CN116361546A - Method and device for processing search request, electronic equipment and storage medium - Google Patents

Method and device for processing search request, electronic equipment and storage medium Download PDF

Info

Publication number
CN116361546A
CN116361546A CN202310205936.7A CN202310205936A CN116361546A CN 116361546 A CN116361546 A CN 116361546A CN 202310205936 A CN202310205936 A CN 202310205936A CN 116361546 A CN116361546 A CN 116361546A
Authority
CN
China
Prior art keywords
candidate
operator
search
determining
operators
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
Application number
CN202310205936.7A
Other languages
Chinese (zh)
Inventor
朱致成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Agricultural Bank of China
Original Assignee
Agricultural Bank of China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Agricultural Bank of China filed Critical Agricultural Bank of China
Priority to CN202310205936.7A priority Critical patent/CN116361546A/en
Publication of CN116361546A publication Critical patent/CN116361546A/en
Pending legal-status Critical Current

Links

Images

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
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
    • 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
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • Geometry (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the application discloses a search request processing method, a search request processing device, electronic equipment and a storage medium. Responding to the search request, and determining target search parameters from candidate search parameters corresponding to the search request; determining at least one candidate operator according to the target search parameter; determining candidate operator structures of all candidate operators based on a genetic algorithm, and determining a target search model according to the candidate operator structures of all candidate operators; the candidate operator structure comprises candidate hierarchical structures of candidate operators and candidate fusion modes of output results of the candidate operators on the same layer; searching the data to be searched associated with the search request based on the target search model to obtain recommended data. The embodiment of the application improves the stability and accuracy of search request processing.

Description

Method and device for processing search request, electronic equipment and storage medium
Technical Field
Embodiments of the present application relate to data processing technologies, and in particular, to a method, an apparatus, an electronic device, and a storage medium for processing a search request.
Background
With the development of internet technology, the information volume is rapidly increased, and feedback information obtained by searching in a network is too much to accurately acquire target information. Therefore, how to make targeted recommendations for search content is an important networking technology.
In the prior art, data recommendation takes a calling plug-in as a core, a final recommended data set is obtained by sequentially calling the plug-in, the calling sequence of the plug-in is mainly considered and specified by a professional according to experience, and a final recommended result is limited by experience of the professional, so that the problems of unstable quality and poor accuracy of recommended data exist.
Disclosure of Invention
The application provides a method, a device, electronic equipment and a storage medium for processing a search request, so as to improve stability and accuracy of processing the search request.
In a first aspect, an embodiment of the present application provides a method for processing a search request, where the method for processing a search request includes:
responding to the search request, and determining target search parameters from candidate search parameters corresponding to the search request;
determining at least one candidate operator according to the target search parameter;
determining candidate operator structures of all candidate operators based on a genetic algorithm, and determining a target search model according to the candidate operator structures of all candidate operators; the candidate operator structure comprises candidate hierarchical structures of candidate operators and candidate fusion modes of output results of the candidate operators on the same layer;
searching the data to be searched associated with the search request based on the target search model to obtain recommended data.
In a second aspect, an embodiment of the present application further provides a processing device for a search request, where the processing device for a search request includes:
the target search parameter determining module is used for responding to the search request and determining target search parameters from candidate search parameters corresponding to the search request;
the candidate operator determining module is used for determining at least one candidate operator according to the target search parameters;
the target search model determining module is used for determining candidate operator structures of all candidate operators based on a genetic algorithm and determining a target search model according to the candidate operator structures of all the candidate operators; the candidate operator structure comprises candidate hierarchical structures of candidate operators and candidate fusion modes of output results of the candidate operators on the same layer;
and the data searching module is used for searching the data to be searched associated with the search request based on the target searching model to obtain recommended data.
In a third aspect, embodiments of the present application further provide an electronic device, including:
one or more processors;
a storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods for processing search requests as provided in the embodiments of the present application.
In a fourth aspect, embodiments of the present application also provide a storage medium comprising computer-executable instructions, which when executed by a computer processor, are configured to perform a method of processing any one of the search requests as provided by the embodiments of the present application.
According to the method and the device, the target search parameters are determined from the candidate search parameters corresponding to the search request in response to the search request, and the search range is reduced and the subsequent search speed and accuracy are improved by determining the target search parameters; determining at least one candidate operator according to the target search parameter; determining candidate operator structures of each candidate operator based on a genetic algorithm, determining a target search model according to the candidate operator structures of each candidate operator, optimizing the structures of each candidate operator through the genetic algorithm, and improving the stability and accuracy of the target search model without relying on manual experience; the candidate operator structure comprises candidate hierarchical structures of candidate operators and candidate fusion modes of output results of the same-layer candidate operators, and response to search requests is realized through structures of different operators, so that components are not required to be added, and development cost is reduced; searching the data to be searched associated with the search request based on the target search model to obtain recommended data. Therefore, through the technical scheme, the problems that the final recommendation result is limited by experience of professionals and the quality of the recommendation data is unstable and the accuracy is poor are solved, and the effect of improving the stability and the accuracy of search request processing is achieved.
Drawings
FIG. 1 is a flow chart of a method for processing a search request according to a first embodiment of the present application;
FIG. 2 is a flow chart of a method for processing a search request in a second embodiment of the present application;
FIG. 3a is a flow chart of a method of processing a search request in a third embodiment of the present application;
FIG. 3b is a flow chart of a process for processing a search request in accordance with a third embodiment of the present application;
fig. 4 is a schematic structural diagram of a processing device for a search request in the fourth embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device in a fifth embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first" and "second" and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for processing a search request according to an embodiment of the present application, where the method may be applied to a case of data recommendation according to the search request, and the method may be performed by a processing device of the search request, where the device may be implemented by software and/or hardware, and specifically configured in an electronic device, for example, a server.
Referring to the processing method of the search request shown in fig. 1, the method specifically includes the following steps:
s110, responding to the search request, and determining target search parameters from candidate search parameters corresponding to the search request.
The search request may be a request sent by a user to search for specified content. By way of example, the search request may be to search for merchandise, school, or building, etc. The candidate search parameters corresponding to the search request may be search parameters set in advance for different types of search requests, for determining target search parameters. For example, if the search request is when purchasing, the candidate search parameters may be brands, price intervals, performance, fuel consumption levels, and the like, which are not specifically limited in this application. The target search parameter may be a search parameter determined from the candidate search parameters for responding to the search request. For a particular search object in a search request of the same type, its corresponding target search parameters may be different. For example, if the search request is to search for a commodity, candidate search parameters that need to be focused are different when the commodity is an automobile and a food, and thus it is necessary to determine a target search parameter from among the candidate search parameters.
In an alternative embodiment, determining the target search parameter from the candidate search parameters corresponding to the search request includes: based on a machine learning algorithm, a target search parameter is determined from candidate search parameters corresponding to the search request.
The machine learning algorithm is an artificial intelligence algorithm for determining target search parameters. By way of example, the machine learning algorithm may be a neural network, decision tree, random forest, or the like, as not specifically limited in this application. The key candidate search parameters that affect search request results may be different for specific search objects in the same type of search request. For example, if the search request is a commodity, the candidate search parameters on which the commodity is a car and a food are different. For example, the search request is an automobile, and the target search parameters may be fuel consumption, safety performance and brand; when the search request is a food product, the target search parameters may be the place of origin, the raw materials of production, and the brand. And inputting the search request and the corresponding candidate search parameters into a machine learning algorithm to obtain target search parameters.
The target search parameters are determined from the candidate search parameters corresponding to the search request based on the machine learning algorithm, so that the target search parameters can be determined rapidly and accurately by using the machine learning algorithm, and the speed and accuracy of the subsequent response to the search request are improved.
S120, determining at least one candidate operator according to the target search parameters.
Candidate operators may be operators that search for data, for determining a target search model. Illustratively, candidate operators may include filter operators and statistical operators. Filtering operator filters input data according to numerical characteristics, and the filtering operator can be used for searching data of 'age >20 years' and 'price > 5000' corresponding to the following target search parameters, and the like; statistical operators filter the input data by statistical features, and the statistical operators can be used for searching data corresponding to the following target search parameters, such as 'all data with income equal to the median' and 'all data with age smaller than mean-standard deviation'. And determining a corresponding candidate operator according to the target search parameter, wherein the candidate operator can be at least one, namely the same target search parameter can correspond to at least one candidate operator.
S130, determining candidate operator structures of all candidate operators based on a genetic algorithm, and determining a target search model according to the candidate operator structures of all candidate operators; the candidate operator structure comprises a candidate hierarchical structure of each candidate operator and a candidate fusion mode of the output result of the same-layer candidate operator.
The genetic algorithm is a method for searching an optimal solution by simulating a natural evolution process, and the solving process of a problem can be converted into processes like crossing and mutation of chromosome genes in biological evolution by using a computer simulation operation in a mathematical mode. When solving more complex combinatorial optimization problems, genetic algorithms generally can obtain better optimization results faster than some conventional optimization algorithms. And optimizing candidate operator structures of each candidate operator through a genetic algorithm to obtain a target search model.
Specifically, the candidate operator structure comprises a candidate hierarchical structure of each candidate operator and a candidate fusion mode of the output result of the same-layer candidate operator. Wherein the hierarchy may include parallel and series relationships of candidate operators. Specifically, candidate operators in each layer in the candidate hierarchy are connected in parallel, and the result obtained by fusing the output results of the operators in the same layer in a candidate fusion mode is connected in series with the operator in the next layer.
And S140, searching the data to be searched associated with the search request based on the target search model to obtain recommended data.
The data to be searched associated with the search request may be a database determined from the search request for determining recommended data. The recommended data may be data determined from the data to be searched according to the target search model, for responding to the search request. And taking the data to be searched as input data of the target search model to obtain recommended data.
According to the technical scheme, the target search parameters are determined from the candidate search parameters corresponding to the search request in response to the search request, and the target search parameters are determined, so that the search range is narrowed, and the subsequent search speed and accuracy are improved; determining at least one candidate operator according to the target search parameter; determining candidate operator structures of each candidate operator based on a genetic algorithm, determining a target search model according to the candidate operator structures of each candidate operator, optimizing the structures of each candidate operator through the genetic algorithm, and improving the stability and accuracy of the target search model without relying on manual experience; the candidate operator structure comprises candidate hierarchical structures of candidate operators and candidate fusion modes of output results of the same-layer candidate operators, and response to search requests is realized through structures of different operators, so that components are not required to be added, and development cost is reduced; searching the data to be searched associated with the search request based on the target search model to obtain recommended data. Therefore, through the technical scheme, the problems that the final recommendation result is limited by experience of professionals and the quality of the recommendation data is unstable and the accuracy is poor are solved, and the effect of improving the stability and the accuracy of search request processing is achieved.
Example two
Fig. 2 is a flowchart of a flowchart method of a processing method of a search request provided in a second embodiment of the present application, and the technical solution of the present embodiment is further refined on the basis of the technical solution.
Further, the method comprises the steps of determining candidate operator structures of all candidate operators based on a genetic algorithm, determining a target search model according to the candidate operator structures of all candidate operators, and refining the target search model as follows: "based on genetic algorithm, according to each candidate operator, determining the primary operator structure of at least one candidate operator, and determining the corresponding primary adaptability; screening and iterating each primary operator structure according to each primary fitness, and obtaining the fitness of the next-generation operator structure; if the fitness of the next generation operator structure converges, determining the operator structure as a target operator structure of each candidate operator so as to determine the target operator structure.
Referring to fig. 2, a method for processing a search request includes:
s210, responding to the search request, and determining target search parameters from candidate search parameters corresponding to the search request.
S220, determining at least one candidate operator according to the target search parameters.
S230, determining a primary operator structure of at least one candidate operator according to each candidate operator based on a genetic algorithm, and determining corresponding primary adaptability.
The primary operator structure may be the initial operator structure in a genetic algorithm. Illustratively, the number of primary operator structures may be randomly generated, and the number of primary operator structures may be a larger number, e.g., 1000 primary operator structures. The fitness function in the genetic algorithm is also called an evaluation function, and is an index for judging the degree of merit of individuals in a population. The adaptation may be an evaluation value of the primary operator structure of each candidate operator determined by the fitness function, for optimizing the primary operator structure of each candidate operator. Each primary fitness may be a fitness corresponding to each primary operator structure.
In an alternative embodiment, determining a primary operator structure for at least one of the candidate operators based on a genetic algorithm based on the candidate operators, comprises: and determining the layer number of at least one primary operator structure, parallel operators in each layer and a fusion mode of search results of the parallel operators in each layer according to each candidate operator, and taking the parallel operators as the primary operator structure of the candidate operator.
The number of layers of the primary operator structure can be the number of layers of each candidate operator in series connection in the primary operator structure, and an exemplary method can be used for fusing the search results of the same-layer parallel operator and the same-layer parallel operator as one layer. The parallel operators can be candidates of the same layer connected in parallel, and input data of the parallel operators in the same layer are the same. The fusion mode can be a fusion mode of the search results of the same-layer parallel operators, namely a fusion mode of output data of the same-layer parallel operators. The fusion manner may be at least one of intersection, union, difference, and random fusion, for example. Specifically, the number of layers of the primary operator and the number of operators can be limited according to actual requirements so as to adapt to personalized requirements. For example, the maximum number of layers of the primary operator may be limited when the corresponding speed requirement for the search request is high.
In the prior art, after determining a target search parameter of a search request, generating a routing code corresponding to the target search parameter; and selecting the plug-in call data from the arrangement definition database according to the routing code, and calling the corresponding plug-ins in sequence according to the plug-in call data. The orchestration definition database is configured in advance by a business expert, and describes plug-ins required by certain routing codes and the calling relations among the plug-ins. Specifically, selecting plug-in call data from the orchestration definition database according to the routing code may include: determining a corresponding route code matching relation according to the route codes; acquiring a plurality of plug-in call data corresponding to the routing codes from the arrangement definition database according to the matching relation of the routing codes; and selecting the plug-in call data with the highest matching correlation degree from the plug-in call data according to the matching correlation degree of the plug-in call data.
The response to the search request takes the calling plugin as a core, and the problems of dependence on manual experience and high development cost exist. On the one hand, the final recommended data set is obtained by sequentially calling the plug-ins, the plug-in calling sequence is manually specified by service personnel according to service experience, and the final recommended result is limited by the service level and service experience of the service personnel. If inexperienced business personnel specify the calling order of the plug-ins, it may be difficult to guarantee recommended data quality. On the other hand, each plugin always operates data in a serial connection manner, which is equivalent to the formation of a relation between the calculation results of each plugin, for example, an operating system calls two filtering plugins of plugin 1 and plugin 2 successively to operate data to be searched, the filtering condition of plugin 1 is 'age >20 years', the filtering condition of plugin 2 is 'month income >5000 yuan', the operating system calls plugin 1 to filter the data first, then takes the filtering result as the input of plugin 2, the filtering result of the final data is 'age >20 years' and 'month income >5000 yuan', if the filtering operation of 'age >20 years' or 'month income >5000 yuan' is required to be carried out, a new plugin needs to be added separately to meet the requirement, and as the searching requirement is enlarged, the request parameters possibly comprise dozens of different dimensions, the excessive creation of new plugins can increase the system burden, reduce the system operation efficiency and increase the development cost under complex scenes.
The number of layers of at least one primary operator structure, parallel operators in each layer and the fusion mode of search results of parallel operators in each layer are determined according to each candidate operator, the primary operator structure of the candidate operator is used, and the parallel operators in the same layer are called in parallel, so that the operation results of the operators can be fused according to the appointed fusion mode, the creation of new plug-ins to realize logical OR is avoided, the number of plug-ins can be reduced in complex business, the system overhead is reduced, and the operation efficiency is improved.
And S240, screening and iterating each primary operator structure according to each primary fitness, and obtaining the fitness of the next-generation operator structure.
And screening the primary operator structure according to each primary fitness, and obtaining a next-generation operator structure through crossover operation and mutation operation in a genetic algorithm, thereby obtaining the fitness of the next-generation operator structure through a fitness function.
S250, if the adaptability of the next generation operator structure is converged, determining the operator structure as a target operator structure of each candidate operator.
And if the adaptability of the next-generation operator structure is converged, namely, when the value of the adaptability of the next-generation operator structure is not increased, determining the operator structure as a target operator structure of each candidate operator.
And S260, searching the data to be searched associated with the search request based on the target search model to obtain recommended data.
According to the technical scheme of the embodiment, the primary operator structure of at least one candidate operator is determined according to each candidate operator based on a genetic algorithm, and the corresponding primary adaptability is determined; screening and iterating each primary operator structure according to each primary fitness, and obtaining the fitness of the next-generation operator structure; if the adaptability of the next generation operator structure is converged, the operator structure is determined to be a target operator structure of each candidate operator, the operator structure of the candidate operator is automatically optimized through a genetic algorithm, the decision process is automated, the artificial experience is not needed, and the rationality of the target operator structure is improved, so that the accuracy of recommended data is improved.
Example III
Fig. 3a is a flowchart of a flowchart method of a processing method of a search request according to a third embodiment of the present application, and the technical solution of the present embodiment is further refined on the basis of the technical solution.
Further, "searching data to be searched associated with the search request based on the target search model to obtain recommended data" is refined into: "according to the keyword in the search request, confirm the data to be searched correlated to search request; and inputting the data to be searched into the target search model to obtain recommended data so as to obtain the recommended data.
Referring to fig. 3a, a method for processing a search request includes:
s310, responding to the search request, and determining target search parameters from candidate search parameters corresponding to the search request.
S320, determining at least one candidate operator according to the target search parameters.
S330, determining candidate operator structures of all candidate operators based on a genetic algorithm, and determining a target search model according to the candidate operator structures of all candidate operators; the candidate operator structure comprises a candidate hierarchical structure of each candidate operator and a candidate fusion mode of the output result of the same-layer candidate operator.
S340, determining data to be searched associated with the search request according to the keywords in the search request.
The keywords in the search request may be keywords used to determine the data to be searched. By way of example, keywords in a search request may be obtained through an intelligent word segmentation algorithm. For example, the keyword may be a car when the search request is a shopping cart. The intelligent word segmentation algorithm may be a deep learning algorithm, for example, a neural network algorithm.
Searching a database matched with the keywords in the database through the keywords, and taking the data in the successfully matched database as the data to be searched associated with the search request.
S350, inputting the data to be searched into the target search model to obtain recommended data.
And inputting the data to be searched into the target search model as input data, and obtaining an output result as recommended data.
In an alternative embodiment, inputting data to be searched into a target search model to obtain recommended data includes: respectively inputting data to be searched into first-layer parallel operators of a target search model to respectively obtain search results after searching by the first-layer parallel operators; fusing the search results of the first-layer parallel operators according to a fusion mode corresponding to the first-layer parallel operators to obtain a first fusion result; and taking the first fusion result as the input of the next layer of parallel operators, and fusing the search results of all the parallel operators according to a corresponding fusion mode until the search results of the last layer of parallel operators are fused, so as to obtain recommended data.
And respectively inputting the data to be searched into the first-layer parallel operators of the target search model, wherein the data to be searched is respectively used as the input data of the first-layer parallel operators of the target search model for searching, namely the input data of the first-layer parallel operators are all the data to be searched. And fusing the search results of the first-layer parallel operators according to a fusion mode corresponding to the first-layer parallel operators to obtain a first fusion result. The first fusion result is used as input data of each parallel operator in the next layer, namely the input data of the next layer of parallel operators are all first fusion results, the output results of the next layer of parallel operators fuse the search results of each parallel operator according to the corresponding fusion mode to obtain the search results of the layer of parallel operators, and the search results are continuously used as the input data of the next layer of the layer of parallel operators until the search results of the last layer of parallel operators are obtained to obtain recommended data.
FIG. 3b is a flow chart of a process for processing a search request. The number of layers of the object search model in FIG. 3b is 2, the operator 11 Operator 12 Sum operator 13 For 3 of the first layer of parallel operators, the result is 11 Results of 12 Sum result 13 Search results corresponding to 3 parallel operators respectively, and results 1 Is the first fusion result. Operator 21 Operator 22 Sum operator 23 Are 3 of the second layer parallel operators. Inputting data to be searched into operator 11 Operator 12 Sum operator 13 In (1) obtaining the result 11 Results of 12 Sum result 13 By the result of 11 Results of 12 Sum result 13 Fusing according to the corresponding fusion mode to obtain a result 1 . Results are obtained 1 Respectively input to operators 21 Operator 22 Sum operator 23 And obtaining recommended data.
Respectively inputting data to be searched into first-layer parallel operators of a target search model to respectively obtain search results after searching by the first-layer parallel operators; fusing the search results of the first-layer parallel operators according to a fusion mode corresponding to the first-layer parallel operators to obtain a first fusion result; and taking the first fusion result as the input of the next layer of parallel operators, fusing the search results of all the parallel operators according to the corresponding fusion mode until the search results of the last layer of parallel operators are fused, obtaining recommended data, and obtaining the recommended data through the parallel operators and the corresponding fusion mode without adding additional components, thereby ensuring the accuracy of the recommended data.
According to the technical scheme, the data to be searched associated with the search request is determined according to the keywords in the search request, so that the data to be searched can be accurately determined, and a data basis is provided for obtaining recommended data; and inputting the data to be searched into the target search model to obtain recommended data, and rapidly and accurately obtaining the recommended data through the target search model, thereby improving the accuracy of the obtained recommended data.
Example IV
Fig. 4 is a schematic structural diagram of a processing device for a search request according to a fourth embodiment of the present application, where the present embodiment is applicable to a case of data recommendation according to a search request, and the specific structure of the processing device for a search request is as follows:
a target search parameter determining module 410, configured to determine a target search parameter from candidate search parameters corresponding to the search request in response to the search request;
a candidate operator determining module 420, configured to determine at least one candidate operator according to the target search parameter;
a target search model determining module 430, configured to determine candidate operator structures of each candidate operator based on a genetic algorithm, and determine a target search model according to the candidate operator structures of each candidate operator; the candidate operator structure comprises candidate hierarchical structures of candidate operators and candidate fusion modes of output results of the candidate operators on the same layer;
the data searching module 440 is configured to search the data to be searched associated with the search request based on the target search model, so as to obtain recommended data.
According to the technical scheme, the target search parameters are determined from the candidate search parameters corresponding to the search request in response to the search request, and the target search parameters are determined, so that the search range is narrowed, and the subsequent search speed and accuracy are improved; determining at least one candidate operator according to the target search parameter; determining candidate operator structures of each candidate operator based on a genetic algorithm, determining a target search model according to the candidate operator structures of each candidate operator, optimizing the structures of each candidate operator through the genetic algorithm, and improving the stability and accuracy of the target search model without relying on manual experience; the candidate operator structure comprises candidate hierarchical structures of candidate operators and candidate fusion modes of output results of the same-layer candidate operators, and response to search requests is realized through structures of different operators, so that components are not required to be added, and development cost is reduced; searching the data to be searched associated with the search request based on the target search model to obtain recommended data. Therefore, through the technical scheme, the problems that the final recommendation result is limited by experience of professionals and the quality of the recommendation data is unstable and the accuracy is poor are solved, and the effect of improving the stability and the accuracy of search request processing is achieved.
Optionally, the target search model determination module 430 includes:
the primary operator structure determining unit is used for determining the primary operator structure of at least one candidate operator according to each candidate operator based on a genetic algorithm and determining the corresponding primary adaptability;
the next generation operator structure determining unit is used for screening and iterating each primary operator structure according to each primary fitness and obtaining the fitness of the next generation operator structure;
and the target operator structure determining unit is used for determining the operator structure as the target operator structure of each candidate operator if the adaptability of the next generation operator structure is converged.
Optionally, the primary operator structure determining unit includes:
the candidate operator structure determining subunit is used for determining the layer number of at least one primary operator structure according to each candidate operator, parallel operators in each layer and a fusion mode of search results of the parallel operators in each layer, and is used as the primary operator structure of the candidate operator.
Optionally, the data search module 440 includes:
the to-be-searched data determining unit is used for determining to-be-searched data associated with the search request according to the keywords in the search request;
and the recommended data determining unit is used for inputting the data to be searched into the target search model to obtain recommended data.
Optionally, the recommendation data determining unit includes:
the parallel operator result determining subunit is used for respectively inputting the data to be searched into the first-layer parallel operators of the target search model to respectively obtain search results after the first-layer parallel operators are searched;
the parallel operator result determining fusion subunit is used for fusing the search results of the first-layer parallel operators according to the fusion mode corresponding to the first-layer parallel operators to obtain a first fusion result;
and the recommended data determining subunit is used for taking the first fusion result as the input of the next layer of parallel operators, and fusing the search results of all the parallel operators according to a corresponding fusion mode until the search results of the last layer of parallel operators are fused, so as to obtain recommended data.
Optionally, the target search parameter determination module 410 includes:
and the candidate search parameter screening unit is used for determining target search parameters from candidate search parameters corresponding to the search request based on a machine learning algorithm.
The processing device for the search request provided by the embodiment of the application can execute the processing method for the search request provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of executing the processing method for the search request.
Example five
Fig. 5 is a schematic structural diagram of an electronic device provided in a fifth embodiment of the present application, as shown in fig. 5, the electronic device includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of processors 510 in the electronic device may be one or more, one processor 510 being taken as an example in fig. 5; the processor 510, memory 520, input device 530, and output device 540 in the electronic device may be connected by a bus or other means, for example in fig. 5.
The memory 520 serves as a computer-readable storage medium, and may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules (e.g., the target search parameter determination module 410, the candidate operator determination module 420, the target search model determination module 430, and the data search module 440) corresponding to a method of processing a search request in an embodiment of the present application. The processor 510 executes various functional applications of the electronic device and data processing, i.e., implements the above-described search request processing method, by running software programs, instructions, and modules stored in the memory 520.
Memory 520 may include primarily a program storage area and a data storage area, wherein the program storage area may store an operating system, at least one application program required for functionality; the storage data area may store data created according to the use of the terminal, etc. In addition, memory 520 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, memory 520 may further include memory located remotely from processor 510, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 530 may be used to receive input character information and to generate key signal inputs related to user settings and function control of the electronic device. The output 540 may include a display device such as a display screen.
Example six
A sixth embodiment of the present application also provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method of processing a search request, the method comprising: responding to the search request, and determining target search parameters from candidate search parameters corresponding to the search request; determining at least one candidate operator according to the target search parameter; determining candidate operator structures of all candidate operators based on a genetic algorithm, and determining a target search model according to the candidate operator structures of all candidate operators; the candidate operator structure comprises candidate hierarchical structures of candidate operators and candidate fusion modes of output results of the candidate operators on the same layer; searching the data to be searched associated with the search request based on the target search model to obtain recommended data.
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present application is not limited to the method operations described above, and may also perform the related operations in the method for processing a search request provided in any embodiment of the present application.
From the above description of embodiments, it will be clear to a person skilled in the art that the present application may be implemented by means of software and necessary general purpose hardware, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a FLASH Memory (FLASH), a hard disk, or an optical disk of a computer, etc., including several instructions for causing an electronic device (which may be a personal computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.
It should be noted that, in the above-mentioned embodiments of the search apparatus, each unit and module included are only divided according to the functional logic, but not limited to the above-mentioned division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present application.
Note that the above is only a preferred embodiment of the present application and the technical principle applied. Those skilled in the art will appreciate that the present application is not limited to the particular embodiments described herein, but is capable of numerous obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the present application. Therefore, while the present application has been described in connection with the above embodiments, the present application is not limited to the above embodiments, but may include many other equivalent embodiments without departing from the spirit of the present application, the scope of which is defined by the scope of the appended claims.

Claims (10)

1. A method for processing a search request, comprising:
responding to a search request, and determining target search parameters from candidate search parameters corresponding to the search request;
determining at least one candidate operator according to the target search parameter;
determining candidate operator structures of the candidate operators based on a genetic algorithm, and determining a target search model according to the candidate operator structures of the candidate operators; the candidate operator structure comprises candidate hierarchical structures of the candidate operators and candidate fusion modes of output results of the same-layer candidate operators;
and searching the data to be searched associated with the search request based on the target search model to obtain recommended data.
2. The method of claim 1, wherein the determining candidate operator structures for each of the candidate operators based on the genetic algorithm and determining a target search model based on the candidate operator structures for each of the candidate operators comprises:
determining a primary operator structure of at least one candidate operator according to each candidate operator based on a genetic algorithm, and determining corresponding primary adaptability;
screening and iterating each primary operator structure according to each primary fitness, and obtaining the fitness of the next-generation operator structure;
and if the adaptability of the next generation operator structure is converged, determining the operator structure as a target operator structure of each candidate operator.
3. The method of claim 2, wherein said determining at least one primary operator structure for each of said candidate operators based on each of said candidate operators comprises:
and determining the layer number of at least one primary operator structure, parallel operators in each layer and a fusion mode of search results of the parallel operators in each layer according to each candidate operator, and taking the parallel operators as the primary operator structure of the candidate operator.
4. The method of claim 1, wherein searching for data to be searched associated with the search request based on the target search model to obtain recommended data comprises:
determining data to be searched associated with the search request according to the keywords in the search request;
and inputting the data to be searched into the target search model to obtain recommended data.
5. The method of claim 4, wherein the inputting the data to be searched into the target search model to obtain recommended data comprises:
the data to be searched are respectively input into first-layer parallel operators of the target search model, and search results obtained after the first-layer parallel operators are searched are respectively obtained;
fusing the search results of the first-layer parallel operators according to a fusion mode corresponding to the first-layer parallel operators to obtain a first fusion result;
and taking the first fusion result as the input of the next layer of parallel operators, and fusing the search results of all the parallel operators according to a corresponding fusion mode until the search results of the last layer of parallel operators are fused, so as to obtain recommended data.
6. The method of claim 1, wherein determining the target screening parameter from the candidate screening parameters corresponding to the search request comprises:
and determining target search parameters from candidate search parameters corresponding to the search request based on a machine learning algorithm.
7. A search request processing apparatus, comprising:
the target search parameter determining module is used for responding to a search request and determining target search parameters from candidate search parameters corresponding to the search request;
the candidate operator determining module is used for determining at least one candidate operator according to the target search parameter;
the target search model determining module is used for determining candidate operator structures of the candidate operators based on a genetic algorithm and determining a target search model according to the candidate operator structures of the candidate operators; the candidate operator structure comprises candidate hierarchical structures of the candidate operators and candidate fusion modes of output results of the same-layer candidate operators;
and the data searching module is used for searching the data to be searched associated with the search request based on the target searching model to obtain recommended data.
8. The apparatus of claim 7, wherein the target search model determination module comprises:
the primary operator structure determining unit is used for determining the primary operator structure of at least one candidate operator according to the candidate operators based on a genetic algorithm and determining the corresponding primary adaptability;
the next generation operator structure determining unit is used for screening and iterating each primary operator structure according to each primary adaptability and obtaining the adaptability of the next generation operator structure;
and the target operator structure determining unit is used for determining the operator structure as the target operator structure of each candidate operator if the adaptability of the next generation operator structure is converged.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of processing a search request according to any one of claims 1-6 when the program is executed by the processor.
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 a method of processing a search request according to any one of claims 1-6.
CN202310205936.7A 2023-03-06 2023-03-06 Method and device for processing search request, electronic equipment and storage medium Pending CN116361546A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310205936.7A CN116361546A (en) 2023-03-06 2023-03-06 Method and device for processing search request, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310205936.7A CN116361546A (en) 2023-03-06 2023-03-06 Method and device for processing search request, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116361546A true CN116361546A (en) 2023-06-30

Family

ID=86932588

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310205936.7A Pending CN116361546A (en) 2023-03-06 2023-03-06 Method and device for processing search request, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116361546A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116884759A (en) * 2023-07-19 2023-10-13 重庆望变电气（集团）股份有限公司 Iron core stacking process scheme generation system and method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116884759A (en) * 2023-07-19 2023-10-13 重庆望变电气（集团）股份有限公司 Iron core stacking process scheme generation system and method
CN116884759B (en) * 2023-07-19 2024-03-22 重庆望变电气（集团）股份有限公司 Iron core stacking process scheme generation system and method

Similar Documents

Publication Publication Date Title
CN112232925A (en) Method for carrying out personalized recommendation on commodities by fusing knowledge maps
CN110909182B (en) Multimedia resource searching method, device, computer equipment and storage medium
CN108595533B (en) Article recommendation method based on collaborative filtering, storage medium and server
CN111611488B (en) Information recommendation method and device based on artificial intelligence and electronic equipment
CN113326377A (en) Name disambiguation method and system based on enterprise incidence relation
CN108563663A (en) Picture recommendation method, device, equipment and storage medium
CN113011529B (en) Training method, training device, training equipment and training equipment for text classification model and readable storage medium
CN113536097A (en) Recommendation method and device based on automatic feature grouping
CN116361546A (en) Method and device for processing search request, electronic equipment and storage medium
CN111797320A (en) Data processing method, device, equipment and storage medium
CN117495512B (en) Order data management method, device, equipment and storage medium
CN114428910A (en) Resource recommendation method and device, electronic equipment, product and medium
CN117725220A (en) Method, server and storage medium for document characterization and document retrieval
CN112860878A (en) Service data recommendation method, storage medium and equipment
CN116628346A (en) Training method and device for search word recommendation model
CN108595395B (en) Nickname generation method, device and equipment
CN114385876B (en) Model search space generation method, device and system
CN116522232A (en) Document classification method, device, equipment and storage medium
CN111324344A (en) Code statement generation method, device, equipment and readable storage medium
CN115600818A (en) Multi-dimensional scoring method and device, electronic equipment and storage medium
CN111291904B (en) Preference prediction method and device and computer equipment
CN115345687A (en) Cross-website commodity alignment method and device
CN113343100A (en) Wisdom city resource recommendation method and system based on knowledge graph
Cruz-Reyes et al. Simplification of decision rules for recommendation of projects in a public project portfolio
CN117786234B (en) Multimode resource recommendation method based on two-stage comparison learning

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