Search method and device, computer device and storage medium

Abstract

The present disclosure provides a search method and device, computer equipment and a storage medium. The method comprises: determining the relevant information of the candidate search words matched with the to-be-searched word in a preset database, wherein the to-be-searched word belongs to the to-be-searched text; determining the adaptation value of the to-be-searched word corresponding to each first search mode and the association degree value of the to-be-searched word corresponding to the target technical field according to the relevant information; generating the first search result corresponding to the to-be-searched word according to the adaptation value; determining the second search mode according to the adaptation value and the association degree value; and generating the second search result corresponding to the to-be-searched text based on the second search mode. Through the implementation of the method of the present disclosure, various suitable search modes can be reasonably called based on the relevant information of the candidate search words, thereby greatly improving the richness and diversity of the obtained search results, and further improving the user search experience.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically to a search method, apparatus, computer device, and storage medium. Background Technology

[0002] With the rapid development of information technology, knowledge base applications and management systems have become important tools for academic research and technological development. Therefore, many companies have developed knowledge service platforms for mining. These platforms store a large number of research reports, technical documents, and data, providing researchers with a convenient resource-sharing and knowledge management platform.

[0003] The knowledge base management system contains a large number of original research results and technical materials, and provides corresponding results through various technologies such as text search, graph search, targeted question answering, and large models.

[0004] In related technologies, system users often cannot obtain the accurate results they want when searching, which affects the user search experience. Summary of the Invention

[0005] This disclosure aims to at least partially address one of the technical problems in the related art.

[0006] Therefore, the purpose of this disclosure is to propose a search method, apparatus, computer device, and storage medium that can reasonably invoke various suitable search methods based on relevant information of candidate search terms, thereby greatly improving the richness and diversity of the obtained search results and thus enhancing the user search experience.

[0007] To achieve the above objectives, the search method proposed in the first aspect of this disclosure includes:

[0008] Determine relevant information of candidate search terms that match the search term in a preset database, wherein the search term belongs to the text to be searched;

[0009] Based on the relevant information, determine the matching value between the search term and each first search method, as well as the correlation value between the search term and the target technology field;

[0010] Based on the adaptation value, a first search result corresponding to the search term is generated;

[0011] The second search method is determined based on the fit value and the correlation value;

[0012] Based on the second search method, a second search result corresponding to the text to be searched is generated.

[0013] To achieve the above objectives, the search apparatus proposed in the second aspect of this disclosure includes:

[0014] The first determining module is used to determine relevant information of candidate search terms that match the search term in a preset database, wherein the search term belongs to the text to be searched;

[0015] The second determining module is used to determine, based on the relevant information, the matching value between the search term and each first search method, and the degree of association between the search term and the target technical field.

[0016] The first generation module is used to generate a first search result corresponding to the search term based on the adaptation value.

[0017] The third determining module is used to determine the second search method based on the adaptation value and the correlation degree value;

[0018] The second generation module is used to generate a second search result corresponding to the text to be searched, based on the second search method.

[0019] The computer device proposed in the third aspect of this disclosure includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the search method proposed in the first aspect of this disclosure.

[0020] A fourth aspect of this disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the search method as described in the first aspect of this disclosure.

[0021] A fifth aspect of this disclosure provides a computer program product in which, when instructions in the computer program product are executed by a processor, a search method as described in a first aspect of this disclosure is performed.

[0022] The search method, apparatus, computer equipment, and storage medium disclosed herein determine relevant information of candidate search terms matching the search term in a preset database, wherein the search term belongs to the text to be searched; based on the relevant information, determine the fit value between the search term and each first search method, as well as the relevance value between the search term and the target technical field; generate a first search result corresponding to the search term based on the fit value; determine a second search method based on the fit value and the relevance value; and generate a second search result corresponding to the text to be searched based on the second search method. Therefore, it can reasonably invoke various suitable search methods based on the relevant information of the candidate search terms, thereby greatly improving the richness and diversity of the obtained search results and thus enhancing the user search experience.

[0023] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0025] Figure 1 This is a schematic flowchart of a search method proposed in an embodiment of this disclosure;

[0026] Figure 2 This is a schematic flowchart of a search method proposed in another embodiment of this disclosure;

[0027] Figure 3 This is a schematic diagram of the search process proposed in this disclosure;

[0028] Figure 4 This is a schematic diagram of the structure of a search device proposed in an embodiment of this disclosure;

[0029] Figure 5 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0030] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are used only to explain this disclosure, and should not be construed as limiting this disclosure. Rather, embodiments of this disclosure include all variations, modifications, and equivalents falling within the spirit and scope of the appended claims.

[0031] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, data stored, data displayed, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0032] Figure 1 This is a schematic flowchart of a search method proposed in one embodiment of this disclosure.

[0033] It should be noted that the execution subject of the search method in this embodiment is a search device, which can be implemented by software and / or hardware. The device can be configured in a computer device, which may include, but is not limited to, a terminal, a server, etc., such as a mobile phone, a PDA, etc.

[0034] like Figure 1 As shown, the search method includes:

[0035] S101: Determine the relevant information of candidate search terms that match the search term in the preset database, wherein the search term belongs to the text to be searched.

[0036] The pre-set database refers to a database established after statistical analysis of user search records. This database may include multiple candidate search terms and the analysis results data corresponding to each candidate search term.

[0037] The term to be searched can be any word involved in this search process.

[0038] Candidate search terms can refer to search terms stored in a preset database.

[0039] The relevant information can be used to indicate the relevant information of the candidate search term in the preset database, such as search frequency, lexical features, etc., without limitation.

[0040] The text to be searched refers to the text that needs to be searched in this instance. This text may contain one or more of the aforementioned search terms.

[0041] In this embodiment of the present disclosure, when determining the relevant information of candidate search terms that match the term to be searched in the preset database, the candidate search terms that are the same as the term to be searched in the preset database may be used as the target search terms, and then the relevant information associated with the target search terms may be determined. Alternatively, the candidate search terms that have the same or similar meaning as the term to be searched in the preset database may be used as the target search terms, and then the relevant information associated with the target search terms may be determined. There are no restrictions on this.

[0042] S102: Based on the relevant information, determine the matching value between the search term and each first search method, as well as the correlation value between the search term and the target technical field.

[0043] The first search method can be a search method that points to the search terms, such as graph search, targeted question answering, large model, etc., and there are no restrictions on this.

[0044] The fit value can be used to indicate whether the corresponding first search method is applicable to the above search term.

[0045] The target technical field can refer to the technical field involved in the preset database, such as the field of coal knowledge, and there are no restrictions on this.

[0046] Among them, the correlation degree value (V) proThe value can be used to quantify the level of expertise of a search term in a target technical field. A higher value indicates greater expertise and non-general terminology.

[0047] Optionally, in some embodiments, when determining the fit value between the search term and each first search method based on relevant information, the following steps can be taken: First, second, third, fourth, fifth, and sixth parameters of the search term are determined based on relevant information. The first parameter indicates whether the search term is a word in a professional knowledge graph within a preset database; the second parameter indicates whether the search term is a word in a professional knowledge graph library within the preset database; the third parameter indicates the quantity of knowledge associated with the search term in the professional knowledge graph library; the fourth parameter indicates whether the search term is a word in a graph attribute within the professional knowledge graph library; the fifth parameter indicates the quantity of attribute-related knowledge associated with the search term in the professional knowledge graph library; and the sixth parameter indicates the historical search frequency of the search term in the preset database. Based on the first, second, third, fourth, fifth, and sixth parameters, a first fit value corresponding to the graph search method is determined, where the graph search method belongs to multiple first search methods. Therefore, multiple parameters can be combined to achieve quantitative analysis of the fit between the search term and the graph search method, thereby effectively improving the reliability and practicality of the obtained first fit value.

[0048] For example, among them,

[0049] The first parameter (Is_graph) is used to indicate whether the search term is a term in the professional knowledge graph in the preset database. It is 1 if yes and 0 if no. The knowledge service platform will maintain a coal professional knowledge graph.

[0050] The second parameter (Is_node) indicates whether the search term is a term in the pre-defined professional knowledge graph library; 1 indicates yes, 0 indicates no. The knowledge service platform maintains a coal professional knowledge graph library, recording graph information.

[0051] The third parameter (Node_value) is used to indicate the number of knowledge associated with the search term in the professional knowledge graph library. The number of knowledge associated with the node of the term in the graph library is counted x, and its In(x+1) value is stored. x is an integer with a minimum value of 0, so In(x+1)>=0;

[0052] The fourth parameter (Is_attribute) indicates whether the search term is a word in the graph attribute of the professional knowledge graph library; 1 indicates yes, and 0 indicates no.

[0053] The fifth parameter (Attribute_value) is used to indicate the quantity of attribute-related knowledge of the search term in the professional knowledge graph library. The quantity x of attribute-related knowledge of the term in the graph library is counted and its In(x+1) value is stored. x is an integer with a minimum value of 0, so In(x+1)>=0;

[0054] The sixth parameter (Search_number) is used to indicate the historical search frequency of the term in the preset database, recording the number of times the term has been searched.

[0055] Among them, the first adaptation value (V) graph This can be used to quantify the degree of fit between the search term and the graph search method.

[0056] Optionally, in some embodiments, when determining the fit value between the search term and each first search method based on relevant information, the following steps can be taken: First, determine the seventh, eighth, and ninth parameters of the search term based on relevant information. The seventh parameter indicates whether the search term is a word in a pre-defined database of professional knowledge-oriented question-and-answer resources. The eighth parameter indicates the quantity of knowledge associated with the search term in the professional knowledge-oriented question-and-answer resources. The ninth parameter indicates whether the search term is an identifier in a pre-defined database of large model vectors. Second, determine the tenth parameter based on search requirement information. The tenth parameter indicates the importance of the large model search method, which belongs to multiple first search methods. Third, determine the second fit value between the search term and the targeted question-and-answer method based on the sixth, seventh, eighth, ninth, and tenth parameters. The targeted question-and-answer method belongs to multiple first search methods. Therefore, multiple parameters can be combined to achieve quantitative analysis of the fit between the search term and the targeted question-and-answer method, thereby effectively improving the reliability and practicality of the obtained second fit value.

[0057] For example, among them,

[0058] The seventh parameter (Is_answer) indicates whether the search term is a word in the pre-defined professional knowledge-oriented question and answer database. It is 1 if yes and 0 if no. The knowledge service platform maintains a coal professional knowledge-oriented question and answer database.

[0059] The eighth parameter (Answer_value) is used to indicate the number of related knowledge items for the search term in the professional targeted question and answer database. The number of related knowledge items x in the targeted question and answer database is counted and its In(x) value is stored. x is an integer with a minimum value of 1, so In(x)>=0;

[0060] The ninth parameter (Is_vector) is used to indicate whether the search term is an identifier in the large model vector library of the preset database. It is 1 if yes and 0 if no. The knowledge service platform introduces a self-built large model, which has a vector library. Is_vector determines whether the term has been trained by the large model using vectors.

[0061] The tenth parameter (p) represents the importance of the large model search. It can be set to a value of [0,1] according to the actual needs of the system. For example, the current mining knowledge service platform sets this value to 0.01 because coal knowledge is relatively specialized, and targeted question answering is more accurate than general question answering based on the large model.

[0062] Among them, the second adaptation value (V) answer This can be used to quantify the degree of fit between the search term and the targeted question-and-answer method.

[0063] Optionally, in some embodiments, when determining the fit value between the search term and each first search method based on relevant information, a third fit value between the search term and the large model search method can also be determined based on the sixth, seventh, eighth, ninth, and tenth parameters. This allows for the quantitative analysis of the fit between the search term and the large model search method by combining multiple parameters, thereby effectively improving the reliability and practicality of the obtained third fit value.

[0064] Among them, the third adaptation value (V) vecter This can be used to quantify the degree of fit between the search term and the search method of a large model.

[0065] Optionally, in some embodiments, the correlation value between the search term and the target technical field is determined based on the following method: Based on relevant information, the eleventh, twelfth, thirteenth, fourteenth, and fifteenth parameters of the search term are determined. The eleventh parameter indicates whether the search term is a word in a pre-defined database of professional knowledge tags; the twelfth parameter indicates the quantity of knowledge identified by the search term in the professional knowledge tag library; the thirteenth parameter indicates whether the search term is a word in a pre-defined database of professional knowledge directories; the fourteenth parameter indicates the quantity of directory knowledge in the professional knowledge directory; and the fifteenth parameter indicates the level of the directory to which the search term belongs in the professional knowledge directory. Based on the sixth, eleventh, twelfth, thirteenth, fourteenth, and fifteenth parameters, the correlation value between the search term and the target technical field is determined. Therefore, combining multiple parameters can effectively improve the accuracy of the obtained correlation value.

[0066] For example, among them,

[0067] The eleventh parameter (Is_label) indicates whether the search term is a term in the preset professional knowledge tag library in the database; 1 indicates yes, 0 indicates no. The knowledge service platform maintains a coal professional knowledge tag library to distinguish the knowledge domain to which the knowledge belongs.

[0068] The twelfth parameter (Label_value) is used to indicate the number of knowledge items identified by the search term in the professional knowledge tag library. The number of knowledge items identified by the term in the tag library is counted x, and its In(x) value is stored. Since x is an integer with a minimum value of 1, In(x) >= 0.

[0069] The thirteenth parameter (Is_contents) indicates whether the search term is a term in the preset professional knowledge directory library. It is 1 if yes and 0 if no. The knowledge service platform maintains a coal professional knowledge directory library to store the terms used in the knowledge classification directory, which is used to classify and classify coal knowledge.

[0070] The fourteenth parameter (Contents_value) is used to indicate the number of directory knowledge items for the search term in the professional knowledge directory. The number of directory knowledge items for this term in the directory is counted x, and its In(x) value is stored. Since there are no empty directories, x is an integer with a minimum value of 1, so In(x) >= 0.

[0071] The fifteenth parameter (Contents_level) is used to indicate the level information of the directory to which the search term belongs in the professional knowledge directory. It records the level of the directory to which the term belongs. If it is the root directory, the value is recorded as 0, the second-level directory is recorded as 1, and so on.

[0072] S103: Generate the first search result corresponding to the search term based on the adaptation value.

[0073] In this embodiment of the disclosure, when generating the first search result corresponding to the search term based on the adaptation value, it may be possible to determine the maximum value of multiple adaptation values ​​between different first search methods and the search term, and then generate the first search result corresponding to the search term based on the first search method corresponding to the maximum value. Alternatively, it may be possible to generate the first search result corresponding to the search term based on the adaptation value using any other possible method, without any limitation.

[0074] Optionally, in some embodiments, when generating the first search result corresponding to the search term based on the adaptation value, at least one of the following is included: when the first adaptation value is greater than or equal to a first preset threshold, processing the search term based on a graph search method to obtain the first search result; when the second adaptation value is greater than or equal to a second preset threshold, processing the search term based on a targeted question-and-answer method to obtain the first search result; determining the maximum value between the second adaptation value and the second preset threshold, and when the third adaptation value is greater than or equal to the maximum value, processing the search term based on a large model search method to obtain the first search result. Therefore, the adaptation can be guaranteed when executing the first search method based on the preset threshold, thereby effectively improving the practicality of the obtained first search result.

[0075] The specific values ​​of the first preset threshold and the second preset threshold can be flexibly configured according to the application scenario, and there are no restrictions on them.

[0076] S104: Determine the second search method based on the fit value and the relevance value.

[0077] The second search method can be a search method that points to the text to be searched, such as word segmentation search and string matching search, and there are no restrictions on this.

[0078] In this embodiment of the disclosure, when determining the second search method based on the fit value and the correlation value, the fit value and the correlation value may be input into a pre-trained machine learning model to determine the fit second search method, or the second search method may be determined based on a combination of numerical and graphical methods, without limitation.

[0079] In this embodiment of the disclosure, when the second search method is determined based on the adaptation value and the degree of association value, a reliable execution basis can be provided for the subsequent generation of the second search result.

[0080] S105: Based on the second search method, generate a second search result corresponding to the text to be searched.

[0081] The second search result can refer to the result obtained after searching the text based on the second search method.

[0082] In this embodiment, relevant information of candidate search terms matching the search term in a preset database is determined, where the search term belongs to the text to be searched. Based on the relevant information, the adaptation value corresponding to each first search method and the relevance value between the search term and the target technical field are determined. Based on the adaptation value, a first search result corresponding to the search term is generated. Based on the adaptation value and the relevance value, a second search method is determined. Based on the second search method, a second search result corresponding to the text to be searched is generated. Therefore, various suitable search methods can be reasonably invoked based on the relevant information of the candidate search terms, thereby greatly improving the richness and diversity of the obtained search results and enhancing the user search experience.

[0083] Figure 2 This is a schematic flowchart of a search method proposed in another embodiment of this disclosure.

[0084] like Figure 2 As shown, the search method includes:

[0085] S201: Determine the relevant information of candidate search terms that match the search term in the preset database, wherein the search term belongs to the text to be searched.

[0086] S202: Based on the relevant information, determine the adaptation value of the search term to each first search method, and the degree of association between the search term and the target technical field. The adaptation value includes: the first adaptation value corresponding to the graph search method, the second adaptation value corresponding to the targeted question answering method, and the third adaptation value corresponding to the large model search method.

[0087] S203: Generate the first search result corresponding to the search term based on the adaptation value.

[0088] The descriptions of S201-S203 can be found in the above embodiments, and will not be repeated here.

[0089] S204: Evaluate the importance of the search term in the knowledge graph to obtain a first evaluation value.

[0090] The first evaluation value can be used to indicate the importance of the search term in the knowledge graph.

[0091] For example, in this embodiment of the disclosure, when evaluating the importance of the search term in the knowledge graph to obtain a first evaluation value, the TF*IDF value of a random text associated with the term's graph node can be calculated as the first evaluation value, denoted as G. TF*IDFTF-IDF (Term Frequency–Inverse Document Frequency) is a commonly used weighting technique in information retrieval and text mining. TF-IDF is a statistical method used to evaluate the importance of a term to a document within a document set or corpus. A term's importance increases proportionally to its frequency of occurrence in a document, but decreases inversely proportionally to its frequency of occurrence in the corpus. Various forms of TF-IDF weighting are frequently used by search engines as a measure or ranking of the relevance between documents and user queries.

[0092] S205: Evaluate the importance of the search term in the knowledge-oriented question-and-answer database to obtain a second evaluation value.

[0093] The second evaluation value can be used to indicate the importance of the search term in a knowledge-oriented question-and-answer database.

[0094] For example, in this embodiment of the disclosure, when evaluating the importance of the search term in the specialized knowledge-oriented question-and-answer database to obtain a second evaluation value, the TF*IDF value of the associated specialized question-and-answer text of the term can be calculated as the second evaluation value, denoted as A. TF*IDF .

[0095] S206: Determine the first product of the first fit value and the first evaluation value, the second product of the second fit value and the second evaluation value, and the third product of the tenth parameter and the third fit value.

[0096] S207: Based on the relevance value, the first product value, the second product value, and the third product value, calculate and determine the third evaluation value of the search term, wherein the third evaluation value is used to quantitatively evaluate whether the search term needs to be searched.

[0097] For example, in the embodiments of this disclosure, when calculating and determining the third evaluation value of the search term based on the relevance value, the first product value, the second product value, and the third product value, the relevance value, the first product value, the second product value, and the third product value may be input into a pre-trained machine learning model to obtain the corresponding third evaluation value. Alternatively, the relevance value, the first product value, the second product value, and the third product value may be processed by a third-party device to determine the third evaluation value of the search term. There are no limitations on this.

[0098] S208: Determine the first sum of the third evaluation values ​​corresponding to the search term in the text to be searched.

[0099] The first sum can be used to comprehensively indicate whether a text search is needed in the text to be searched.

[0100] In other words, in this embodiment of the present disclosure, after determining the third evaluation value corresponding to each search term contained in the text to be searched, the first sum of the third evaluation values ​​corresponding to all search terms in the text to be searched can be determined, thereby achieving the [further details regarding the determination of the third evaluation value].

[0101] S209: Determine the second search method based on the first sum.

[0102] In this embodiment of the disclosure, when the first sum is less than zero, it can be determined that the text to be searched is not suitable for text search.

[0103] Optionally, in some embodiments, when determining the second search method based on the first sum, the similarity between the search term and each candidate search term in a preset database can be determined when the first sum is greater than zero; when the similarity is greater than or equal to a third preset threshold, the corresponding candidate search term is determined as a similar search term to the search term; a second sum is determined to show the degree of association between the search term and multiple similar search terms and the target technical field; the mean of the second sum corresponding to at least one search term in the search text is determined; when the mean is greater than or equal to a fourth preset threshold, string matching search is determined as the second search method; when the mean is less than the fourth preset threshold, word segmentation search is determined as the second search method. This ensures the applicability of the determined second search method to the text to be searched.

[0104] The specific values ​​of the third and fourth preset thresholds can be flexibly configured according to the application scenario, and there are no restrictions on them.

[0105] In this embodiment of the disclosure, when determining the similarity between the search term and each candidate search term in the preset database, the cosine similarity between the search term and each candidate search term in the preset database may be determined.

[0106] In other words, this embodiment of the disclosure can assess the importance of the search term in the professional knowledge graph to obtain a first assessment value; assess the importance of the search term in the professional knowledge-oriented question-and-answer database to obtain a second assessment value; determine the first product of the first fit value and the first assessment value, the second product of the second fit value and the second assessment value, and the third product of the tenth parameter and the third fit value; calculate and determine the third assessment value of the search term based on the relevance value, the first product value, the second product value, and the third product value, wherein the third assessment value is used to quantitatively assess whether the search term needs to be searched via text; determine the first sum of the third assessment values ​​corresponding to the search term in the search text; and determine the second search method based on the first sum. Therefore, a comprehensive assessment of whether the search text is suitable for text search can be achieved by combining the first sum of the third assessment values ​​corresponding to the search term in the search text, ensuring the reliability of the obtained second search method.

[0107] S210: Based on the second search method, generate a second search result corresponding to the text to be searched.

[0108] For a detailed description of S210, please refer to the above embodiments, which will not be repeated here.

[0109] In this embodiment, a first evaluation value is obtained by assessing the importance of the search term in the professional knowledge graph; a second evaluation value is obtained by assessing the importance of the search term in the professional knowledge-oriented question-and-answer database; a first product value of the first fit value and the first evaluation value, a second product value of the second fit value and the second evaluation value, and a third product value of the tenth parameter and the third fit value are determined; based on the relevance value, the first product value, the second product value, and the third product value, a third evaluation value of the search term is calculated and determined, wherein the third evaluation value is used to quantitatively assess whether the search term needs to be searched via text search; a first sum value of the third evaluation values ​​corresponding to the search term in the search text is determined; and a second search method is determined based on the first sum value. Therefore, a comprehensive assessment of whether the search text is suitable for text search can be achieved by combining the first sum value of the third evaluation values ​​corresponding to the search term in the search text, ensuring the reliability of the obtained second search method.

[0110] Based on the above embodiments, this disclosure can achieve knowledge retrieval based on the following steps:

[0111] I. Establish a word frequency search database (i.e., the aforementioned preset database)

[0112] The knowledge service platform is an internal knowledge base platform used by the company, with a user base designed to be in the thousands, which is moderate. Therefore, this method can utilize a suitable resource statistics platform to track user search records. Each user's search terms or sentences are recorded, with sentences broken down into words. These words are then stored in a database table, storing the following information:

[0113] 1. Word name: The name of the stored word.

[0114] 2. Search_number: The search frequency of the term, recording the number of times the term has been searched.

[0115] 3. Is_label: Whether the term is in the coal professional knowledge tag library; 1 for yes, 0 for no. The knowledge service platform maintains a coal professional knowledge tag library to distinguish the knowledge domain to which the knowledge belongs.

[0116] 4. Label_value: Counts the number of knowledge items identified by this term in the tag library, x, and stores the value of In(x). Since x is an integer with a minimum value of 1, In(x) >= 0.

[0117] 5. Is_contents: Whether it is a term in the coal professional knowledge catalog. 1 if yes, 0 if no. The knowledge service platform maintains a coal professional knowledge catalog, which stores the terms used in the knowledge classification catalog to classify and classify coal knowledge.

[0118] 6. Contents_value: Counts the number of terms in the directory, x, and stores the value of In(x). Since there are no empty directories, x is an integer with a minimum value of 1, so In(x) >= 0.

[0119] 7. Contents_level: Records the directory level to which the word belongs. If it is the root directory, the value is 0; if it is a second-level directory, the value is 1, and so on.

[0120] 8. Is_graph: Is it a term in the coal knowledge graph? 1 if yes, 0 if no. The knowledge service platform maintains a coal knowledge graph.

[0121] 9. Is_node: Whether it is a word in the graph node; 1 for yes, 0 for no. The knowledge service platform maintains a coal professional knowledge graph database to record graph information.

[0122] 10. Node_value: The number of knowledge associated with this word node in the statistical graph library, x. It stores the value of In(x+1), where x is an integer with a minimum value of 0, so In(x+1)>=0.

[0123] 11. Is_attribute: Whether it is a word in the graph attributes; 1 if yes, 0 if no.

[0124] 12. Attribute_value, the number of knowledge related to the attribute of this word in the statistical graph library, x, stores the value of In(x+1), where x is an integer with a minimum value of 0, so In(x+1)>=0.

[0125] 13. Is_answer: Is it a word in the coal industry knowledge-specific question and answer database? 1 for yes, 0 for no. The knowledge service platform maintains a coal industry knowledge-specific question and answer database.

[0126] 14. Answer_value: Counts the number of related knowledge points x in the targeted question-and-answer database and stores the value of In(x). x is an integer with a minimum value of 1, so In(x) >= 0.

[0127] 15. Is_vector: Whether it is an identifier in the large model vector library. It is 1 if yes, and 0 if no. The knowledge service platform introduces a self-built large model, which has a vector library. Is_vector determines whether the word has been trained by the large model through vector training.

[0128] II. Search Process

[0129] like Figure 3 As shown, Figure 3 This is a schematic diagram of the search process proposed in this disclosure.

[0130] III. Algorithm

[0131] When the search term enters the search judgment module

[0132] 1. Determine if a spectral search is needed using the following formula:

[0133]

[0134] Set a threshold a1, when V graph When the threshold is greater than or equal to a1, the module will enter the spectrum search. This threshold is set according to the actual use of the system. For example, in actual use, the threshold a is set to 0.12.

[0135] Simultaneously, calculate the TF*IDF value of a random text associated with this word graph node, denoted as G. TF*IDF .

[0136] TF-IDF (Term Frequency–Inverse Document Frequency) is a commonly used weighting technique in information retrieval and text mining. TF-IDF is a statistical method used to evaluate the importance of a term to a document within a document set or corpus. A term's importance increases proportionally to its frequency of occurrence in a document, but decreases inversely proportionally to its frequency of occurrence in the corpus. Various forms of TF-IDF weighting are frequently used by search engines as a measure or ranking of the relevance between documents and user queries.

[0137] 2. To determine whether a question is targeted or not, use the following formula:

[0138]

[0139] Where p is a parameter representing the importance of the large model search, and is set to a value of [0,1] according to the actual needs of the system. For example, the current mining knowledge service platform sets this value to 0.01 because coal knowledge is relatively specialized, and targeted question answering is more accurate than general question answering of large models.

[0140] Here, a threshold a2 is set, when V answer When the threshold is greater than or equal to a2, the module will enter a targeted search. This threshold is set according to the actual usage of the system. For example, in actual use, the threshold a is set to 0.2.

[0141] Simultaneously, calculate the TF*IDF value of the word-related targeted question-and-answer text, denoted as A. TF*IDF .

[0142] 3. Determine if the solution is based on a large-scale model using the following formula:

[0143]

[0144] When V answer Existence, V vecter ≥V answer ; or V answer V does not exist. vecter When a = a2, the module will enter the large model search.

[0145] At the same time, directly take the p value.

[0146] 4. Calculate V pro (i.e., the correlation level value mentioned above):

[0147]

[0148] p1 is a parameter of [0,1] used to adjust the influence of directory depth. It is set according to the actual system situation, for example, the current system is set to 0.5.

[0149] This value is used to determine the level of expertise of a search term in the coal industry. The higher the value, the more specialized the search term is. It is not a general term.

[0150] 5. Based on V graph *G TF*IDF V answer *A TF*IDF V vecter *p calculates the value of |V|.

[0151]

[0152] When |V|>=0, the text search process begins; when |V|<0, the text search process does not begin.

[0153] 6. The text search module determines the type of text search. There are two ways of text search on the knowledge service platform, namely tokenized search and string matching search. Tokenized Search is an information retrieval technology. Its core is to decompose the text content into smaller units (called "lexical units" or "tokens"), and then build an index based on these tokenized units and conduct a search. Compared with traditional string matching search, tokenized search can provide more accurate and relevant search results and is one of the core technologies of modern information retrieval systems. However, since the tokenization of coal-related professional vocabulary requires professionals to sort out the lexical units to be accurate, in many cases, the professional vocabulary results obtained by tokenized search often get a lot of meaningless results that are not what the user wants. In this case, the results obtained by string matching search are more accurate.

[0154] The text search module determines and calculates the cosine similarity between the search text or vocabulary x and the vocabulary n in the database.

[0155] Cosine similarity: Represent the text as a vector and calculate the cosine similarity between two vectors. Cosine Similarity is a method for measuring the cosine value of the angle between two non-zero vectors. It is usually used to compare document similarities. The value of cosine similarity ranges from -1 to 1, where 1 means exactly the same, 0 means dissimilar, and -1 means exactly opposite.

[0156] Here, a parameter α is set. The system uses it to obtain the pre-set similarity value, which is set according to the actual operation of the system. For example, the current value of the platform is 0.5, and then the formula is used to calculate the association degree value V between each similar search term and the term to be searched. pro :

[0157]

[0158] Here, a threshold p2 (i.e., the above-mentioned fourth preset threshold) is set. When the mean value of the second sum values corresponding to all the terms to be searched in the text to be searched >= p2, the text search module selects string matching search. When the mean value of the second sum values corresponding to all the terms to be searched in the text to be searched < p2, the text search module selects tokenized search.

[0159] Figure 4 It is a schematic structural diagram of a search device proposed in an embodiment of the present disclosure.

[0160] As Figure 4 shown, the search device 40 includes:

[0161] A first determination module 401, configured to determine the relevant information of candidate search terms that match the term to be searched in a preset database, where the term to be searched belongs to the text to be searched;

[0162] The second determining module 402 is used to determine, based on relevant information, the matching value between the search term and each first search method, and the degree of association between the search term and the target technical field.

[0163] The first generation module 403 is used to generate a first search result corresponding to the search term based on the adaptation value;

[0164] The third determining module 404 is used to determine the second search method based on the fit value and the degree of association value;

[0165] The second generation module 405 is used to generate a second search result corresponding to the text to be searched based on the second search method.

[0166] It should be noted that the foregoing explanation of the search method also applies to the search device of this embodiment, and will not be repeated here.

[0167] In this embodiment, relevant information of candidate search terms matching the search term in a preset database is determined, where the search term belongs to the text to be searched. Based on the relevant information, the adaptation value corresponding to each first search method and the relevance value between the search term and the target technical field are determined. Based on the adaptation value, a first search result corresponding to the search term is generated. Based on the adaptation value and the relevance value, a second search method is determined. Based on the second search method, a second search result corresponding to the text to be searched is generated. Therefore, various suitable search methods can be reasonably invoked based on the relevant information of the candidate search terms, thereby greatly improving the richness and diversity of the obtained search results and enhancing the user search experience.

[0168] Figure 5 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. Figure 5 The computer device 12 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0169] like Figure 5 As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and a bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0170] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0171] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0172] Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 5 Not shown; usually referred to as a "hard drive".

[0173] although Figure 5 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disc drive for reading and writing to a removable non-volatile optical disc (e.g., a Compact Disc Read-Only Memory (CD-ROM), a Digital Video Disc Read-Only Memory (DVD-ROM), or other optical media). In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.

[0174] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of this disclosure.

[0175] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable human interaction with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0176] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the search method mentioned in the foregoing embodiments.

[0177] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the search method proposed in the foregoing embodiments of this disclosure.

[0178] To implement the above embodiments, this disclosure also proposes a computer program product that, when the instruction processor in the computer program product is executed, performs the search method as proposed in the foregoing embodiments of this disclosure.

[0179] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this disclosure all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0180] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0181] This disclosure is intended to provide implementation schemes for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0182] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0183] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0184] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0185] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0186] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0187] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0188] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0189] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A search method, characterized in that, include: Determine relevant information of candidate search terms that match the search term in a preset database, wherein the search term belongs to the text to be searched; Based on the relevant information, determine the matching value between the search term and each first search method, as well as the correlation value between the search term and the target technology field; Based on the adaptation value, a first search result corresponding to the search term is generated; The second search method is determined based on the fit value and the correlation value; Based on the second search method, a second search result corresponding to the text to be searched is generated; The step of determining the matching value between the search term and each first search method based on the relevant information includes: Based on the relevant information, a first parameter, a second parameter, a third parameter, a fourth parameter, a fifth parameter, and a sixth parameter are determined for the search term. The first parameter indicates whether the search term is a word in the professional knowledge graph of the preset database; the second parameter indicates whether the search term is a word in the professional knowledge graph library of the preset database; the third parameter indicates the quantity of knowledge associated with the search term in the professional knowledge graph library; the fourth parameter indicates whether the search term is a word in the graph attributes of the professional knowledge graph library; the fifth parameter indicates the quantity of attribute-related knowledge of the search term in the professional knowledge graph library; and the sixth parameter indicates the historical search frequency of the search term in the preset database. Based on the first parameter, the second parameter, the third parameter, the fourth parameter, the fifth parameter, and the sixth parameter, a first matching value is determined for the search term and the graph search method, wherein the graph search method belongs to multiple first search methods; Based on the relevant information, the seventh, eighth, and ninth parameters of the search term are determined. The seventh parameter indicates whether the search term is a word in the professional knowledge-oriented question-and-answer library in the preset database. The eighth parameter indicates the quantity of knowledge associated with the search term in the professional knowledge-oriented question-and-answer library. The ninth parameter indicates whether the search term is an identifier in the large model vector library in the preset database. Based on the search requirement information, a tenth parameter is determined, wherein the tenth parameter is used to indicate the importance of the large model search method, and the large model search method belongs to multiple first search methods; Based on the sixth parameter, the seventh parameter, the eighth parameter, the ninth parameter, and the tenth parameter, a second matching value corresponding to the search term and the targeted question-and-answer method is determined, wherein the targeted question-and-answer method belongs to multiple first search methods; Based on the sixth parameter, the seventh parameter, the eighth parameter, the ninth parameter, and the tenth parameter, a third adaptation value corresponding to the search term and the large model search method is determined; The step of generating a first search result corresponding to the search term based on the adaptation value includes at least one of the following: When the first adaptation value is greater than or equal to the first preset threshold, the search term is processed based on the graph search method to obtain the first search result; When the second adaptation value is greater than or equal to the second preset threshold, the search term is processed based on the targeted question-and-answer method to obtain the first search result; The maximum value between the second adaptation value and the second preset threshold is determined, and when the third adaptation value is greater than or equal to the maximum value, the search term is processed based on the large model search method to obtain the first search result; The step of determining the second search method based on the fit value and the correlation value includes: The importance of the search term in the professional knowledge graph is evaluated to obtain a first evaluation value; The importance of the search term in the professional knowledge-oriented question-and-answer database is evaluated to obtain a second evaluation value; Determine the first product of the first adaptation value and the first evaluation value, the second product of the second adaptation value and the second evaluation value, and the third product of the tenth parameter and the third adaptation value; Based on the correlation value, the first product value, the second product value, and the third product value, a third evaluation value for the search term is calculated and determined, wherein the third evaluation value is used to quantitatively evaluate whether the search term needs to be searched using text search. Determine the first sum value of the third evaluation value corresponding to the search term in the search text; The second search method is determined based on the first sum value.

2. The method as described in claim 1, characterized in that, The correlation value between the search term and the target technical field is determined based on the following method: Based on the aforementioned relevant information, the eleventh, twelfth, thirteenth, fourteenth, and fifteenth parameters of the search term are determined. Specifically, the eleventh parameter indicates whether the search term is a word in the professional knowledge tag library of the preset database; the twelfth parameter indicates the quantity of knowledge identified by the search term in the professional knowledge tag library; the thirteenth parameter indicates whether the search term is a word in the professional knowledge directory library of the preset database; the fourteenth parameter indicates the quantity of directory knowledge of the search term in the professional knowledge directory library; and the fifteenth parameter indicates the level information of the directory to which the search term belongs in the professional knowledge directory library. Based on the sixth parameter, the eleventh parameter, the twelfth parameter, the thirteenth parameter, the fourteenth parameter, and the fifteenth parameter, the correlation value between the search term and the target technical field is determined.

3. The method as described in claim 1, characterized in that, Determining the second search method based on the first sum value includes: When the first sum is greater than zero, the similarity between the term to be searched and each of the candidate search terms in the preset database is determined; When the similarity is greater than or equal to a third preset threshold, the candidate search term is determined to be a similar search term to the term to be searched. Determine a second sum of the correlation values ​​between the search term and the target technical field, corresponding to multiple similar search terms. Determine the mean of the second sum value corresponding to at least one of the search terms in the text to be searched; When the mean is greater than or equal to the fourth preset threshold, string matching search is determined as the second search method; When the mean is less than the fourth preset threshold, word segmentation search is determined as the second search method.

4. A search device, characterized in that, include: The first determining module is used to determine relevant information of candidate search terms that match the search term in a preset database, wherein the search term belongs to the text to be searched; The second determining module is used to determine, based on the relevant information, the matching value between the search term and each first search method, and the degree of association between the search term and the target technical field. The first generation module is used to generate a first search result corresponding to the search term based on the adaptation value. The third determining module is used to determine the second search method based on the adaptation value and the correlation degree value; The second generation module is used to generate a second search result corresponding to the text to be searched, based on the second search method. The second determining module is used to determine a first parameter, a second parameter, a third parameter, a fourth parameter, a fifth parameter, and a sixth parameter of the search term based on the relevant information. The first parameter indicates whether the search term is a word in the professional knowledge graph of the preset database; the second parameter indicates whether the search term is a word in the professional knowledge graph library of the preset database; the third parameter indicates the quantity of knowledge associated with the search term in the professional knowledge graph library; the fourth parameter indicates whether the search term is a word in the graph attributes of the professional knowledge graph library; the fifth parameter indicates the quantity of attribute-related knowledge of the search term in the professional knowledge graph library; and the sixth parameter indicates the historical search frequency of the search term in the preset database. Based on the first parameter, the second parameter, the third parameter, the fourth parameter, the fifth parameter, and the sixth parameter, a first matching value is determined for the search term and the graph search method, wherein the graph search method belongs to multiple first search methods; Based on the relevant information, the seventh, eighth, and ninth parameters of the search term are determined. The seventh parameter indicates whether the search term is a word in the professional knowledge-oriented question-and-answer library in the preset database. The eighth parameter indicates the quantity of knowledge associated with the search term in the professional knowledge-oriented question-and-answer library. The ninth parameter indicates whether the search term is an identifier in the large model vector library in the preset database. Based on the search requirement information, a tenth parameter is determined, wherein the tenth parameter is used to indicate the importance of the large model search method, and the large model search method belongs to multiple first search methods; Based on the sixth parameter, the seventh parameter, the eighth parameter, the ninth parameter, and the tenth parameter, a second matching value corresponding to the search term and the targeted question-and-answer method is determined, wherein the targeted question-and-answer method belongs to multiple first search methods; Based on the sixth parameter, the seventh parameter, the eighth parameter, the ninth parameter, and the tenth parameter, a third adaptation value corresponding to the search term and the large model search method is determined; The first generation module is used to process the search term based on the graph search method to obtain the first search result when the first adaptation value is greater than or equal to the first preset threshold. When the second adaptation value is greater than or equal to the second preset threshold, the search term is processed based on the targeted question-and-answer method to obtain the first search result; The maximum value between the second adaptation value and the second preset threshold is determined, and when the third adaptation value is greater than or equal to the maximum value, the search term is processed based on the large model search method to obtain the first search result; The third determining module is used to evaluate the importance of the search term in the professional knowledge graph to obtain a first evaluation value; The importance of the search term in the professional knowledge-oriented question-and-answer database is evaluated to obtain a second evaluation value; Determine the first product of the first adaptation value and the first evaluation value, the second product of the second adaptation value and the second evaluation value, and the third product of the tenth parameter and the third adaptation value; Based on the correlation value, the first product value, the second product value, and the third product value, a third evaluation value for the search term is calculated and determined, wherein the third evaluation value is used to quantitatively evaluate whether the search term needs to be searched using text search. Determine the first sum value of the third evaluation value corresponding to the search term in the search text; The second search method is determined based on the first sum value.

5. A computer device, characterized in that, include: 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 to enable the at least one processor to perform the method of any one of claims 1-3.

6. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-3.

7. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-3.

Images