A component retrieval method and device based on intelligent recommendation

Abstract

The present invention discloses a component retrieval method and device based on intelligent recommendation. The method comprises: obtaining retrieval information; matching keywords in the retrieval information with a development component database in a development component big data platform to extract diversified data; outputting recommendation results based on the diversified data using a component recommendation model; and reversely verifying the recommendation results through the development component big data platform to obtain verification results. The present invention solves the technical problem that the component retrieval recommendation generation method in the prior art only generates final decision data based on local decision parameters and input factors, but cannot generate component recommendations based on the collection of diversified data, nor can it reversely verify the generated recommendation data using a big data platform, thus resulting in low accuracy and low efficiency in the retrieval recommendation process.

Description

Technical Field

[0001] The present invention relates to the fields of data prediction and data processing in IT and software development, and in particular to a component retrieval method and device based on intelligent recommendation. Background Art

[0002] With the continuous development of intelligent technology, people are increasingly using intelligent devices in their lives, work and study. The use of intelligent technology has improved the quality of people's lives and increased the efficiency of their study and work.

[0003] When it comes to decision-making or component recommendations, decision tree logic algorithms in servers are often used to generate decision result data against a logical adversarial model. During the logical generation process, both the adversarial model training and the model input data are analyzed and processed using a large amount of historical data or unprocessed data collected by a collector. However, existing component retrieval and recommendation generation methods only generate final decision data based on local decision parameters and input factors. They cannot generate component recommendations based on multivariate data collection, nor can they use big data platforms to reverse-validate the generated recommendation data. This leads to technical issues such as low accuracy and low efficiency in the retrieval and recommendation process.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] The embodiments of the present invention provide a component retrieval method and device based on intelligent recommendation, so as to at least solve the technical problem that the component retrieval recommendation generation method in the prior art only generates final decision data based on local decision parameters and input factors, but cannot generate component recommendations based on the collection of multivariate data, and cannot use the big data platform to reversely verify the generated recommendation data, thus resulting in the technical problem of low accuracy and low efficiency of the retrieval recommendation process.

[0006] According to one aspect of an embodiment of the present invention, a component retrieval method based on intelligent recommendation is provided, including: obtaining retrieval information; matching keywords in the retrieval information with a development component database in a development component big data platform to extract diversified data; outputting recommendation results using a component recommendation model based on the diversified data; and reversely verifying the recommendation results through the development component big data platform to obtain verification results.

[0007] Furthermore, the search information includes: search keywords generated by the user according to the search requirements.

[0008] Furthermore, after matching the keywords in the search information with the development component database in the development component big data platform and extracting diversified data, the method further includes: training a component recommendation model based on the diversified data.

[0009] Furthermore, after reversely verifying the recommendation result through the development component big data platform to obtain a verification result, the method further includes: sending the recommendation result to a user terminal.

[0010] According to another aspect of an embodiment of the present invention, a component retrieval device based on intelligent recommendation is also provided, including: an acquisition module for acquiring retrieval information; an extraction module for matching keywords in the retrieval information with a development component database in a development component big data platform to extract diversified data; an output module for outputting recommendation results based on the diversified data using a component recommendation model; and a verification module for reversely verifying the recommendation results through the development component big data platform to obtain verification results.

[0011] Furthermore, the search information includes: search keywords generated by the user according to the search requirements.

[0012] Furthermore, the device also includes: a training module, configured to train a component recommendation model based on the diversified data.

[0013] Furthermore, the device further includes: a sending module, configured to send the recommendation result to a user terminal.

[0014] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, which includes a stored program, wherein when the program is run, it controls the device where the non-volatile storage medium is located to execute a component retrieval method based on intelligent recommendation.

[0015] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising a processor and a memory; the memory stores computer-readable instructions, and the processor is used to run the computer-readable instructions, wherein the computer-readable instructions execute a component retrieval method based on intelligent recommendation when running.

[0016] The present invention has the following beneficial effects:

[0017] In an embodiment of the present invention, the method of obtaining retrieval information; matching the keywords in the retrieval information with the development component database in the development component big data platform to extract diversified data; outputting recommendation results based on the diversified data using a component recommendation model; and reversely verifying the recommendation results through the development component big data platform to obtain verification results solves the technical problem that the component retrieval recommendation generation method in the prior art only generates final decision data based on local decision parameters and input factors, but cannot generate component recommendations based on the collection of diversified data, and cannot reversely verify the generated recommendation data using the big data platform, thereby resulting in the technical problems of low accuracy and low efficiency in the retrieval recommendation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 is a flowchart of a component retrieval method based on intelligent recommendation according to an embodiment of the present invention;

[0020] Figure 2 is a structural block diagram of a component retrieval device based on intelligent recommendation according to an embodiment of the present invention;

[0021] Figure 3 Schematic diagram of the DNN neural network structure according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to an embodiment of the present invention, a method embodiment of a component retrieval method based on intelligent recommendation is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Example 1

[0026] Figure 1 is a flow chart of a component retrieval method based on intelligent recommendation according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0027] Step S102: Acquire search information.

[0028] Step S104 , matching the keywords in the search information with the development component database in the development component big data platform to extract diversified data.

[0029] Step S106: Outputting a recommendation result using a component recommendation model based on the diversified data.

[0030] Step S108: reversely verify the recommendation result through the development component big data platform to obtain a verification result.

[0031] Optionally, the search information includes: search keywords generated by the user according to search requirements.

[0032] Optionally, after matching the keywords in the search information with the development component database in the development component big data platform and extracting diversified data, the method further includes: training a component recommendation model based on the diversified data.

[0033] Optionally, after reverse verifying the recommendation result through the development component big data platform to obtain a verification result, the method further includes: sending the recommendation result to a user terminal.

[0034] Specifically, first obtain the search information, wherein the search information is the search keywords and other information generated by the user according to the search requirements or search instructions, which is used to search for the corresponding development components; specifically, when the user generates the keyword information, the user only needs to enter the keyword search information to obtain the results of the relevant component search, so when the acquisition device is collecting, it is first necessary to collect the search instructions entered by the user and analyze the keywords and other information. Subsequently, it is necessary to match the keywords in the search information with the development component database in the development component big data platform, and extract the corresponding diversified data related to the component search requirements; specifically, after activating the database through the big data platform, it is necessary to search and match the diversified data related to the requirements in the big data database according to the user's requirements or search information, wherein the diversified data refers to the multiple data and multi-channel data related to the requirements, so as to increase the accuracy of subsequent model training.

[0035] The component recommendation neural network model is trained based on the diversified data, and the training result is input as the input object of the retrieval information; the recommendation result output by the component recommendation model is reversely input into the big data platform, and the recommendation result is verified based on the combined data set of the retrieval information and the final selected component information in the big data platform, and a verification result is obtained, wherein the verification result includes qualified and unqualified; specifically, when training the neural network model, the diversified data collected by the big data platform can be used to train the component retrieval DNN neural network model. In addition, from the position of different layers of the DNN, the neural network layers inside the component retrieval DNN can be divided into three categories, namely, input layer, hidden layer and output layer, such as Figure 3 For example, generally speaking, the first layer is the input layer, the last layer is the output layer, and the layers in between are hidden layers.

[0036] The layers are fully connected, that is, any neuron in layer i must be connected to any neuron in layer i+1. Although DNN looks complicated, from a small local model, it is still the same as the perceptron, that is, a linear relationship z = Σw i x i+b plus an activation function σ(z). Further, after constructing the above-mentioned DNN network model, the component retrieval results are obtained through the DNN network model and the recommendation results are verified using a combined data set of the retrieval information and the final selected component information in the big data platform to obtain a verification result. The verification process can be to reversely search the results through the big data platform and check whether the retrieval information is obtained. When the verification result is qualified, it indicates that the component recommendation result obtained by reversely utilizing the big data platform is in line with the user's expectations and also conforms to the statistical laws of historical data; the recommendation result is sent to the user terminal.

[0037] Through the above embodiments, the technical problem that the component retrieval recommendation generation method in the prior art only generates final decision data based on local decision parameters and input factors, but cannot generate component recommendations based on the collection of multivariate data, and cannot use the big data platform to reversely verify the generated recommendation data, thus resulting in low accuracy and low efficiency in the retrieval recommendation process, is solved.

[0038] Example 2

[0039] Figure 1 is a flow chart of a component retrieval method based on intelligent recommendation according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0040] The acquisition module 20 is used to acquire search information.

[0041] The extraction module 22 is used to match the keywords in the search information with the development component database in the development component big data platform to extract diversified data.

[0042] The output module 24 is configured to output a recommendation result based on the diversified data using a component recommendation model.

[0043] The verification module 26 is used to reversely verify the recommendation result through the development component big data platform to obtain a verification result.

[0044] Optionally, the search information includes: search keywords generated by the user according to search requirements.

[0045] Optionally, the device further includes: a training module, configured to train a component recommendation model based on the diversified data.

[0046] Optionally, the device further includes: a sending module, configured to send the recommendation result to a user terminal.

[0047] Specifically, first obtain the search information, wherein the search information is the search keywords and other information generated by the user according to the search requirements or search instructions, which is used to search for the corresponding development components; specifically, when the user generates the keyword information, the user only needs to enter the keyword search information to obtain the results of the relevant component search, so when the acquisition device is collecting, it is first necessary to collect the search instructions entered by the user and analyze the keywords and other information. Subsequently, it is necessary to match the keywords in the search information with the development component database in the development component big data platform, and extract the corresponding diversified data related to the component search requirements; specifically, after activating the database through the big data platform, it is necessary to search and match the diversified data related to the requirements in the big data database according to the user's requirements or search information, wherein the diversified data refers to the multiple data and multi-channel data related to the requirements, so as to increase the accuracy of subsequent model training.

[0048] The component recommendation neural network model is trained based on the diversified data, and the training result is input as the input object of the retrieval information; the recommendation result output by the component recommendation model is reversely input into the big data platform, and the recommendation result is verified based on the combined data set of the retrieval information and the final selected component information in the big data platform, and a verification result is obtained, wherein the verification result includes qualified and unqualified; specifically, when training the neural network model, the diversified data collected by the big data platform can be used to train the component retrieval DNN neural network model. In addition, from the position of different layers of the DNN, the neural network layers inside the component retrieval DNN can be divided into three categories, namely, input layer, hidden layer and output layer, such as Figure 3 For example, generally speaking, the first layer is the input layer, the last layer is the output layer, and the layers in between are hidden layers.

[0049] The layers are fully connected, that is, any neuron in layer i must be connected to any neuron in layer i+1. Although DNN looks complicated, from a small local model, it is still the same as the perceptron, that is, a linear relationship z = Σw i x i+b plus an activation function σ(z). Further, after constructing the above-mentioned DNN network model, the component retrieval results are obtained through the DNN network model and the recommendation results are verified using a combined data set of the retrieval information and the final selected component information in the big data platform to obtain a verification result. The verification process can be to reversely search the results through the big data platform and check whether the retrieval information is obtained. When the verification result is qualified, it indicates that the component recommendation result obtained by reversely utilizing the big data platform is in line with the user's expectations and also conforms to the statistical laws of historical data; the recommendation result is sent to the user terminal.

[0050] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, which includes a stored program, wherein when the program is run, it controls the device where the non-volatile storage medium is located to execute a component retrieval method based on intelligent recommendation.

[0051] Specifically, the above method includes: obtaining search information; matching the keywords in the search information with the development component database in the development component big data platform to extract diversified data; outputting recommendation results using a component recommendation model based on the diversified data; and reverse-verifying the recommendation results through the development component big data platform to obtain verification results. Optionally, the search information includes: search keywords generated by the user based on the search requirements. Optionally, after matching the keywords in the search information with the development component database in the development component big data platform to extract diversified data, the method further includes: training the component recommendation model based on the diversified data. Optionally, after reverse-verifying the recommendation results through the development component big data platform to obtain verification results, the method further includes: sending the recommendation results to the user terminal.

[0052] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising a processor and a memory; the memory stores computer-readable instructions, and the processor is used to run the computer-readable instructions, wherein the computer-readable instructions execute a component retrieval method based on intelligent recommendation when running.

[0053] Specifically, the above method includes: obtaining search information; matching the keywords in the search information with the development component database in the development component big data platform to extract diversified data; outputting recommendation results using a component recommendation model based on the diversified data; and reverse-verifying the recommendation results through the development component big data platform to obtain verification results. Optionally, the search information includes: search keywords generated by the user based on the search requirements. Optionally, after matching the keywords in the search information with the development component database in the development component big data platform to extract diversified data, the method further includes: training the component recommendation model based on the diversified data. Optionally, after reverse-verifying the recommendation results through the development component big data platform to obtain verification results, the method further includes: sending the recommendation results to the user terminal.

[0054] Through the above embodiments, the technical problem that the component retrieval recommendation generation method in the prior art only generates final decision data based on local decision parameters and input factors, but cannot generate component recommendations based on the collection of multivariate data, and cannot use the big data platform to reversely verify the generated recommendation data, thus resulting in low accuracy and low efficiency in the retrieval recommendation process, is solved.

[0055] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0056] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0057] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0058] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0059] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0060] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0061] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A component retrieval method based on intelligent recommendation, characterized in that: include: Get search information; Matching the keywords in the search information with the development component database in the development component big data platform to extract diversified data; Outputting recommendation results using a component recommendation model based on the diversified data; Reversely verify the recommendation result through the development component big data platform to obtain a verification result; Among them, the component recommendation neural network model is trained based on the diversified data, and the training results are input as the input object of the retrieval information; the recommendation results output by the component recommendation model are reversely input into the big data platform, and the recommendation results are verified based on the combined data set of the retrieval information and the final selected component information in the big data platform, and the verification results are obtained, wherein the verification results include qualified and unqualified.

2. The method according to claim 1, characterized in that The search information includes: search keywords generated by the user according to the search requirements.

3. The method according to claim 1, characterized in that After matching the keywords in the search information with the development component database in the development component big data platform to extract diversified data, the method further includes: A component recommendation model is trained based on the diversified data.

4. The method according to claim 1, wherein After reversely verifying the recommendation result through the development component big data platform to obtain a verification result, the method further includes: The recommendation result is sent to the user terminal.

5. A component retrieval device based on intelligent recommendation, characterized in that: include: Acquisition module, used to obtain search information; An extraction module for matching keywords in the search information with a development component database in a development component big data platform to extract diversified data; an output module, configured to output a recommendation result using a component recommendation model based on the diversified data; A verification module, configured to reversely verify the recommendation result through the development component big data platform to obtain a verification result; Among them, the component recommendation neural network model is trained based on the diversified data, and the training results are input as the input object of the retrieval information; the recommendation results output by the component recommendation model are reversely input into the big data platform, and the recommendation results are verified based on the combined data set of the retrieval information and the final selected component information in the big data platform, and the verification results are obtained, wherein the verification results include qualified and unqualified.

6. The device according to claim 5, characterized in that The search information includes: search keywords generated by the user according to the search requirements.

7. The device according to claim 5, characterized in that The device further comprises: A training module is used to train a component recommendation model based on the diversified data.

8. The device according to claim 5, characterized in that The device further comprises: The sending module is used to send the recommendation result to the user terminal.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the method according to any one of claims 1 to 4.

10. An electronic device, characterized in that: The method comprises a processor and a memory; the memory stores computer-readable instructions, and the processor is used to execute the computer-readable instructions, wherein the computer-readable instructions execute the method according to any one of claims 1 to 4 when executed.

Images