CN117591741A - Implement retrieval method, device, electronic equipment and storage medium - Google Patents
Implement retrieval method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117591741A CN117591741A CN202311640721.4A CN202311640721A CN117591741A CN 117591741 A CN117591741 A CN 117591741A CN 202311640721 A CN202311640721 A CN 202311640721A CN 117591741 A CN117591741 A CN 117591741A
- Authority
- CN
- China
- Prior art keywords
- tool
- search
- retrieval
- user
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000003066 decision tree Methods 0.000 claims description 28
- 239000011159 matrix material Substances 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012417 linear regression Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000013138 pruning Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 18
- 230000008569 process Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a tool searching method, a device, electronic equipment and a storage medium. The method comprises the following steps: determining a search element according to input information of a tool user, wherein the search element comprises a search keyword and a search condition; predicting implement use information of the implement user based on the input information; and searching the tool knowledge graph according to the search element, and intervening in search contents according to the tool use information to obtain a tool search result, wherein the tool knowledge graph is generated based on the maintained tool attribute information. According to the technical scheme, the tool knowledge graph is searched, and the predicted tool use information is used for intervening in searching contents, so that the search result which is more accurate and more in line with the requirements and intentions of tool users can be obtained, and the convenience of tool use and the user satisfaction are improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a tool searching method and device, electronic equipment and a storage medium.
Background
With the continuous improvement of living standard, self-service services of various industries are becoming more and more popular, such as going to banking sites or using self-service equipment to finish deposit or withdrawal in daily life. However, the user often does not know the position of the nearby machine, the type of machine and the related functions, and although the user can search by using the map software, the user usually simply obtains the position of the nearby machine, and cannot comprehensively consider the requirement and intention of the user to accurately obtain the proper machine, for example, not all self-service cash dispensers have the function of self-service deposit; for another example, some tools are relatively close to a user, but may not be used by the user in such operation modes as a screen or a keyboard, so that the search result cannot meet the user demand, the convenience of searching and using the tools is affected, and the user experience is relatively poor.
Disclosure of Invention
The invention provides an implement retrieval method, an implement retrieval device, electronic equipment and a storage medium, so that implement retrieval which is more accurate and more in line with the needs and intentions of an implement user is realized, and the convenience of use of the implement and the satisfaction of a user are improved.
In a first aspect, an embodiment of the present invention provides a method for retrieving an implement, including:
determining a search element according to input information of a tool user, wherein the search element comprises a search keyword and a search condition;
predicting implement use information of the implement user based on the input information;
and searching the tool knowledge graph according to the search element, and intervening in search contents according to the tool use information to obtain a tool search result, wherein the tool knowledge graph is generated based on the maintained tool attribute information.
In a second aspect, an embodiment of the present invention provides an implement retrieval device, including:
the input module is used for determining search elements according to input information of a tool user, wherein the search elements comprise search keywords and search conditions;
the prediction module is used for predicting tool use information of the tool user according to the input information;
and the retrieval module is used for retrieving the tool knowledge graph according to the retrieval elements and obtaining tool retrieval results according to the tool use information intervention retrieval content, wherein the tool knowledge graph is generated based on the maintained tool attribute information.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
one or more processors;
a storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the implement method of retrieving an implement as described in the first aspect.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the implement retrieval method of the first aspect.
The embodiment of the invention provides a tool searching method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: determining a search element according to input information of a tool user, wherein the search element comprises a search keyword and a search condition; predicting implement use information of the implement user based on the input information; and searching the tool knowledge graph according to the search element, and intervening in search contents according to the tool use information to obtain a tool search result, wherein the tool knowledge graph is generated based on the maintained tool attribute information. According to the technical scheme, the tool knowledge graph is searched, and the predicted tool use information is used for intervening in searching contents, so that the search result which is more accurate and more in line with the requirements and intentions of tool users can be obtained, and the convenience of tool use and the user satisfaction are improved.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
FIG. 1 is a flowchart of a tool searching method according to a first embodiment of the present invention;
FIG. 2 is a flowchart of a tool searching method according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating a relationship between different tool entities according to a second embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating an implementation of an implement retrieval process according to a second embodiment of the present disclosure;
FIG. 5 is a schematic diagram of an autonomous machine retrieving device according to a second embodiment of the present invention;
fig. 6 is a schematic structural diagram of an implement retrieval device according to a third embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. Furthermore, embodiments of the invention and features of the embodiments may be combined with each other without conflict. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts steps as a sequential process, many of the steps may be implemented in parallel, concurrently, or with other steps. Furthermore, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.
In addition, the technical scheme of the application is used for acquiring, storing, using, processing and the like data, and the data are in accordance with relevant regulations of national laws and regulations.
Example 1
Fig. 1 is a flowchart of a method for searching an implement according to a first embodiment of the present invention, where the embodiment is applicable to a case of searching an implement. The machine tool can refer to any machine which can be used or transacted by a user, such as a self-service cash recycling machine. Typically, the implements are disposed in discrete geographical locations. In particular, the implement retrieval method may be performed by an implement retrieval device, which may be implemented in software and/or hardware and integrated in an electronic device. Further, the electronic device includes, but is not limited to: desktop computers, notebook computers, smart phones, servers, and the like.
As shown in fig. 1, the method specifically includes the following steps:
s110, determining search elements according to input information of a tool user, wherein the search elements comprise search keywords and search conditions.
Specifically, the input information may be input into the electronic device by the tool user in the form of text, voice, instructions, clicking or selecting operations, etc., for indicating the use requirement or intention of the tool user for the tool. The searching element mainly refers to a necessary basis for searching the maintained tool, the searching keyword can be used for specifying the attribute (such as the name of a street where the tool is located, the name of a mechanism where the tool belongs and/or whether the tool is a common tool, etc.) for searching the tool, and the searching condition can be used for specifying the condition (such as whether the distance between the tool and the current position of the tool user is within a specified distance, whether the tool operates in a current period and/or whether the tool has a specified function such as self-service deposit, etc.) for searching the tool.
When the input information of the tool user is obtained, the position information, time information, operation log and the like of the tool user can be recorded, and the position information, the time information, the operation log and the like can be stored in a database as known data, so that the tool retrieval habit of the tool user can be recorded conveniently, and a basis can be provided for optimizing the retrieval result. The operation log is used for recording the usage record of the machine tool by the machine tool user, and comprises search conditions, search keywords, clicking times, clicking positions, page browsing time, page revisiting times and the like. The above information and operation log may be recorded in a structured database.
S120, predicting tool use information of the tool user according to the input information;
specifically, based on the input information, on one hand, the search element can be extracted for searching the machine meeting the requirements of the user of the machine, and the obtained search result is objective; on the other hand, implement use information of the implement user may be predicted, the implement use information including a common implement and a common function of the implement user in the current period, and the like. Compared with the objective search result, the predicted tool use information is more in line with the tool use habit or expectation of the tool user. The predicted tool use information can be utilized to provide a convenient and satisfactory tool search result for a tool user with a higher probability.
And S130, searching the tool knowledge graph according to the search element, and interfering with search contents according to the tool use information to obtain a tool search result, wherein the tool knowledge graph is generated based on the maintained tool attribute information.
In particular, an implement knowledge graph can be understood as a graph-based structured semantic knowledge base that describes entities (different implements) and their relationships in a structured form. The tool knowledge map is generated based on maintained tool attribute information including known tool positions, run times, functions, and/or affiliated mechanisms, etc.
In this embodiment, the searching element is used to search the tools meeting the requirements of the tool users in the tool knowledge graph, and based on this, the searching result can be optimized by using the predicted tool usage information to intervene in the searching content, for example, the searching result is selected, ordered, scored or recommended for the plurality of available tools searched according to the common tools and common functions of the tool users in the current period, so as to provide the tool users with convenient and satisfactory tool searching results.
In one embodiment, the input information includes location information, time information, and an operation log; the operation log includes the following attribute information: search conditions, search keywords, search times (which may reflect the usage habits or preferences of the tool users on the tool or the validity of the search results, etc.), search locations (which may reflect the situations where the tool users have tool searches and use needs, etc.), page browsing times (which may reflect the complexity of the tool users 'search needs and the usefulness of the search results to the tool users, etc.), and page revising times (which may reflect the frequency of tool users' search failures or the non-reference meaning of the search results to the tool users, etc.); the operation log is stored in a structured database.
The first embodiment of the invention provides a tool searching method, which establishes a tool knowledge graph based on maintained tool attribute information; supporting prediction of intention of a tool user, recording operation logs of user searching, browsing and the like, and constructing a prediction model for predicting tool use information through a large number of operation logs; the user search behavior is predicted through the user position and the user operation, the tool knowledge graph is searched according to the input information, the predicted tool use information is used for interfering the search result and returning to the tool user, the requirement of the user on accurately inquiring the tool information is met, the use cost of the user is reduced, and the user experience and satisfaction degree are improved.
Example two
Fig. 2 is a flowchart of an implement searching method according to a second embodiment of the present invention, where the implement searching process is specifically described by optimizing the implement searching process based on the foregoing embodiment. It should be noted that technical details not described in detail in this embodiment may be found in any of the above embodiments.
Specifically, as shown in fig. 2, the method specifically includes the following steps:
s210, determining a search element according to input information of a tool user.
S220, predicting tool use information of a tool user according to the input information.
S230, according to the search elements, a plurality of target RDF triples conforming to the search elements are queried from the tool knowledge graph based on the graph search technology.
S240, calculating the score of each target RDF triplet through the prediction model, sequencing each target RDF triplet according to the score, and generating a machine tool retrieval result according to the sequencing result.
In this embodiment, a resource description framework (Resource Description Framework, RDF) triplet is composed of nodes representing entities, resources, and attributes, and edges representing relationships between entities and attributes. The RDF triples retrieved from the tool indication map can be subjected to secondary screening through the prediction model, the scores of the RDF triples can be calculated, and the RDF triples are ordered according to the scores, so that a convenient and satisfactory tool retrieval result is provided for tool users.
In an embodiment, before retrieving the tool knowledge graph according to the retrieving element, the generating process of the tool knowledge graph includes:
s2310, determining a plurality of entities and a relationship between each entity according to the maintained tool attribute information.
S2320, constructing RDF triples in a bottom-up mode according to a plurality of entities and the relation among the entities.
S2330, storing the RDF triples in a graph database to obtain the tool knowledge graph.
In this embodiment, the tool knowledge graph may be constructed by performing entity analysis and relationship extraction on the maintained tool attribute information. Specifically, the structured data stored in the relational database is taken out, each tool is taken as an entity, and each entity comprises the properties of tool location, affiliated website, tool type, business state, staggered account acceptance line, affiliated first-level division line, remarks and the like, and the relation among each entity is abstracted according to the field properties.
FIG. 3 is a schematic diagram of a relationship between different implement entities according to an embodiment. According to the extracted entity and the relation among the entities, constructing an RDF triplet in a bottom-up mode, wherein the triplet is a representation form of a knowledge graph and can be expressed as follows: g= { E, R, S }, where E represents the set of entities of the knowledge graph, R represents the set of relationships between the entities, and S represents the set of all triples in the knowledge base. And storing the triples in a graph database to form a tool knowledge graph for subsequent retrieval.
In one embodiment, the process of constructing the predictive model includes, prior to predicting implement usage information for the implement user based on the input information:
s2410, generating a sample matrix according to the operation log of the history tool user.
S2420, establishing a decision tree according to the sample matrix.
S2430, constructing and training a prediction model for predicting tool use information according to the decision tree.
In this embodiment, data analysis is performed on the recorded operation log, features such as a place, a search condition, a search keyword, a click frequency, a click position, a page browsing time and the like are extracted, a sample matrix is constructed as attributes of samples, a decision tree is built by using a plurality of sample matrices, and training of a prediction model is completed. A decision tree is a tree structure in which each internal node represents a test on an attribute, each branch represents a test output, and each leaf node represents a class. In machine learning, decision trees may be used as predictive models.
In one embodiment, generating a sample matrix from an operation log of a history tool user includes:
clearing samples of the operation logs of the history tool users, which lack key attribute values, to obtain effective samples, and generating corresponding sample matrixes according to the attribute values of the effective samples;
establishing a decision tree according to the sample matrix, including: and determining a node splitting position based on the variance of the attribute value of each sample matrix corresponding to the retrieval position, and obtaining a decision tree.
In this embodiment, the recorded operation log is subjected to data preprocessing, and samples lacking key attribute values are removed, and the remaining samples are valid samples according to each valid sampleThe attribute values generate a sample matrix. The operation time sequence can be determined according to the sample matrix, the operation time of the user, the browsing time and other contents, the samples can be layered, data cohesion is carried out according to the use places of different users, namely, individuals with strong correlation in each sample matrix are recombined into a new sample set, specifically, users in the near places (search positions) are cohesive into the same subgroup, the whole sample is divided into a plurality of sub-samples, the processed samples are used for training, and the variance of the corresponding attribute (search position) value of each sample matrix is calculated according to the following formula:wherein c i Representing the value of the ith sample matrix above the corresponding attribute, N represents the capacity of the sample. The node splitting position can be determined according to the variance of the attribute values of each sample matrix, so that a decision tree is established.
In one embodiment, constructing and training a predictive model for predicting the implement use information based on the decision tree includes:
performing linear regression on all leaf nodes in the decision tree to construct a linear regression model;
pruning the decision tree to adjust corresponding parameters of the linear regression model to obtain the prediction model.
In this embodiment, linear regression is performed on all leaf nodes in the decision tree, and a linear regression model is constructed, where the linear relation is as follows: y=β 0 +β 1 x 1 +β 2 x 2 +...+β n x n +ε, where y is an observable random variable, x 1 ,...,x n Is an observable dependent variable, ε represents a random variable, also known as error, β 1 ,...,β n Is a regression coefficient. By pruning the decision tree, namely cutting out certain subtrees and nodes from the generated tree, the decision tree model is simplified, the over-fitting phenomenon is reduced, the model parameters are optimized according to continuous updating of the data set in the process, and the optimal prediction model is iterated.
Fig. 4 is a schematic diagram illustrating an implementation of an implement retrieval process according to an embodiment. As shown in fig. 4, input information of a user (i.e., a tool user) is obtained, the input information of the user is preprocessed, on one hand, search elements are extracted and a tool knowledge graph is searched to obtain a search result, on the other hand, search (search) behaviors of the user are recorded according to the input information, a sample matrix (i.e., search features) is extracted by analyzing the user behaviors, the search features are input into an established use behavior model (i.e., a prediction model), and an analysis result (i.e., predicted tool use information) of similar user use conditions is obtained; and then, the search result is interfered by using the user-like use condition analysis result, and a final search result is output.
In an embodiment, an autonomous implement retrieval device may be designed based on the above embodiments. Fig. 5 is a schematic diagram of an autonomous implement retrieval device according to an embodiment. As shown in fig. 5, the autonomous machine searching device mainly comprises four parts, namely a graph calculating unit, an input unit, a behavior predicting unit and an output unit.
The diagram calculation unit can be used for analyzing the maintained tool, abstracting out the entity and the relation according to the maintained tool attribute information, and generating a tool knowledge graph; the input unit can be used for acquiring user information (a user is a machine tool user), preprocessing the input information and recording user use data; the behavior prediction unit is used for training the recorded user operation log, generating a use behavior prediction model (namely a prediction model) and predicting tool use information; the output unit is used for acting the prediction model generated by the behavior prediction unit on the tool knowledge graph generated by the graph calculation unit, intervening the search result and finally outputting the search result to the user.
The input unit is composed of a user information acquirer, an input content preprocessor, and an operation log recorder. The user information acquirer is used for acquiring user information including places, time and the like for use in subsequent processes after a user logs in the system. The input content preprocessor is used for classifying and word-separating the content input by the user, and intelligently identifying the input content to be corresponding to the corresponding tool attribute, so that the subsequent unit can be conveniently used. The operation log recorder is used for acquiring a use record of a user, including search conditions, search keywords, click times, click positions, page browsing time, page revisit times and the like, and recording the use record in the structured database.
The behavior prediction unit is composed of a user behavior data analysis operator, a user behavior relation mining operator, a similar user mining operator and a using behavior model generator. The unit is mainly used for carrying out data analysis on the operation log recorded in the input unit, extracting features such as places, search conditions, search keywords, click times, click positions, page browsing time and the like, constructing a sample matrix as attributes of each sample, establishing a decision tree and completing training of a prediction model.
The user behavior data analysis operator is used for carrying out data preprocessing on the operation log recorded in the input unit, removing samples of which key attributes are missing in the data set, and generating a sample matrix according to the attribute values. And the user behavior relation mining operator determines an operation time sequence according to the sample matrix, the operation time of the user, the browsing time and other contents. And layering the samples by using similar user mining operators, carrying out data cohesion according to the use places of different users, converging users in the nearby places into the same subgroup, and dividing the whole sample into a plurality of sub-samples. Training by using the processed samples by using a behavior model generator, determining node splitting positions by calculating variances of attribute values of a sample matrix, and establishing a decision tree.
The graph calculation unit is used for carrying out entity analysis and relation extraction on the maintained tool information and constructing a tool knowledge graph. The unit is composed of a entity, an attribute extraction operator, an implement knowledge graph construction operator and a knowledge storage. The entity and attribute extraction operator takes out the structured data stored in the relational database, each machine tool is taken as an entity, each entity comprises the attributes of machine tool places, affiliated net points, machine tool types, business states, staggered account acceptance lines, affiliated level division lines, notes and the like, and the relation among each entity is abstracted according to field attributes. And the tool knowledge graph construction operator constructs the entity and the relation among the entities extracted from the former operator in a bottom-up mode to form an RDF triplet, wherein the triplet is a representation form of the knowledge graph. The knowledge memory is used to store the triples in the graph database for subsequent retrieval use.
The output unit is composed of an implement map searching operator and a behavior model predicting intervention operator. The tool map searching operator is used for determining searching elements according to input information and performing polarity searching in a tool knowledge map, the behavior model is used for predicting intervention operators and is used for intervening searching results according to tool use information predicted by the prediction model, and the searching results are output to a user.
According to the tool searching method, the knowledge graph is used for storing tool information and relations among tools, behavior prediction is added in the searching process of a tool user, a query result is accurately returned to the user, searching efficiency is improved, and customer satisfaction is improved; the intention of the tool user can be predicted by analyzing the search or browsing content and the like of the user through the excavation of the similar user; the index map retrieval and the intention prediction are combined, so that the intelligent tool retrieval is realized, the query efficiency and the retrieval accuracy are higher, and the requirements of tool users can be met.
Example III
Fig. 6 is a schematic structural diagram of an implement retrieval device according to a third embodiment of the present invention. As shown in fig. 6, the implement retrieval device provided in this embodiment includes:
an input module 310 for determining a search element according to input information of a tool user, wherein the search element comprises a search keyword and a search condition;
a prediction module 320 configured to predict implement usage information of the implement user based on the input information;
and the retrieving module 330 is configured to retrieve an implement knowledge graph according to the retrieving element, and intervene in the retrieving content according to the implement use information to obtain an implement retrieving result, where the implement knowledge graph is generated based on the maintained implement attribute information.
The implement retrieval device provided by the third embodiment of the invention realizes … through ….
On the basis of the above embodiment, the input information includes location information, time information, and an operation log;
the operation log includes the following attribute information: search conditions, search keywords, search times, search positions, page browsing time and page revisit times;
the operation log is stored in a structured database.
On the basis of the above embodiment, the device further includes:
the generation module is used for generating a sample matrix according to an operation log of a history tool user before predicting tool use information of the tool user according to the input information, wherein the sample matrix is used for representing retrieval characteristics of the history tool user, and the retrieval characteristics correspond to the attribute information;
the establishing module is used for establishing a decision tree according to the sample matrix;
and the construction module is used for constructing and training a prediction model for predicting the tool use information according to the decision tree.
On the basis of the above embodiment, the generating module is specifically configured to:
clearing samples of the operation logs of the history tool users, which lack key attribute values, to obtain effective samples, and generating corresponding sample matrixes according to the attribute values of the effective samples;
the building module is specifically used for:
and determining a node splitting position based on the variance of the attribute value of each sample matrix corresponding to the retrieval position, and obtaining a decision tree.
On the basis of the above embodiment, the building module includes:
the regression unit is used for carrying out linear regression on all leaf nodes in the decision tree so as to construct a linear regression model;
and the pruning unit is used for pruning the decision tree to adjust corresponding parameters of the linear regression model so as to obtain the prediction model.
On the basis of the above embodiment, the device further includes:
the entity extraction module is used for determining a plurality of entities and the relation between each entity according to the maintained tool attribute information before searching the tool knowledge graph according to the search elements, wherein each tool is used as an entity, and the attribute of each entity comprises a tool place, a affiliated website, a tool type, a business state, a staggered account acceptance line, an affiliated first-class line and a remark;
the triplet construction module is used for constructing resource description framework RDF triples in a bottom-up mode according to the entities and the relation among the entities, wherein the RDF triples comprise entity sets, relation sets among the entities and sets of all triples in a knowledge base;
and the map generation module is used for storing the RDF triples in a map database to obtain the tool knowledge map.
On the basis of the above embodiment, the retrieval module 330 includes:
the searching unit is used for inquiring a plurality of target RDF triples conforming to the searching elements from the tool knowledge graph based on a graph searching technology according to the searching elements;
and the intervention unit is used for calculating the score of each target RDF triplet through the prediction model, sequencing each target RDF triplet according to the score and generating an implement retrieval result according to the sequencing result.
The implement searching device provided by the third embodiment of the invention can be used for executing the implement searching method provided by any embodiment, and has corresponding functions and beneficial effects.
Example IV
Fig. 7 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device 10 may also represent various forms of mobile equipment, such as personal digital assistants, cellular telephones, smartphones, user equipment, wearable devices (e.g., helmets, eyeglasses, watches, etc.), and other similar computing equipment. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 7, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks, wireless networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above.
In some embodiments, the methods of the above embodiments may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. One or more steps of the methods described above may be performed when the computer program is loaded into RAM 13 and executed by processor 11. Alternatively, in other embodiments, processor 11 may be configured to perform any of the embodiment methods described above in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device 10, the electronic device 10 having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the electronic device 10. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, 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: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of retrieving an implement, comprising:
determining a search element according to input information of a tool user, wherein the search element comprises a search keyword and a search condition;
predicting implement use information of the implement user based on the input information;
and searching the tool knowledge graph according to the search element, and intervening in search contents according to the tool use information to obtain a tool search result, wherein the tool knowledge graph is generated based on the maintained tool attribute information.
2. The method of claim 1, wherein the input information includes location information, time information, and an operation log;
the operation log includes the following attribute information: search conditions, search keywords, search times, search positions, page browsing time and page revisit times;
the operation log is stored in a structured database.
3. The method of claim 2, further comprising, prior to predicting implement use information for the implement user based on the input information:
generating a sample matrix according to an operation log of a history tool user, wherein the sample matrix is used for representing retrieval characteristics of the history tool user, and the retrieval characteristics correspond to the attribute information;
establishing a decision tree according to the sample matrix;
and constructing and training a prediction model for predicting the tool use information according to the decision tree.
4. The method of claim 3, wherein generating the sample matrix from the operation log of the history tool user comprises:
clearing samples of the operation logs of the history tool users, which lack key attribute values, to obtain effective samples, and generating corresponding sample matrixes according to the attribute values of the effective samples;
establishing a decision tree according to the sample matrix, including:
and determining a node splitting position based on the variance of the attribute value of each sample matrix corresponding to the retrieval position, and obtaining a decision tree.
5. The method of claim 4, wherein constructing and training a predictive model for predicting the implement use information based on the decision tree comprises:
performing linear regression on all leaf nodes in the decision tree to construct a linear regression model;
pruning the decision tree to adjust corresponding parameters of the linear regression model to obtain the prediction model.
6. The method of claim 1, further comprising, prior to retrieving the tool knowledge-graph based on the retrieval element:
determining a plurality of entities and a relation among each entity according to the maintained tool attribute information, wherein each tool is used as an entity, and the attribute of each entity comprises a tool place, a belonging website, a tool type, a business state, a staggered account acceptance line, a belonging level line and notes;
constructing resource description framework RDF triples in a bottom-up mode according to the plurality of entities and the relation among each entity, wherein the RDF triples comprise entity sets, relation sets among the entities and sets of all triples in a knowledge base;
and storing the RDF triples in a graph database to obtain the tool knowledge graph.
7. The method of claim 6, wherein retrieving the tool knowledge graph according to the retrieval element and retrieving content according to the tool use information intervention, obtaining a tool retrieval result, comprises:
inquiring a plurality of target RDF triples conforming to the retrieval elements from the tool knowledge graph based on a graph retrieval technology according to the retrieval elements;
and calculating the score of each target RDF triplet through a prediction model, sequencing each target RDF triplet according to the score, and generating a machine tool retrieval result according to the sequencing result.
8. An implement retrieval device, comprising:
the input module is used for determining search elements according to input information of a tool user, wherein the search elements comprise search keywords and search conditions;
the prediction module is used for predicting tool use information of the tool user according to the input information;
and the retrieval module is used for retrieving the tool knowledge graph according to the retrieval elements and obtaining tool retrieval results according to the tool use information intervention retrieval content, wherein the tool knowledge graph is generated based on the maintained tool attribute information.
9. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the implement retrieval method of any one of claims 1-7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the implement retrieval method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311640721.4A CN117591741A (en) | 2023-12-01 | 2023-12-01 | Implement retrieval method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311640721.4A CN117591741A (en) | 2023-12-01 | 2023-12-01 | Implement retrieval method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117591741A true CN117591741A (en) | 2024-02-23 |
Family
ID=89909755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311640721.4A Pending CN117591741A (en) | 2023-12-01 | 2023-12-01 | Implement retrieval method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117591741A (en) |
-
2023
- 2023-12-01 CN CN202311640721.4A patent/CN117591741A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9171078B2 (en) | Automatic recommendation of vertical search engines | |
| JP2021166109A (en) | Fusion sorting model training method and device, search sorting method and device, electronic device, storage medium, and program | |
| CN114840671A (en) | Dialogue generation method, model training method, device, equipment and medium | |
| CN103309869A (en) | Method and system for recommending display keyword of data object | |
| CN112818230B (en) | Content recommendation method, device, electronic equipment and storage medium | |
| KR20220119745A (en) | Methods for retrieving content, devices, devices and computer-readable storage media | |
| JP2024507902A (en) | Information retrieval methods, devices, electronic devices and storage media | |
| CN113988157A (en) | Semantic retrieval network training method and device, electronic equipment and storage medium | |
| CN113660541A (en) | News video abstract generation method and device | |
| CN113722600B (en) | Data query method, device, equipment and product applied to big data | |
| CN114090877A (en) | Position information recommendation method and device, electronic equipment and storage medium | |
| CN112506864A (en) | File retrieval method and device, electronic equipment and readable storage medium | |
| CN116383340A (en) | Information searching method, device, electronic equipment and storage medium | |
| CN113536156A (en) | Search result ordering method, model construction method, device, equipment and medium | |
| US20230274161A1 (en) | Entity linking method, electronic device, and storage medium | |
| CN114491232B (en) | Information query method and device, electronic equipment and storage medium | |
| CN115329195A (en) | Artificial intelligence-based intention mining method, device, equipment and storage medium | |
| CN117591741A (en) | Implement retrieval method, device, electronic equipment and storage medium | |
| CN113868481A (en) | Component acquisition method and device, electronic equipment and storage medium | |
| CN113407579A (en) | Group query method and device, electronic equipment and readable storage medium | |
| CN113326438A (en) | Information query method and device, electronic equipment and storage medium | |
| CN114528378A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN113722593A (en) | Event data processing method and device, electronic equipment and medium | |
| CN116501841B (en) | Fuzzy query method, system and storage medium for data model | |
| CN115795023B (en) | Document recommendation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |