Diffusion prediction method for dynamic characteristics of hyperbolic space modeling mining service node

Abstract

The invention discloses a hyperbolic space modeling mining service node dynamic feature diffusion prediction method comprising the following steps: S01, setting feature information, and setting a crawler capture period based on the feature information; s02, a prediction model is created according to the feature information, the prediction probability of the service provider is obtained, the prediction model is the feature information captured by multiple service providers, and multiple period sets A are formed; and S03, training the prediction model according to a plurality of period sets A to indicate a prediction probability corresponding to the feature information, the prediction probability being used for indicating a probability that each period set A is greater than a first preset threshold, and A being an integer greater than 0. According to the hyperbolic space modeling mining service node dynamic feature diffusion prediction method provided by the invention, service data prediction is carried out by comprehensively judging various feature information of a service provider sample in combination with periodic acquisition times, so that the accuracy of service data prediction is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a diffusion prediction method for mining dynamic characteristics of service nodes using hyperbolic space modeling. Background Art

[0002] When collecting data from the Internet of Things, the input method is used to input the features to be searched, and then the search program obtains the data of the corresponding features based on the entries for display.

[0003] As disclosed in Publication (Announcement) No.: CN101405731A, Publication (Announcement) Date: 2009-04-08, a system is disclosed that allows a query to be submitted to a query distribution server, and the query distribution server locates a manual searcher that can perform a search on the query. The searcher uses a conventional search tool such as a computer browser to perform the search, and the results are provided to the user through the system. A bonus is given to the searcher who produces a search accepted by the user. The results linked to the query can be stored in a database for use when another user submits a similar query in the future. The searcher is located by comparing the keywords of the query with the keywords that the searcher has registered to search for. The searcher selected by the system is a searcher that ranks well in the keywords of the query that match the keywords registered by the searcher, the searcher's previous successful searches, the speed of generating search results, and other factors that help provide users with a high-quality search and experience. The user is able to focus on the information provided to him during the execution of the search, such as videos, games, advertisements, etc. The information presented during the search can be based on the keywords of the query and can be specified by the searcher performing the search. Bonuses to searchers can be based on revenue from advertising.

[0004] As disclosed in the publication (announcement) number: CN101937433A, the publication (announcement) date: 2011-01-05, a real-time product search method is disclosed, which includes the following steps: (1) product index search: using a unified index structure, the index data is divided into two parts: fields and attributes. The field part includes the product name and product keyword data for which full-text search text content is required; the attribute part includes the product price, location and classification data for which screening content is required; (2) data query search: firstly, the variable segmentation method is used to segment the user keywords, then the syntax analysis engine is enabled to analyze, understand and filter the segmentation results, and finally the results are submitted to the search query device, which retrieves the analyzed keywords and returns the search results. The present invention can update the index data in real time, and provide full-text search based on keywords and screening based on attributes, so as to realize the accurate search function for products, and can be widely used in search fields with high search accuracy such as e-commerce search.

[0005] In the prior art including the above two patents, when retrieving terms through search engines, the most important thing is to extract the features of the terms. Different term analysis methods retrieve different given data. Therefore, how to extract features more accurately to provide faster retrieval convenience is expected to be well solved. Summary of the invention

[0006] The purpose of the present invention is to provide a diffusion prediction method for mining the dynamic characteristics of service nodes by hyperbolic space modeling, so as to solve the above problems.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a diffusion prediction method for mining the dynamic characteristics of service nodes by hyperbolic space modeling, comprising the following steps:

[0008] S01, setting characteristic information, and setting a crawler capture cycle based on the characteristic information;

[0009] S02, creating a prediction model based on the feature information to obtain a prediction probability of a service provider, wherein the prediction model is feature information captured by multiple service providers to form multiple period sets A;

[0010] S03, training the prediction model according to multiple period sets A to indicate the prediction probability corresponding to the feature information, wherein: the prediction probability is used to indicate the probability that each of the period sets A is greater than a first preset threshold, and A is an integer greater than 0;

[0011] S04. According to the prediction probability and the mapping relationship between the prediction probability and the predicted service times, determine the data changes of the multiple prediction models trained under the multiple period sets A, and display the data changes in execl form.

[0012] Preferably, before obtaining the predicted probability, the method further includes:

[0013] S05, obtaining the characteristic information in multiple periods and the number of collection times N of the service provider in each period;

[0014] S06, establishing a mapping relationship between feature information and N times of collection within a period;

[0015] S07. According to the mapping relationship between the feature information and the N times collected within a period, the prediction model is trained and acquired.

[0016] Preferably, according to the mapping relationship between the feature information and the N times collected in a period, the prediction model is trained and acquired, wherein the feature information of the plurality of service provider samples is divided according to the mapping relationship between the feature information and the N times collected in a period according to a preset feature information level;

[0017] At least includes first sample characteristic information and second sample characteristic information.

[0018] Preferably, the mapping relationship between the feature information and the N number of times collected in a period in step S04 includes the following steps:

[0019] S41, according to the preset initialized prediction model, calculation is performed to obtain the number of sample collection cycle cycles and the number of collection volumes for obtaining accurate prediction probability by providing characteristic data of each service provider;

[0020] S42, sorting the samples of the plurality of service providers according to the number of cycles of the sample collection period and the number of collection amounts;

[0021] S43, obtaining the number of times the multiple service providers collect samples according to the order of the samples of the multiple service providers;

[0022] S44. Obtain the number of period sets A according to the number of times N collected in each period when the service provider collects samples and preset rules.

[0023] Preferably, setting the characteristic information in step S01 includes:

[0024] S11, determine the feature type collection task;

[0025] S12, according to the feature identifier carried by the feature type collection task, determining the feature identifier corresponding to the feature type collection task from the started classification prediction service;

[0026] S13: predicting the feature type acquisition task through the feature identification.

[0027] Preferably, the feature type acquisition task in step S11 includes a plurality of acquisition objects to be classified, and the feature type acquisition task is predicted through the feature identification, including: batch acquisition of the plurality of acquisition objects to be classified through the feature identification.

[0028] Preferably, the feature type collection task in step S11 also includes a single collection object to be classified, by generating a single task identifier for each feature type collection task, and adding the identifier to a list of pending identifiers of a batch collection task, and then traversing the list of pending identifiers to obtain the collection object to be classified that needs to be processed by the feature type collection task corresponding to each table item, and the obtained multiple collection objects to be classified are collected in batches.

[0029] In the above technical scheme, the diffusion prediction method of a hyperbolic space modeling and mining dynamic characteristics of service nodes provided by the present invention has the following beneficial effects: through comprehensive evaluation of various characteristic information of service provider samples and combining the number of periodic collection times to predict service data, the accuracy of service data prediction is effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0031] Figure 1 A schematic diagram of the process structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments 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 creative work are within the scope of protection of the present invention.

[0033] Embodiment 1

[0034] like Figure 1 As shown, a diffusion prediction method for mining the dynamic characteristics of service nodes by hyperbolic space modeling includes the following steps:

[0035] S01, setting feature information, and setting a crawler capture cycle based on the feature information;

[0036] S02. Create a prediction model based on the feature information to obtain the prediction probability of the service provider, where the prediction model is feature information captured by multiple service providers to form multiple period sets A;

[0037] S03. Training the prediction model according to the multiple period sets A to indicate the prediction probability corresponding to the feature information, wherein the prediction probability is used to indicate the probability that each period set A is greater than a first preset threshold, and A is an integer greater than 0;

[0038] S04. According to the prediction probability and the mapping relationship between the prediction probability and the prediction service times, determine the data changes of multiple prediction models trained under multiple period sets A, and display the data changes in execl form.

[0039] Embodiment 2

[0040] Before getting the predicted probability, it also includes:

[0041] S05, obtaining feature information in multiple periods and the number of times N collected by the service provider in each period;

[0042] S06, establishing a mapping relationship between feature information and N times of collection within a period;

[0043] S07. According to the mapping relationship between the feature information and the N times collected within the period, a prediction model is trained and obtained.

[0044] Embodiment 3

[0045] According to the mapping relationship between the feature information and the N times collected in the cycle, the prediction model is trained and obtained. According to the mapping relationship between the feature information and the N times collected in the cycle, the feature information of multiple service provider samples needs to be divided according to the preset feature information level;

[0046] At least includes first sample characteristic information and second sample characteristic information.

[0047] Embodiment 4

[0048] In step S04, the mapping relationship between the characteristic information and the N number of times collected in the cycle includes the following steps:

[0049] S41, according to the preset initialized prediction model, calculation is performed to obtain the number of sample collection cycle cycles and the number of collection volumes for obtaining accurate prediction probability by providing feature data from each service provider;

[0050] S42, sorting the samples of multiple service providers according to the number of sample collection cycle cycles and the number of collection volumes;

[0051] S43, according to the order of the samples of the multiple service providers, to obtain the number of times the multiple service providers collect samples;

[0052] S44. Obtain the number of period sets A according to the number of times N collected in each period when the service provider collects samples and preset rules.

[0053] Embodiment 5

[0054] In step S01, characteristic information is set, including:

[0055] S11, determine the feature type collection task;

[0056] S12, according to the feature identifier carried by the feature type collection task, determining the feature identifier corresponding to the feature type collection task from the started classification prediction service;

[0057] S13. Predict the feature type acquisition task through feature identification.

[0058] Embodiment 6

[0059] In step S11, the feature type acquisition task includes a plurality of acquisition objects to be classified, and the feature type acquisition task is predicted through feature identification, including: batch acquisition of the plurality of acquisition objects to be classified through feature identification.

[0060] Embodiment 7

[0061] Step S11, the feature type collection task also includes a single collection object to be classified. By generating a single task identifier for each feature type collection task, and adding the identifier to the list of pending identifiers of the batch collection task, and then traversing the list of pending identifiers, the collection object to be classified that needs to be processed by the feature type collection task corresponding to each table item is obtained, and the obtained multiple collection objects to be classified are collected in batches.

[0062] In the above technology, the accuracy of service data prediction is effectively improved by comprehensively evaluating various feature information of service provider samples and combining the number of periodic collection times to perform service data prediction.

[0063] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0064] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0065] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0067] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0068] The embodiments of the present application also provide a specific implementation of an electronic device capable of implementing all steps of the method in the above embodiments, and the electronic device specifically includes the following contents:

[0069] Processor, memory, communications interface and bus;

[0070] Wherein, the processor, memory, and communication interface communicate with each other via the bus;

[0071] The processor is used to call the computer program in the memory, and when the processor executes the computer program, all the steps in the method in the above embodiment are implemented.

[0072] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps of the method in the above embodiments are implemented.

[0073] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Although the embodiment of this specification provides the method operation steps described in the embodiment or flow chart, more or less operation steps can be included based on conventional or non-creative means. The order of steps listed in the embodiment is only one way of executing the order of many steps, and does not represent the only execution order. When the device or terminal product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same one or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, 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 coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The present invention is described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the process and / or box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, the embodiments of this specification may be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment. In the description of this specification, the description of the reference term "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification.

[0075] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradicting each other. The above is only an embodiment of the embodiment of this specification and is not intended to limit the embodiment of this specification. For those skilled in the art, the embodiment of this specification may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of this specification shall be included in the scope of the claims of the embodiment of this specification.

Claims

1. A diffusion prediction method for mining the dynamic characteristics of service nodes using hyperbolic space modeling, characterized in that: The following steps are involved: S01, setting characteristic information, and setting a crawler capture cycle based on the characteristic information; S02, creating a prediction model based on the feature information to obtain a prediction probability of a service provider, wherein the prediction model is feature information captured by multiple service providers to form multiple period sets A; S03, training the prediction model according to multiple period sets A to indicate the prediction probability corresponding to the feature information, wherein: the prediction probability is used to indicate the probability that each of the period sets A is greater than a first preset threshold, and A is an integer greater than 0; S04. According to the prediction probability and the mapping relationship between the prediction probability and the predicted service times, determine the data changes of the multiple prediction models trained under the multiple period sets A, and display the data changes in execl form.

2. According to claim 1, a diffusion prediction method for mining service node dynamic characteristics by hyperbolic space modeling is characterized in that: Before obtaining the predicted probability, the method further includes: S05, obtaining the characteristic information in multiple periods and the number of collection times N of the service provider in each period; S06, establishing a mapping relationship between feature information and N times of collection within a period; S07. According to the mapping relationship between the feature information and the N times collected within a period, the prediction model is trained and acquired.

3. According to claim 2, a diffusion prediction method for mining service node dynamic characteristics by hyperbolic space modeling is characterized in that: According to the mapping relationship between the feature information and the N times collected in the period, the prediction model is trained and obtained, wherein the feature information of the plurality of service provider samples is divided according to the mapping relationship between the feature information and the N times collected in the period according to the preset feature information level; At least includes first sample characteristic information and second sample characteristic information.

4. According to claim 1, a diffusion prediction method for mining service node dynamic characteristics by hyperbolic space modeling is characterized in that: The step S04 includes the following steps based on the mapping relationship between the feature information and the N number of times collected within a period: S41, according to the preset initialized prediction model, calculation is performed to obtain the number of sample collection cycle cycles and the number of collection volumes for obtaining accurate prediction probability by providing characteristic data of each service provider; S42, sorting the samples of the plurality of service providers according to the number of cycles of the sample collection period and the number of collection amounts; S43, obtaining the number of times the multiple service providers collect samples according to the order of the samples of the multiple service providers; S44. Obtain the number of period sets A according to the number of times N collected in each period when the service provider collects samples and preset rules.

5. According to claim 1, a diffusion prediction method for mining service node dynamic characteristics by hyperbolic space modeling is characterized in that: The step S01 of setting characteristic information includes: S11, determine the feature type collection task; S12, according to the feature identifier carried by the feature type collection task, determining the feature identifier corresponding to the feature type collection task from the started classification prediction service; S13: predicting the feature type acquisition task through the feature identification.

6. The diffusion prediction method of mining service node dynamic characteristics by hyperbolic space modeling according to claim 5 is characterized in that: The feature type acquisition task in step S11 includes a plurality of acquisition objects to be classified, and the feature type acquisition task is predicted through the feature identification, including: batch acquisition of the plurality of acquisition objects to be classified through the feature identification.

7. The diffusion prediction method of mining service node dynamic characteristics by hyperbolic space modeling according to claim 5 is characterized in that: The step S11 feature type acquisition task also includes a single collection object to be classified. A single task identifier is generated for each feature type acquisition task, and the identifier is added to a list of pending identifiers of a batch acquisition task. Then, the list of pending identifiers is traversed to obtain the collection object to be classified that needs to be processed by the feature type acquisition task corresponding to each entry, and the obtained multiple collection objects to be classified are collected in batches.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the visual positioning method based on local variance and posterior probability classifier according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the visual positioning method based on local variance and posterior probability classifier described in any one of claims 1 to 7 are implemented.

Images