CN114781717A - Network point equipment recommendation method, device, equipment and storage medium - Google Patents
Network point equipment recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114781717A CN114781717A CN202210409382.8A CN202210409382A CN114781717A CN 114781717 A CN114781717 A CN 114781717A CN 202210409382 A CN202210409382 A CN 202210409382A CN 114781717 A CN114781717 A CN 114781717A
- Authority
- CN
- China
- Prior art keywords
- equipment
- busy value
- busy
- value
- power consumption
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a website device recommendation method, a website device recommendation device, a computer device and a storage medium. According to the method and the system, the optimal network point equipment can be recommended for the user based on the network point equipment operation power consumption information, the network point pedestrian flow and the distance between the user and the network point, the power consumption level of each network point can be considered, and the effects of energy conservation and emission reduction can be achieved while the network point service processing efficiency is improved. The method comprises the following steps: responding to a network node device search request of a user terminal, and acquiring position information of the user terminal, device power consumption information corresponding to a plurality of candidate network node devices and people flow data; acquiring a device busy value of the network point device according to the device running power consumption information; inputting the position information of the user terminal, the equipment busy value and the people flow data of each site equipment into a pre-trained equipment resource distribution model to obtain the optimal site equipment determined by the equipment resource distribution model from a plurality of site equipment; and returning the equipment information of the optimal network point equipment to the user terminal.
Description
Technical Field
The present application relates to the field of internet of things technologies, and in particular, to a network point device recommendation method and apparatus, a computer device, a storage medium, and a computer program product.
Background
With the development of information technology, all industries are gradually deepened towards digitization, automation and intellectualization. In financial business services, such as bank outlets, currently, according to the density of people streams and the level of user evaluation, business outlets which are close in distance, relatively idle or have a good public praise can be recommended to users through application software, so that the utilization rate of the outlet resources can be improved while the quality of service is ensured.
However, the service resource allocation methods provide more and more convenient services for users from the perspective of serving the users, but with the development of energy saving, emission reduction, cost reduction, efficiency improvement and carbon neutralization measures, under the goal of resource optimization configuration of network nodes, network node resource reduction for reducing power consumption often occurs, and further, the network node resources are busy, under such a circumstance, the service resource allocation methods cannot give consideration to the power consumption level of each network node, only recommend services for users according to the people flow density and public praise, and cannot balance the problem of uneven equipment resource allocation.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a website device recommendation method, apparatus, computer device and computer readable storage medium.
In a first aspect, the present application provides a website device recommendation method. The method comprises the following steps:
responding to a network node device search request of a user terminal, and acquiring position information of the user terminal, device power consumption information corresponding to a plurality of candidate network node devices and people flow data;
acquiring a device busy value of the network point device according to the device running power consumption information;
inputting the position information of the user terminal, the equipment busy value and the people flow data of each site equipment into a pre-trained equipment resource allocation model to obtain the optimal site equipment determined by the equipment resource allocation model from a plurality of site equipment;
and returning the equipment information of the optimal network point equipment to the user terminal.
In one embodiment, the inputting the location information of the user terminal and the device busy values and the traffic data of the respective website devices into a pre-trained device resource allocation model includes:
calculating a positive ideal value and a negative ideal value of the mesh point equipment through a good-bad solution distance model;
determining equipment evaluation indexes of the mesh point equipment according to the positive ideal value and the negative ideal value of the mesh point equipment;
sorting the plurality of mesh point devices according to respective device evaluation indexes of the plurality of mesh point devices;
and inputting the position information of the user terminal, the sequenced multiple website devices and the people flow data of each website device into a pre-trained device resource allocation model.
In one embodiment, the method further comprises:
acquiring training sample data; the training sample data comprises a device busy value sample set, a position information sample set of a user terminal, a regional people stream state sample set and a historical optimal network point device identification sample set;
performing multi-round training on a random forest model by using the training sample data, and adjusting a random forest parameter combination until the classification accuracy reaches the highest to obtain an optimal random forest parameter combination;
and constructing and obtaining the pre-trained equipment resource distribution model according to the optimal random forest parameter combination.
In one embodiment, the obtaining a device busy value of the mesh point device according to the device operation power consumption information includes:
acquiring a plurality of busy value influence factors and acquiring a factor weight list of the busy value influence factors; the factor weight list records a factor weight vector corresponding to each mesh point device, and the factor weight vector comprises respective weights of the busy value influence factors;
obtaining busy value influence factor values corresponding to busy value influence factors of the mesh point equipment according to the equipment power consumption information of the mesh point equipment;
constructing a decision matrix based on the busy value influence factor values of all the network point devices;
and obtaining the equipment busy value of each mesh point equipment according to the factor weight list and the decision matrix.
In one embodiment, the obtaining the factor weight list of the busy value influence factors includes:
acquiring the importance degree values of the busy value influence factors aiming at each mesh point device, and determining an influence factor weight vector of each busy value influence factor according to the importance degree values of the busy value influence factors;
and constructing a factor weight list based on a plurality of influence factor weight vectors of each mesh point device.
In one embodiment, the determining an influence factor weight vector for each busy value influence factor according to the importance degree values of the busy value influence factors includes:
acquiring judgment tables corresponding to the busy value influence factors; the judgment table records an importance degree value of one busy value influence factor relative to any other busy value influence factor in the busy value influence factors;
for each busy value influence factor, carrying out normalization calculation on a plurality of importance degree values associated with the busy value influence factor to obtain the weight of the busy value influence factor;
and constructing an influence factor weight vector of each mesh point device through the weight of each busy value influence factor.
In one embodiment, the busy value impact factor comprises a current traffic busy value gain; the method further comprises the following steps:
acquiring current service calling increment and service historical processing speed of each network point device;
and for each network node device, weighting the current service calling increment and the service historical processing speed to obtain the gain of the busy value of the current service of each network node device.
In a second aspect, the application further provides a website device recommendation apparatus. The device comprises:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for responding to a website equipment search request of a user terminal and acquiring position information of the user terminal, equipment power consumption information corresponding to a plurality of candidate website equipment and people flow data;
the equipment busy value acquisition module is used for acquiring the equipment busy value of the network point equipment according to the equipment running power consumption information;
the optimal network node equipment determining module is used for inputting the position information of the user terminal, equipment busy values and people flow data of each network node equipment into a pre-trained equipment resource allocation model to obtain the optimal network node equipment determined by the equipment resource allocation model from a plurality of network node equipment;
and the equipment information returning module is used for returning the equipment information of the optimal network point equipment to the user terminal.
In a third aspect, the present application also provides a computer device. The computer equipment comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps in the website equipment recommendation method embodiment when executing the computer program.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer readable storage medium stores thereon a computer program, and the computer program, when executed by a processor, implements the steps in the website device recommendation method embodiment.
According to the network equipment recommendation method, the network equipment recommendation device, the computer equipment and the storage medium, the position information of the user terminal, the equipment power consumption information corresponding to a plurality of candidate network equipment and the people flow data are obtained by responding to the network equipment search request of the user terminal; acquiring a device busy value of the network point device according to the device running power consumption information; inputting the position information of the user terminal, the equipment busy value and the people flow data of each network point equipment into a pre-trained equipment resource allocation model to obtain the optimal network point equipment determined by the equipment resource allocation model from a plurality of network point equipment; and returning the equipment information of the optimal network point equipment to the user terminal. The method and the system can recommend the optimal network point equipment for the user based on the network point equipment operation power consumption information, the network point pedestrian volume and the distance between the user and the network point, and compared with the traditional method that the service is recommended for the user only aiming at the pedestrian flow density and the network point business public praise, the method and the system can give consideration to the power consumption level of each network point, improve the network point business processing efficiency and simultaneously can achieve the effects of energy conservation and emission reduction.
Drawings
FIG. 1 is a diagram of an application environment of a website device recommendation method in one embodiment;
FIG. 2 is a flowchart illustrating a website device recommendation method in one embodiment;
FIG. 3 is a block diagram showing an overall architecture of a website device recommendation method in one embodiment;
FIG. 4 is a network diagram of a website device recommendation method in another embodiment;
FIG. 5 is a block diagram of a website device recommendation apparatus in one embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The website device recommendation method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 101 communicates with the server 102 via a network. The data storage system may store data that the server 102 needs to process. The data storage system may be integrated on the server 102, or may be located on the cloud or other network server. The terminal 101 may be but not limited to various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 102 may be implemented as a stand-alone server or a server cluster comprising a plurality of servers.
In one embodiment, as shown in fig. 2, a website device recommendation method is provided, which is described by taking the method as an example applied to the server 102 in fig. 1, and includes the following steps:
step S201, responding to a website device search request of a user terminal, and acquiring position information of the user terminal, device power consumption information corresponding to a plurality of candidate website devices and people flow data;
the website device search request refers to a request for searching a service website initiated by a user on a terminal device, for example, if the user wants to deposit or withdraw money, an ATM (automatic Teller Machine) search request needs to be sent out, or if the user needs to transact a bank card, the user needs to search for a card opener. The network point equipment is the equipment such as the ATM or the card issuer required by the user. The device power consumption information refers to information such as current device power consumption (power consumption), device rated power, device historical power consumption and the like of each device; the people flow data refers to the service transacted people flow data of each network node device, and can be determined according to the number of people currently transacting the service in queue, or can be determined according to the average value of historical data.
Specifically, when a user searches for an ATM device on a user terminal, such as a mobile phone, a server receives a network node device search request sent by the user, obtains location information of the user terminal according to location information of the user terminal, searches for all network node devices within a certain distance range from the user terminal according to the location information, uses the network node devices as candidate network node devices, and obtains device power consumption information and people flow information corresponding to the candidate network node devices, where the device power consumption information may include current device power consumption, device rated power, device historical power consumption, device power consumption average value of the same type, device power consumption maximum value of the same type, current busy service value gain, and the like, and as shown in fig. 3, this embodiment may obtain and count device power consumption information through a power consumption monitoring module.
Step S202, acquiring a device busy value of the network point device according to the device running power consumption information;
specifically, the device busy value refers to a device busy level calculated from the power consumption of the device. In this embodiment, the device running power consumption information is converted into the device busy value through the adaptive busy value quantization sorting model, as shown in fig. 3, fig. 3 shows an overall architecture diagram of the method, the method is implemented by the modules shown in fig. 3, and the method mainly includes two modules, respectively: the device comprises a power consumption monitoring module and a device resource allocation module. The power consumption monitoring module comprises networking equipment, power consumption monitoring equipment and a power consumption collecting platform; the device resource allocation module comprises a self-adaptive busy value quantization and sorting model and a device resource allocation model, wherein the self-adaptive busy value quantization and sorting model carries out unified quantization and sorting on the power consumption conditions of different devices by using an analytic hierarchy process and a good-and-bad solution distance algorithm; and the equipment resource allocation model performs allocation recommendation of the intelligent website resource equipment by using an efficient and simple random forest algorithm and combining the quantified busy value sequencing.
In the step S202, the device power consumption information is converted into the device busy values of the devices of each node mainly through the adaptive busy value quantization and sorting model, and it should be emphasized that the model calculates and sorts the busy values of similar devices requested by the user each time, for example, if the user requests an ATM, the model calculates and sorts all ATM in the candidate nodes.
Step S203, inputting the position information of the user terminal, the equipment busy value and the people flow data of each site equipment into a pre-trained equipment resource distribution model to obtain the optimal site equipment determined by the equipment resource distribution model from a plurality of site equipment.
The optimal network equipment is comprehensively balanced according to the three dimensions, so that the distance is as close as possible, the people flow data is as little as possible, the busy value of the equipment is as small as possible, and the network equipment which is most suitable for the current user is obtained.
Specifically, the equipment resource allocation model uses an efficient and simple random forest algorithm to classify and sort the equipment busy values, the people flow data and the distances between the user terminals and the network point equipment of the network point equipment to obtain the optimal network point equipment.
Step S204, returning the device information of the optimal network point device to the user terminal.
Specifically, it is possible to select a Media Access Control (MAC) Address of the mesh point device as the device unique identifier, and transmit the device unique identifier and the device Address as device information to the user terminal.
In the embodiment, the position information of the user terminal, the equipment power consumption information corresponding to a plurality of candidate website equipment and the people flow data are obtained by responding to the website equipment search request of the user terminal; acquiring a device busy value of the network point device according to the device running power consumption information; inputting the position information of the user terminal, the equipment busy value and the people flow data of each network point equipment into a pre-trained equipment resource allocation model to obtain the optimal network point equipment determined by the equipment resource allocation model from a plurality of network point equipment; and returning the equipment information of the optimal network point equipment to the user terminal. The method and the system can recommend the optimal network point equipment for the user based on the network point equipment operation power consumption information, the network point pedestrian volume and the distance between the user and the network point, and compared with the traditional method that the service can be recommended for the user only aiming at the pedestrian flow density and the network point service public praise, the method and the system can give consideration to the power consumption level of each network point, improve the network point service processing efficiency and achieve the effects of energy conservation and emission reduction.
In an embodiment, the step S203 includes: determining a positive ideal value and a negative ideal value corresponding to the busy value influence factor combination of the screen point equipment; calculating equipment evaluation indexes of the mesh point equipment according to a first distance between the busy value influence factor combination of the mesh point equipment and the positive ideal value and a second distance between the busy value influence factor combination of the mesh point equipment and the negative ideal value; sorting the plurality of mesh point devices according to respective device evaluation indexes of the plurality of mesh point devices; and inputting the position information of the user terminal, the sequenced plurality of network point devices and the pedestrian flow data of each network point device into a pre-trained device resource allocation model.
The good and bad solution distance model is also called a good and bad solution distance method or an ideal solution method, and is an effective multi-index evaluation method. The method constructs a positive ideal solution and a negative ideal solution of the evaluation problem, wherein the positive ideal solution means that each index is supposed to reach a theoretical optimal value, so that the problem to be solved reaches an ideal optimal state; the negative ideal solution means that all indexes are assumed to reach the theoretical worst value, so that the problem to be solved reaches the theoretical worst state. The actual solutions are ranked by calculating the relative closeness of each solution to the ideal solution, i.e., the degree of closeness to the positive ideal solution and distancing from the negative ideal solution, to select the optimal solution. It is generally necessary to construct a proximity coefficient for each specific problem, which is an equipment evaluation index for evaluating the degree to which the actual index is close to the positive ideal solution and away from the negative ideal solution. The busy value influence factor combination is a plurality of preset busy value influence factors, and comprises one or more of current equipment power consumption (electric power consumption), equipment rated power, equipment historical power consumption, the average value of the power consumption of the same equipment, the maximum value of the power consumption of the same equipment and the gain of the busy value of the current service.
Specifically, for a certain network point device i, a group of busy value influence factor combinations needs to be found by combining the parameters of the device, the historical statistical parameters of similar devices and the service characteristics, so that the network point device can reach the theoretical most busy state, and the busy value influence factor combinations are called positive ideal values of the network point device i; correspondingly, if a group of busy value influence factor combinations is found, so that the mesh point device can reach the theoretical most idle state, the busy value influence factor combinations are called as the negative ideal values of the mesh point device i. The distance from the busy value influence factor combination actual value of each mesh point device to the positive ideal value and the negative ideal value can be calculated by the following formula:
wherein, the first and the second end of the pipe are connected with each other,
combining a first distance from the busy value impact factor of the ith mesh point device to a positive ideal value;
a positive ideal value for the jth busy value impact factor; u. ofijThe actual value of the j busy value influence factor of the ith mesh point device;
a second distance for combining the busy value influence factor of the ith mesh point device to a negative ideal value;
a negative ideal value of the factor is affected for the jth busy value. In this embodiment, the busy value influence factor combination may include one or more of current device power consumption (power consumption), device rated power, device historical power consumption, average of similar device power consumption, maximum of similar device power consumption, and current traffic busy value gain.
Then, the equipment evaluation index alpha of the ith network point equipment is calculated by using a preset equipment evaluation index calculation formulai：
And sequencing the plurality of website equipment according to the equipment evaluation index of each website equipment, inputting the position information of the user terminal, the sequenced plurality of website equipment and the people flow data of each website into a pre-trained equipment resource allocation model for classification and selection, and finally obtaining the optimal website equipment.
In the embodiment, the busy values of the plurality of network point devices are sorted by the distance method of good and bad solutions, and the sorting can be adaptively realized for the network point devices in the vicinity area around each user terminal based on the multi-index evaluation mode, so that a data basis is provided for obtaining the optimal network point devices by subsequent distribution and screening, and the efficiency of subsequent classification and screening is further improved.
In an embodiment, the method further includes: acquiring training sample data; the training sample data comprise a single busy value sample set of equipment, a position information sample set of a user terminal, a regional people stream state sample set and a historical optimal network point equipment identification sample set; performing multi-round training on the random forest model by using training sample data, and adjusting random forest parameter combinations until the classification accuracy reaches the highest to obtain the optimal random forest parameter combination; and constructing and obtaining a pre-trained equipment resource distribution model according to the optimal random forest parameter combination.
Specifically, in the embodiment, a random forest algorithm is used, and the factors of the busy values of the devices of a plurality of candidate website devices, the flow information of the website people and the distance between the client and each website device are combined to decide whether the website is recommended to the user for service handling.
Further specifically, the problem of whether the website equipment is recommended to the user is converted into a two-Classification problem of the random forest, And a CART (Classification And Regression Trees) decision tree is selected to construct the random forest for two-Classification judgment. There are three main factors affecting random forest generation: the number of features c in each decision tree, the number of decision trees m and the minimum leaf node number l of the decision trees. In order to determine the optimal values of c, m and l, three values are respectively extracted from the selectable values of c, m and l to combine the random forest parameters of the round, and a random forest consisting of m trees is generated according to the values of the selected parameters.
And taking a busy value sample set, a position information sample set of a user terminal and a regional pedestrian flow state sample set as the input of a random forest, outputting the model as the equipment information (such as equipment identification) of the optimal network point equipment, adjusting model parameters c, m and l until the output result is the equipment information sample of the historical optimal network point, and finally obtaining the trained equipment resource allocation model. And (3) deciding by m decision trees by combining the marked training data, and finally determining whether the node equipment is recommended to a customer, wherein the classification effect of the random forest generated by each round of selection of model parameters c, m and l is evaluated by the following formula in the training process.
Wherein Q represents the accuracy of the second classification, P represents the number of positive samples (the input samples corresponding to the device information of the historical optimal halftone dot device are positive samples), N represents the number of negative samples (the input samples not corresponding to the device information of the historical optimal halftone dot device are negative samples), TP represents the number of positive samples correctly determined in each round of training, and TN represents the number of negative samples correctly determined in each round of training.
The training sample data is obtained by statistics of historical data of actual network points, and a corresponding relation is formed by busy values of network point equipment, pedestrian flow states of areas where the network points are located, distances between users and the network point equipment and network point equipment lists finally selected by the users. Each round of samples are extracted from the training sample data set in a mode of sampling with a return, m rounds of extraction are carried out to respectively train m decision trees, and then the training set extracted in each round is T1,T2,…,Tm. And (4) carrying out circular training to finally obtain model parameters c, m and l corresponding to the highest Q value, namely the optimal values of the parameters. And constructing a trained equipment resource allocation model by using the optimal value.
According to the embodiment, the model is trained by using the training sample set to obtain the trained equipment resource allocation model, so that the subsequent screening of the optimal network point equipment is facilitated.
In an embodiment, the step S202 includes: acquiring a plurality of busy value influence factors and acquiring a factor weight list of the busy value influence factors; the factor weight list records a factor weight vector corresponding to each mesh point device, and the factor weight vector comprises respective weights of the busy value influence factors; acquiring busy value influence factor values corresponding to busy value influence factors of the network point equipment according to the equipment power consumption information of the network point equipment; constructing a decision matrix based on busy value influence factor values of all the network point devices; and obtaining the equipment busy value of each net point equipment according to the factor weight list and the decision matrix.
The busy value influence factors comprise current equipment power consumption, equipment rated power, historical equipment power consumption, the average power consumption of similar equipment, the maximum power consumption of similar equipment and the gain of the busy value of the current service. For each mesh point device, these 6 evaluation coefficients are selected as the basis for the busy value of the subsequent computing device. Each mesh point device has 6 busy value impact factor parameter values, denoted as eijA j busy value impact factor parameter value representing an i mesh point device; j ═ 1,2,3 … … 6; assuming h candidate mesh point devices in total, the busy value influence factor parameter values of the h candidate mesh point devices are constructed into a multi-attribute decision matrix E ═ (E)ij)h×6Wherein e isijA jth busy value impact factor parameter value representing an ith mesh point device, and h representing a number of mesh point devices.
Specifically, first, a plurality of busy value influence factors, i.e., the above 6 busy value influence factors, are determined; then, the weights of the busy value influence factors are obtained to form a factor weight list M ═ M1,M2,…,Mh-1,MhIn which MhFactor weight vector representing h-th screen point device, each factor weight vector including factor weight of the 6 busy value influence factors, namely Mh＝[ω1，ω2，…ωn]TIn this embodiment, n may be 6, indicating that there are 6 busy value effects in totalA factor.
Then, busy value influence factor values corresponding to busy value factors of the mesh point devices are calculated according to the device power consumption information of the mesh point devices, and the multi-attribute decision matrix E is constructed and obtained based on the busy value influence factor values (E ═ E-ij)h×6Also called decision matrix E, where EijThe j busy value of the ith screen point device is represented by the influence factor value, and h represents the number of screen point devices.
Performing a dot product operation on the factor weight list M and the decision matrix E to obtain a busy matrix U (U ═ U)i)hWherein u isi＝ei·M，uiA device busy value representing the ith mesh point device.
In the embodiment, the busy value of each mesh point device is obtained through calculation by obtaining the busy value influence factor parameter value of each mesh point device and the weight of each busy value influence factor, so as to lay a data base for subsequently screening the optimal mesh point device.
In an embodiment, the determining a weight vector of an influence factor of each busy value influence factor according to the importance level values of the busy value influence factors includes: acquiring judgment tables corresponding to a plurality of busy value influence factors; the judgment table records the importance degree value of one busy value influence factor relative to any other busy value influence factor in the busy value influence factors; for each busy value influence factor, carrying out normalization calculation on a plurality of importance degree values associated with the busy value influence factor to obtain the weight of the busy value influence factor; and constructing an influence factor weight vector of each mesh point device through the weight of each busy value influence factor.
Specifically, in order to better utilize 6 different busy value influence factors, the weights among the factors are determined by adopting a consistent matrix method, and the core of the consistent matrix method is that different factors are compared with each other, but not all factors are compared. The consistency matrix method is commonly used in a hierarchical analysis model, and according to the thinking of the hierarchical analysis method, the method solves the following problems: selecting the network node equipment which is most suitable for accessing the service in a certain time period, namely the network node equipment with the lowest busy value, and splitting a scheme layer, a criterion layer and a target layer, wherein the target layer is the network node equipment with the lowest busy value in a certain time period; the scheme layer comprises a plurality of network point devices, such as an intelligent terminal device 1 of a network point A, an intelligent terminal device 2 of a network point A and an intelligent terminal device 1 of a network point B (the unique mark of the device can be distinguished by using the MAC address of the device, and the use sequence number is used for facilitating the description of the invention case); the running power consumption of the device under different conditions is different, and if the requested service network IO (Input/Output) requests more, the power consumption may be more reflected in the overhead of the network IO; if the requested service requires printing information, power consumption may be more reflected in the operation of hardware devices, etc., and according to this feature, a conversion relationship between power consumption and busy values may be established. Because different service types operated by the same equipment can have different influences on the busy value, if the influence of the simple query service on the busy value of the equipment is not large, and if the complex service relates to operations such as networking check, face detection and the like, the influence of the busy value of the equipment is larger; and considering the loss condition of the device, the old device may have a busy state for simple service, so the rule layer setting for determining the influence factor of the busy value of the device needs to take these conditions into consideration. According to actual service investigation, the current equipment power consumption, the equipment rated power, the historical equipment power consumption, the current average value of the same type of equipment power consumption, the current maximum value of the same type of equipment power consumption and the current busy value gain of the service are introduced as the influence factors for judging the busy value. Data such as the power consumption condition of the device needs to be obtained from a power consumption monitoring module (such as the power consumption monitoring module shown in fig. 3), and the rated power needs to refer to the production description and the historical power consumption condition of the device.
For further explanation, as shown in fig. 4, fig. 4 shows a network relationship diagram of a network device recommendation method, and the power consumption monitoring module mainly includes a smart network device, a power consumption monitoring socket, a Long Range Radio (Long Range Radio, short for Long distance Radio) data collection network, a WiFi/private line communication network, and a monitoring platform. The power consumption monitoring socket is connected with the smart network point equipment, and the effect of monitoring the power consumption of the equipment can be achieved with low hardware intrusion degree; the LoRa data collection network utilizes the characteristic that the signal coverage range of the LoRa base station is wide, has great advantage for signal transmission with small data quantity, and the power consumption monitoring socket is embedded with the LoRa node and can transmit power consumption data to the LoRa base station; the LoRa base station collects power consumption information to the power consumption monitoring platform in a WiFi or private line network mode, and the power consumption monitoring platform analyzes, counts and stores data.
In this embodiment, a nine-level scale may be used to effectively reduce the difficulty of comparing different factors with different attributes, thereby improving accuracy. As shown in Table 1 below, each numerical value in Table 1 represents the importance level value of the horizontal axis influence factor to the vertical axis influence factor, the importance level value increases from 1 to 9 in turn, and if the numerical value is a score, the importance level value represents the unimportance degree of the horizontal axis influence factor to the vertical axis influence factor and decreases from 1/9 to 1 in turn. The parameters in table 1 take into account the weights between the different influencing factors. The two factors of the current business busy value gain and the current equipment power consumption are two most important parameters for determining the equipment busy value.
TABLE 1 judgment Table
Firstly, the above-mentioned judgment table is obtained, the numerical values therein can be set manually according to actual needs, and nine-level scale auxiliary calculation can also be used.
And calculating the normalized importance degree value of each busy value influence factor according to the importance degree values in the judgment table, wherein the calculation formula is as follows:
wherein r isijThe importance of the importance value in the above judgment table, i.e. the importance of the ith busy value influence factor relative to the jth busy value influence factorA value of the metric; n is the total number of classes of busy impact factors, e.g., in this embodiment, n is 6. k is 1,2,3 … …; omegaiThe normalized importance degree value of the ith busy value influence factor is the weight of the busy value influence factor. Aiming at each mesh point device h, the weight of each busy value influence factor is combined to form an influence factor weight vector M of the mesh point device hh＝[ω1，ω2，…ωn]TN is the total number of classes of the busy value influencing factor, for example, in the present embodiment, n may be 6.
According to the embodiment, the weight of each busy value influence factor is calculated by combining a hierarchical analysis model and a consistency matrix method, and a data basis is provided for the follow-up calculation of the busy value of each net point device.
In one embodiment, the busy value impact factor includes a current traffic busy value gain, and the method further includes: acquiring current service calling increment and service historical processing speed of each network point device; and for each node device, weighting the current service calling increment and the historical service processing speed to obtain the gain of the busy value of the current service of each node device.
Specifically, the gain of the current service busy value needs to be determined by the service call increment and the service historical processing speed, and the main calculation formula is as follows:
Bi＝βjN_addi+βkSi
wherein, BiA busy value gain parameter of the ith network point device represents the increment of the service calling amount of the network point device, for example, the service increment of an ATM at 5-6 o' clock at night is obviously increased compared with the service increment at noon; n _ addiCalling increment, beta, for the service of the ith network point devicejWeight of traffic call volume for ith network point device, SiFor the historical processing speed, beta, of the service of the ith network point equipmentkAnd processing the weight of the average value of the speed for the service history of the ith mesh point equipment. For a network node device with less calling increment, there may be sporadic service demands in a day, and therefore, the network node device corresponds to the network node deviceThe busy value gain of the equipment is low, and for the core business of promotion or stock, the busy value gain of the equipment is high. For the historical processing speed of the device, if the historical processing speed is higher, the gain of the busy value of the service corresponding to the mesh point device is lower. The relevant weight parameters need to be determined by repeated experiments in combination with the running conditions of the mesh points.
According to the embodiment, the current business busy value gain is selected as one of the busy value influence factors, so that the website equipment recommendation method can recommend the appropriate website equipment to the user more pertinently and more accurately in combination with the business scene characteristics.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the application also provides a website device recommendation device for implementing the website device recommendation method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so the specific limitations in one or more embodiments of the website device recommendation device provided below may refer to the limitations on the website device recommendation method in the above description, and are not described herein again.
In one embodiment, as shown in fig. 5, there is provided a website device recommending apparatus 500, including: a data obtaining module 501, a device busy value obtaining module 502, an optimal mesh point device determining module 503, and a device information returning module 504, wherein:
a data obtaining module 501, configured to respond to a website device search request of a user terminal, and obtain location information of the user terminal, device power consumption information corresponding to multiple candidate website devices, and people flow data;
a device busy value obtaining module 502, configured to obtain a device busy value of the mesh point device according to the device running power consumption information;
an optimal mesh point device determining module 503, configured to input the location information of the user terminal, the device busy values of each mesh point device, and the people flow data into a pre-trained device resource allocation model, so as to obtain an optimal mesh point device determined by the device resource allocation model from multiple mesh point devices;
a device information returning module 504, configured to return the device information of the optimal mesh point device to the user terminal.
In one embodiment, the optimal mesh point device determining module 503 is further configured to:
calculating a positive ideal value and a negative ideal value of the mesh point equipment through a good-bad solution distance model; determining equipment evaluation indexes of the website equipment according to the positive ideal value and the negative ideal value of the website equipment; the method comprises the steps of sequencing a plurality of mesh point devices according to respective device evaluation indexes of the mesh point devices; and inputting the position information of the user terminal, the sequenced plurality of network point devices and the pedestrian flow data of each network point device into a pre-trained device resource allocation model.
In one embodiment, device busy value obtaining module 502 is further configured to:
acquiring a plurality of busy value influence factors and acquiring a factor weight list of the busy value influence factors; the factor weight list records a factor weight vector corresponding to each mesh point device, and the factor weight vector comprises respective weights of the busy value influence factors; obtaining busy value influence factor values corresponding to busy value influence factors of the mesh point equipment according to the equipment power consumption information of the mesh point equipment; constructing a decision matrix based on busy value influence factor values of all the network point devices; and obtaining the equipment busy value of each mesh point equipment according to the factor weight list and the decision matrix.
In one embodiment, the device busy value obtaining module 502 is further configured to:
aiming at each mesh point device, obtaining the importance degree values of the busy value influence factors, and determining an influence factor weight vector of each busy value influence factor according to the importance degree values of the busy value influence factors;
and constructing a factor weight list based on a plurality of influence factor weight vectors of each mesh point device.
In one embodiment, the device busy value obtaining module 502 is further configured to:
acquiring a judgment table corresponding to the busy value influence factors; the judgment table records the importance degree value of one busy value influence factor relative to any other busy value influence factor in the busy value influence factors;
for each busy value influence factor, carrying out normalization calculation on a plurality of importance degree values associated with the busy value influence factor to obtain the weight of the busy value influence factor;
and constructing an influence factor weight vector of each mesh point device according to the weight of each busy value influence factor.
In one embodiment, the system further includes a device resource allocation model training unit, configured to:
acquiring training sample data; the training sample data comprise a device busy value sample set, a position information sample set of a user terminal, a regional people stream state sample set and a historical optimal network point device identification sample set; performing multi-round training on a random forest model by using the training sample data, and adjusting random forest parameter combinations until the classification accuracy reaches the highest to obtain an optimal random forest parameter combination; and constructing and obtaining the pre-trained equipment resource distribution model according to the optimal random forest parameter combination.
In one embodiment, the busy value impact factor comprises a current traffic busy value gain; the optimal mesh point device determining module 503 is further configured to:
acquiring current service calling increment and service historical processing speed of each network point device; and for each network node device, weighting the current service calling increment and the service historical processing speed to obtain the gain of the busy value of the current service of each network node device.
All or part of the modules in the website equipment recommending device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing data such as the running power consumption information of the network node equipment. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a website device recommendation method.
The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the website device recommendation method embodiment when executing the computer program.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps in the foregoing website device recommendation method embodiments.
In one embodiment, a computer program product is provided, which includes a computer program that when executed by a processor implements the steps of the above-described website device recommendation method embodiments.
It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include a Read-Only Memory (ROM), a magnetic tape, a floppy disk, a flash Memory, an optical Memory, a high-density embedded nonvolatile Memory, a resistive Random Access Memory (ReRAM), a Magnetic Random Access Memory (MRAM), a Ferroelectric Random Access Memory (FRAM), a Phase Change Memory (PCM), a graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the various embodiments provided herein may be, without limitation, general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, or the like.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims (10)
1. A website device recommendation method, the method comprising:
responding to a network node device search request of a user terminal, and acquiring position information of the user terminal, device power consumption information corresponding to a plurality of candidate network node devices and people flow data;
acquiring a device busy value of the network point device according to the device operation power consumption information;
inputting the position information of the user terminal, the equipment busy value and the people flow data of each site equipment into a pre-trained equipment resource allocation model to obtain the optimal site equipment determined by the equipment resource allocation model from a plurality of site equipment;
and returning the equipment information of the optimal network point equipment to the user terminal.
2. The method of claim 1, wherein inputting the location information of the user terminal and the device busy value and the traffic data of each website device into a pre-trained device resource allocation model comprises:
determining a positive ideal value and a negative ideal value corresponding to the busy value influence factor combination of the screen point equipment;
calculating a device evaluation index of the mesh point device according to a first distance between the busy value influence factor combination of the mesh point device and the positive ideal value and a second distance between the busy value influence factor combination of the mesh point device and the negative ideal value;
the method comprises the steps of sequencing a plurality of mesh point devices according to respective device evaluation indexes of the mesh point devices;
and inputting the position information of the user terminal, the sequenced multiple website devices and the people flow data of each website device into a pre-trained device resource allocation model.
3. The method of claim 1, further comprising:
acquiring training sample data; the training sample data comprise a device busy value sample set, a position information sample set of a user terminal, a regional people stream state sample set and a historical optimal network point device identification sample set;
performing multi-round training on a random forest model by using the training sample data, and adjusting random forest parameter combinations until the classification accuracy reaches the highest to obtain an optimal random forest parameter combination;
and constructing and obtaining the pre-trained equipment resource distribution model according to the optimal random forest parameter combination.
4. The method according to claim 1, wherein the obtaining the device busy value of the mesh point device according to the device operation power consumption information comprises:
acquiring a plurality of busy value influence factors and acquiring a factor weight list of the busy value influence factors; the factor weight list records a factor weight vector corresponding to each mesh point device, and the factor weight vector comprises respective weights of the busy value influence factors;
obtaining busy value influence factor values corresponding to busy value influence factors of the mesh point equipment according to the equipment power consumption information of the mesh point equipment;
constructing a decision matrix based on the busy value influence factor values of all the network point devices;
and obtaining the equipment busy value of each mesh point equipment according to the factor weight list and the decision matrix.
5. The method of claim 4, wherein obtaining the factor weight list of busy value impact factors comprises:
aiming at each mesh point device, obtaining the importance degree values of the busy value influence factors, and determining an influence factor weight vector of each busy value influence factor according to the importance degree values of the busy value influence factors;
a factor weight list is constructed based on a plurality of impact factor weight vectors for respective mesh point devices.
6. The method of claim 4, wherein determining an impact factor weight vector for each busy value impact factor based on the importance values for the plurality of busy value impact factors comprises:
acquiring judgment tables corresponding to the busy value influence factors; the judgment table records an importance degree value of one busy value influence factor relative to any other busy value influence factor in the busy value influence factors;
for each busy value influence factor, carrying out normalization calculation on a plurality of importance degree values associated with the busy value influence factor to obtain the weight of the busy value influence factor;
and constructing an influence factor weight vector of each mesh point device according to the weight of each busy value influence factor.
7. The method of claim 4, wherein the busy value impact factor comprises a current traffic busy value gain; the method further comprises the following steps:
acquiring current service calling increment and service historical processing speed of each network point device;
and for each network node device, weighting the current service calling increment and the service historical processing speed to obtain the gain of the busy value of the current service of each network node device.
8. A website device recommendation apparatus, the apparatus comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for responding to a website equipment search request of a user terminal and acquiring position information of the user terminal, equipment power consumption information corresponding to a plurality of candidate website equipment and people flow data;
the equipment busy value acquisition module is used for acquiring the equipment busy value of the network point equipment according to the equipment running power consumption information;
the optimal network node equipment determining module is used for inputting the position information of the user terminal, equipment busy values and people flow data of each network node equipment into a pre-trained equipment resource allocation model to obtain the optimal network node equipment determined by the equipment resource allocation model from a plurality of network node equipment;
and the equipment information returning module is used for returning the equipment information of the optimal network point equipment to the user terminal.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210409382.8A CN114781717A (en) | 2022-04-19 | 2022-04-19 | Network point equipment recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210409382.8A CN114781717A (en) | 2022-04-19 | 2022-04-19 | Network point equipment recommendation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114781717A true CN114781717A (en) | 2022-07-22 |
Family
ID=82431202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210409382.8A Pending CN114781717A (en) | 2022-04-19 | 2022-04-19 | Network point equipment recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114781717A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116468294A (en) * | 2023-04-18 | 2023-07-21 | 湖北安源安全环保科技有限公司 | Emergency evaluation method, system, terminal and terminal quick positioning method for power enterprises |
| CN117094713A (en) * | 2023-10-18 | 2023-11-21 | 杭州青橄榄网络技术有限公司 | Self-service payment method and terminal based on intelligent campus |
-
2022
- 2022-04-19 CN CN202210409382.8A patent/CN114781717A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116468294A (en) * | 2023-04-18 | 2023-07-21 | 湖北安源安全环保科技有限公司 | Emergency evaluation method, system, terminal and terminal quick positioning method for power enterprises |
| CN116468294B (en) * | 2023-04-18 | 2024-05-14 | 湖北安源安全环保科技有限公司 | Emergency evaluation method, system, terminal and terminal quick positioning method for power enterprises |
| CN117094713A (en) * | 2023-10-18 | 2023-11-21 | 杭州青橄榄网络技术有限公司 | Self-service payment method and terminal based on intelligent campus |
| CN117094713B (en) * | 2023-10-18 | 2024-02-23 | 杭州青橄榄网络技术有限公司 | Self-service payment method and terminal based on intelligent campus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110837931B (en) | Customer churn prediction method, device and storage medium | |
| CN114781717A (en) | Network point equipment recommendation method, device, equipment and storage medium | |
| WO2019134274A1 (en) | Interest exploration method, storage medium, electronic device and system | |
| CN108805413A (en) | Labor turnover Risk Forecast Method, device, computer equipment and storage medium | |
| Yang et al. | IoT information service composition driven by user requirement | |
| CN111695084A (en) | Model generation method, credit score generation method, device, equipment and storage medium | |
| CN111541628A (en) | Power communication network service resource allocation method and related device | |
| CN111598723A (en) | Electric power marketing management platform construction method based on big data management | |
| CN115983900A (en) | Method, apparatus, device, medium, and program product for constructing user marketing strategy | |
| CN114693409A (en) | Product matching method, device, computer equipment, storage medium and program product | |
| CN111061948A (en) | User label recommendation method and device, computer equipment and storage medium | |
| CN111260288B (en) | Order management method, device, medium and electronic equipment | |
| CN113191828A (en) | Method, device, equipment and medium for constructing user electricity value grade label | |
| CN116188050A (en) | Takeaway platform information processing system based on data analysis | |
| CN115292475A (en) | Cloud computing service information processing method and system based on smart city | |
| CN114782062A (en) | Commodity recall optimization method and device, equipment, medium and product thereof | |
| CN104778636B (en) | Method is recommended in the information service of apparel maintenance support | |
| CN113760550A (en) | Resource allocation method and resource allocation device | |
| Kong et al. | The risk prediction of mobile user tricking account overdraft limit based on fusion model of logistic and GBDT | |
| Singh et al. | Applications of clustering algorithms and self organizing maps as data mining and business intelligence tools on real world data sets | |
| CN113052629A (en) | Network user image drawing method based on CECU system intelligent algorithm model | |
| CN110807599A (en) | Method, device, server and storage medium for deciding electrochemical energy storage scheme | |
| CN114155038B (en) | Epidemic situation affected user identification method | |
| Li et al. | A fast real-time qos-aware service selection algorithm | |
| Vitoropoulou et al. | CAUSE: Caching Aided by USer Equipment |
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 |