graph to be retrieved. For example, the two nodes with the least number of edge connections between the nodes can be determined as the nodes for connection.

[0109] This setup has the beneficial effect of retaining nodes surrounding the target node, preventing loss of important information and increasing the richness of the response information. By splicing multiple cropped atlases together to achieve atlas integration, it facilitates retrieval of question information, improves the accuracy and efficiency of response information, and enhances the user's human-computer interaction experience.

[0110] S405: Determine the reply information corresponding to the question information from the target graph, and send the reply information to the user.

[0111] For example, this step may refer to the above-mentioned step S103 and will not be described in detail.

[0112] In the embodiment of the present disclosure, the knowledge graph is first pruned based on the user's question information to obtain a graph to be retrieved. Then, the graph to be retrieved is pruned a second time based on the vocabulary units represented by the nodes in the graph to be retrieved to obtain a target graph. Based on the target graph, the reply information corresponding to the question information is determined and sent to the user. By pruned irrelevant or redundant subgraphs during the graph retrieval process, unnecessary computation is effectively reduced, thereby further focusing on the reply information related to the user's needs, improving the accuracy and efficiency of data retrieval, and enhancing the user experience.

[0113] Figure 5 This is a structural block diagram of a data retrieval device based on human-computer interaction provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 5 The data retrieval device 500 based on human-computer interaction includes: an acquisition unit 501, a clipping unit 502 and a reply unit 503.

[0114] An acquisition unit 501 is configured to acquire a user's question information and, based on the question information, determine a graph to be searched from a preset knowledge graph; wherein the preset knowledge graph includes a plurality of nodes, each node representing a vocabulary unit, and the graph to be searched is a subgraph in the preset knowledge graph, and the graph to be searched represents the question information and information related to the question information;

[0115] A clipping unit 502 is configured to clip the graph to be searched according to the vocabulary units represented by the nodes in the graph to be searched, to obtain a target graph;

[0116] The reply unit 503 is configured to determine reply information corresponding to the question information from the target graph and send the reply information to the user.

[0117] Figure 6 This is a structural block diagram of a data retrieval device based on human-computer interaction provided by an embodiment of the present disclosure, such as Figure 6 As shown, the data retrieval device 600 based on human-computer interaction includes an acquisition unit 601, a cropping unit 602 and a reply unit 603, wherein the acquisition unit 601 includes a segmentation module 6011 and a graph determination module 6012.

[0118] A segmentation module 6011 is used to segment the question information to obtain vocabulary units in the question information;

[0119] The graph determination module 6012 is used to determine the graph to be searched from the preset knowledge graph based on the vocabulary units in the question information.

[0120] In one example, the atlas determination module 6012 includes:

[0121] a part-of-speech determination submodule, configured to determine the part-of-speech information of the vocabulary units in the question information;

[0122] The graph determination submodule is used to determine the graph to be retrieved from the preset knowledge graph based on the part-of-speech information of the vocabulary unit in the question information.

[0123] In one example, the graph determination submodule is specifically used to:

[0124] Determining, based on the part-of-speech information of the vocabulary unit in the question information and a preset first association relationship, a first weight of the vocabulary unit in the question information; wherein the first weight represents the importance of the vocabulary unit, and the preset first association relationship represents the association relationship between the part-of-speech information and the weight;

[0125] According to the first weight of the vocabulary unit in the question information, the to-be-searched graph is determined from a preset knowledge graph.

[0126] In one example, the graph determination submodule is specifically used to:

[0127] Determining a target vocabulary from the question information according to a first weight of the vocabulary unit in the question information; wherein the target vocabulary is a key vocabulary unit in the question information;

[0128] According to the target vocabulary, the graph to be searched is determined from a preset knowledge graph.

[0129] In one example, the cropping unit 602 includes:

[0130] A type determination module, configured to determine the vocabulary type to which the vocabulary unit represented by the node in the to-be-searched graph belongs, as the to-be-searched type; wherein the vocabulary type represents the meaning of the vocabulary unit;

[0131] A weight determination module, configured to determine a second weight corresponding to the type to be retrieved based on a preset second association relationship; wherein the preset second association relationship represents an association relationship between the vocabulary type and the second weight, and the second weight represents the importance of the vocabulary type;

[0132] The target determination module is used to crop the to-be-retrieved atlas according to the second weight corresponding to the to-be-retrieved type to obtain a target atlas.

[0133] In one example, the target determination module includes:

[0134] A target determination submodule, configured to determine a target type from the types to be retrieved according to a second weight corresponding to the types to be retrieved; wherein the target type is a key vocabulary type in the types to be retrieved;

[0135] The cropping submodule is used to crop the to-be-retrieved atlas according to the target type to obtain the target atlas.

[0136] In one example, the cropping submodule is specifically used to:

[0137] Determine the node in the to-be-searched graph where the vocabulary unit belonging to the target type is located as the target node;

[0138] According to the position of the target node in the to-be-searched graph, the to-be-searched graph is cropped to obtain the target graph.

[0139] In one example, the cropping submodule is specifically used to:

[0140] According to a preset clipping range, the to-be-searched graph is clipped with the position of the target node in the to-be-searched graph as the center to obtain a clipped graph corresponding to the target node; wherein the clipped graph is a subgraph of the to-be-searched graph, and the target node corresponds to the clipped graph one-to-one;

[0141] The cropped atlas corresponding to each target node is spliced ​​to obtain the target atlas.

[0142] In one example, the reply unit 603 includes:

[0143] A semantic determination module, configured to determine the semantic information of the vocabulary unit represented by each node in the target graph;

[0144] The reply generation module is used to perform semantic splicing processing on the vocabulary units represented by each node in the target graph according to the semantic information of the vocabulary units represented by each node in the target graph to obtain reply information corresponding to the question information.

[0145] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device.

[0146] Figure 7 This is a structural block diagram of an electronic device provided in an embodiment of the present disclosure. The electronic device may be a terminal device, a processor or a server. Figure 7As shown, the electronic device 70 includes: at least one processor 702; and a memory 701 communicatively connected to the at least one processor 702; wherein the memory stores instructions that can be executed by the at least one processor 702, and the instructions are executed by the at least one processor 702 to enable the at least one processor 702 to execute the human-computer interaction-based data retrieval method disclosed herein.

[0147] The electronic device 70 further includes a receiver 703 and a transmitter 704. The receiver 703 is used to receive instructions and data sent by other devices, and the transmitter 704 is used to send instructions and data to external devices.

[0148] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0149] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device executes the solution provided by any of the above embodiments.

[0150] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0151] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0152] Various components in device 800 are connected to I / O interface 805, including an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0153] The computing unit 801 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as a data retrieval method based on human-computer interaction. For example, in some embodiments, the data retrieval method based on human-computer interaction can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the data retrieval based on human-computer interaction described above can be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the human-computer interaction-based data retrieval method in any other appropriate manner (for example, by means of firmware).

[0154] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0155] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0156] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0157] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0158] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0159] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship is established by computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and VPS services ("Virtual Private Servers" or simply "VPS"). The server may also be a server in a distributed system or a server integrated with blockchain.

[0160] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0161] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A data retrieval method based on human-computer interaction, comprising: Acquiring user's question information and segmenting the question information to obtain vocabulary units in the question information; Determining part-of-speech information of vocabulary units in the question information; Determining, based on the part-of-speech information of the vocabulary unit in the question information and a preset first association relationship, a first weight of the vocabulary unit in the question information; wherein the first weight represents the importance of the vocabulary unit, and the preset first association relationship represents the association relationship between the part-of-speech information and the weight; Determining a graph to be searched from a preset knowledge graph based on a first weight of a vocabulary unit in the question information; wherein the preset knowledge graph includes a plurality of nodes, each node represents a vocabulary unit, the graph to be searched is a subgraph in the preset knowledge graph, and the graph to be searched represents the question information and information related to the question information; Determine the vocabulary type to which the vocabulary unit represented by the node in the to-be-searched graph belongs, as the to-be-searched type; wherein the vocabulary type represents the meaning of the vocabulary unit; Determining a second weight corresponding to the type to be retrieved according to a preset second association relationship; wherein the preset second association relationship represents an association relationship between the vocabulary type and the second weight, and the second weight represents the importance of the vocabulary type; According to the second weight corresponding to the type to be searched, the to-be-searched atlas is cropped to obtain a target atlas; Determine reply information corresponding to the question information from the target graph, and send the reply information to the user.

2. The method according to claim 1, wherein The step of determining a graph to be searched from a preset knowledge graph based on the first weight of the vocabulary unit in the question information includes: Determining a target vocabulary from the question information according to a first weight of the vocabulary unit in the question information; wherein the target vocabulary is a key vocabulary unit in the question information; According to the target vocabulary, the graph to be searched is determined from a preset knowledge graph.

3. The method according to claim 1, wherein The step of clipping the to-be-searched graph according to the second weight corresponding to the to-be-searched type to obtain a target graph includes: Determining a target type from the types to be searched according to a second weight corresponding to the types to be searched; wherein the target type is a key vocabulary type in the types to be searched; According to the target type, the to-be-searched atlas is cropped to obtain the target atlas.

4. The method according to claim 3, wherein: The step of clipping the to-be-searched atlas according to the target type to obtain the target atlas includes: Determine the node in the to-be-searched graph where the vocabulary unit belonging to the target type is located as the target node; According to the position of the target node in the to-be-searched graph, the to-be-searched graph is cropped to obtain the target graph.

5. The method according to claim 4, wherein The step of clipping the graph to be searched according to the position of the target node in the graph to be searched to obtain the target graph includes: According to a preset clipping range, the to-be-searched graph is clipped with the position of the target node in the to-be-searched graph as the center to obtain a clipped graph corresponding to the target node; wherein the clipped graph is a subgraph of the to-be-searched graph, and the target node corresponds to the clipped graph one-to-one; The cropped atlas corresponding to each target node is spliced ​​to obtain the target atlas.

6. The method according to any one of claims 1 to 5, wherein The determining, from the target graph, reply information corresponding to the question information includes: Determining semantic information of the vocabulary units represented by each node in the target graph; According to the semantic information of the vocabulary units represented by each node in the target graph, semantic splicing processing is performed on the vocabulary units represented by each node in the target graph to obtain reply information corresponding to the question information.

7. A data retrieval device based on human-computer interaction, comprising: An acquisition unit is used to acquire the user's question information, the acquisition unit includes a segmentation module and a graph determination module, the graph determination module includes a part-of-speech determination submodule and a graph determination submodule, wherein the segmentation module is used to segment the question information to obtain the vocabulary units in the question information; the part-of-speech determination submodule is used to determine the part-of-speech information of the vocabulary units in the question information; the graph determination submodule is used to determine the first weight of the vocabulary units in the question information based on the part-of-speech information of the vocabulary units in the question information and a preset first association relationship; wherein the first weight represents the importance of the vocabulary units, and the preset first association relationship represents the association relationship between the part-of-speech information and the weight; according to the first weight of the vocabulary units in the question information, a graph to be retrieved is determined from a preset knowledge graph; wherein the preset knowledge graph includes multiple nodes, each node represents a vocabulary unit, the graph to be retrieved is a subgraph in the preset knowledge graph, and the graph to be retrieved represents the question information and information related to the question information; The clipping unit includes a type determination module, a weight determination module and a target determination module, wherein the type determination module is used to determine that the vocabulary type to which the vocabulary unit represented by the node in the to-be-retrieved graph belongs is the to-be-retrieved type; wherein the vocabulary type represents the meaning of the vocabulary unit; the weight determination module is used to determine the second weight corresponding to the to-be-retrieved type according to a preset second association relationship; wherein the preset second association relationship represents the association relationship between the vocabulary type and the second weight, and the second weight represents the importance of the vocabulary type; the target determination module is used to clip the to-be-retrieved graph according to the second weight corresponding to the to-be-retrieved type to obtain a target graph; A reply unit is used to determine reply information corresponding to the question information from the target map and send the reply information to the user.

8. The device according to claim 7, wherein The graph determination submodule is specifically used to: Determining a target vocabulary from the question information according to a first weight of the vocabulary unit in the question information; wherein the target vocabulary is a key vocabulary unit in the question information; According to the target vocabulary, the graph to be searched is determined from a preset knowledge graph.

9. The device according to claim 7, wherein The target determination module includes: A target determination submodule, configured to determine a target type from the types to be retrieved according to a second weight corresponding to the types to be retrieved; wherein the target type is a key vocabulary type in the types to be retrieved; The cropping submodule is used to crop the to-be-retrieved atlas according to the target type to obtain the target atlas.

10. The device according to claim 9, wherein The cutting submodule is specifically used for: Determine the node in the to-be-searched graph where the vocabulary unit belonging to the target type is located as the target node; According to the position of the target node in the to-be-searched graph, the to-be-searched graph is cropped to obtain the target graph.

11. The device according to claim 10, wherein The cutting submodule is specifically used for: According to a preset clipping range, the to-be-searched graph is clipped with the position of the target node in the to-be-searched graph as the center to obtain a clipped graph corresponding to the target node; wherein the clipped graph is a subgraph of the to-be-searched graph, and the target node corresponds to the clipped graph one-to-one; The cropped atlas corresponding to each target node is spliced ​​to obtain the target atlas.

12. The device according to any one of claims 7 to 11, wherein: The reply unit includes: A semantic determination module, configured to determine the semantic information of the vocabulary unit represented by each node in the target graph; The reply generation module is used to perform semantic splicing processing on the vocabulary units represented by each node in the target graph according to the semantic information of the vocabulary units represented by each node in the target graph to obtain reply information corresponding to the question information.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 6.

15. A computer program product, wherein The invention comprises a computer program, which implements the steps of the method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images