CN111107003A - Intelligent routing method - Google Patents
Intelligent routing method Download PDFInfo
- Publication number
- CN111107003A CN111107003A CN201911408370.8A CN201911408370A CN111107003A CN 111107003 A CN111107003 A CN 111107003A CN 201911408370 A CN201911408370 A CN 201911408370A CN 111107003 A CN111107003 A CN 111107003A
- Authority
- CN
- China
- Prior art keywords
- service
- routing
- authentication
- service data
- channel
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/302—Route determination based on requested QoS
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/02—Topology update or discovery
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/14—Routing performance; Theoretical aspects
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to an intelligent routing method, which comprises the following steps of S1: receiving and caching real-time service data; step S2: performing routing auxiliary calculation based on the service characteristics; step S3: and performing service classification caching and routing processing based on the auxiliary calculation result. The invention can distinguish the routing processing of the emergency service and the non-emergency service, selects a faster routing decision method for the emergency service, and can adopt an artificial intelligent mode to consider a plurality of factors for the non-emergency service to carry out the routing of the service, thereby providing the possibility of dynamic adjustment of the model through the weight value; the storage and reading expenses caused by decision making are reduced through the hierarchical cache arrangement, and the real-time performance is also guaranteed on the basis of guaranteeing the intelligence of decision making results through the cache ordered control and the backward pushing mechanism of the list to be selected.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an intelligent routing method.
Background
The existing service routing method mainly adopts dynamic routing and static routing, wherein the static routing is also called customized routing, which means that a routing channel is selected in advance according to specific routing requirements, configured in an available channel list, and the priority of the channel is manually preset. When the service arrives, the system firstly queries an available routing channel list according to service elements, then filters each channel one by using the routing decisive elements, channels which do not meet the conditions are eliminated, finally the left channels are sorted according to the priority, and the channel with the highest priority is adopted by the route. The routing mode obviously lacks flexibility and adaptability, and the existing dynamic routing mode only achieves the result of dynamically calculating the decision according to a plurality of elements of the channel, so that the dynamic result lacks basis, the dynamic calculation cost is too large, the emergency service cannot be effectively processed, and the dynamic routing effect is poor; therefore, the invention provides an intelligent routing method, which can perform routing processing of emergency and non-emergency services in a differentiated manner, select a faster routing decision method for emergency services, and perform routing of services by considering a plurality of factors in an artificial intelligent manner for non-emergency services, thereby providing possibility of dynamic adjustment of a model through a weight value; the storage and reading expenses caused by decision making are reduced through the hierarchical cache arrangement, and the real-time performance is also guaranteed on the basis of guaranteeing the intelligence of decision making results through the cache ordered control and the backward pushing mechanism of the list to be selected.
Disclosure of Invention
The invention aims to provide an intelligent routing method, which is realized by the following technical scheme.
An intelligent routing method, characterized by: the method comprises the following steps:
step S1: receiving and caching real-time service data;
step S2: performing routing auxiliary calculation based on the service characteristics;
step S3: and performing service classification caching and routing processing based on the auxiliary calculation result.
Further, the method further includes, at step S4: and performing routing authentication based on the service scene and the service type.
Further, the step S1 is specifically: receiving real-time service data from a terminal, storing the service data in a temporary cache, extracting service characteristics, setting a weight value for the service characteristics if the service is an emergency service, and selecting one or more routing channels to perform routing processing of the service based on the service characteristics after the weight value is set; otherwise, step S2 is entered, the temporary buffer is merged into the to-be-processed buffer, and the temporary buffer is regenerated to be ready to receive the next real-time service data.
Further, the step S2 is specifically: and acquiring and classifying the service characteristics, inputting the classified service characteristics into an artificial intelligence model according to the classification, and taking the output of the artificial intelligence model as a calculation result of the auxiliary calculation.
Further, the step S3 is specifically: before the service data is processed, the authentication type is selected according to the service scene and the service type.
Furthermore, different authentication types correspond to different authentication elements with different quantities.
Further, the authentication type comprises two-element, three-element, four-element and five-element authentication.
Further, the number of the elements is the number of the authentication factors which need to be considered for authentication.
Further, the selection of the authentication type is performed according to the service scenario and the service type, which specifically includes: and selecting the selectable authentication types according to the service types, and determining an authentication type from the selectable authentication types based on the service scene to perform routing authentication.
Further, in the process of performing service processing, when one routing channel fails to process the service data, the next to-be-routed channel is selected to process the service data until all routing channels are unsuccessful.
The invention has the beneficial effects that: the routing processing of emergency and non-emergency (or simple and responsible) services can be distinguished, a faster routing decision method is selected for the emergency services, and a plurality of factors can be considered for routing the services for the non-emergency services in an artificial intelligent mode, so that the possibility of dynamic model adjustment is provided through weight values; the storage and reading expenses caused by decision making are reduced through the hierarchical cache arrangement, and the real-time performance is also guaranteed on the basis of guaranteeing the intelligence of decision making results through the cache ordered control and the backward pushing mechanism of the list to be selected.
Drawings
FIG. 1 is a schematic diagram of the steps of the intelligent routing method provided by the present invention;
Detailed Description
The intelligent routing method of the present invention will be described in further detail below.
The present invention will now be described in more detail with reference to the accompanying drawings, in which preferred embodiments of the invention are shown, it being understood that one skilled in the art may modify the invention herein described while still achieving the beneficial results of the present invention. Accordingly, the following description should be construed as broadly as possible to those skilled in the art and not as limiting the invention.
In the interest of clarity, not all features of an actual implementation are described. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. It will of course be appreciated that in the development of any such actual embodiment, numerous implementation-specific details must be set forth in order to achieve the developer's specific goals.
In order to make the objects and features of the present invention more comprehensible, embodiments of the present invention are described in detail below with reference to the accompanying drawings. It is to be noted that the drawings are in a very simplified form and are not to precise scale, which is provided solely for the purpose of facilitating and distinctly claiming the embodiments of the present invention.
The intelligent routing method provided by the invention comprises the following steps:
step S1: receiving and caching real-time service data; specifically, the method comprises the following steps: receiving real-time service data from a terminal, storing the service data in a temporary cache, extracting service characteristics, setting a weight value for the service characteristics if the service is an emergency service, and selecting one or more routing channels to perform routing processing of the service based on the service characteristics after the weight value is set; otherwise, step S2 is entered, the temporary cache is merged into the cache to be processed, and the temporary cache is regenerated to wait for receiving the next real-time service data; wherein: service features are features related to the service-related subject and the service type, for example: the type of service, the type of service initiator, etc. the subject (client a, client B, etc.) involved in the service; preferably: storing the service data after the routing processing in a channel cache of the selected routing channel, and deleting the service data from the temporary cache;
setting a weighted value for the service characteristics, specifically: calculating the historical emergency degree of the service characteristics, and setting the weight value of the service characteristics to be equal to the normalized historical emergency degree; wherein: the historical emergency degree of the service features is the number of historical emergency services or historical services, wherein the historical emergency services or historical services have the consistent characteristic values corresponding to the service features in all the historical emergency services or all the historical services and the characteristic values corresponding to the service features of the current service; for example: for the service characteristic A, the value of the service characteristic A of the current service is A1, and in the historical emergency service or the historical service, if the quantity of the emergency service or the service with the value of the emergency service or the service characteristic A of the service being A1 is X, the emergency degree of the service characteristic A is X;
specifically, according to the calculation of historical routing records, for each service characteristic SCi, the total times of finally selecting the routing channel Cj by all corresponding services is SNij, the weighted number WSNi is calculated to be Wi ＊ SNij, wherein Wi is the weighted value of the service characteristic SCi, and for the channel Cj, the weighted total number is calculated to be sigmaiWSNij, selecting the channel with the maximum total weight and/or the channels corresponding to the first few bits as the selected routing channel; preferably: selecting part of the service features to perform the selection, for example: selecting the service characteristics of Z position before the weighted value ranking, and selecting based on the service characteristics of the Z position before the weighted value ranking;
in the process of processing the service, when one routing channel fails to process the service data, selecting the next channel to be routed to process the service data until all the routing channels are unsuccessful;
preferentially, the method comprises the following steps: storing the typical service characteristics and the corresponding times of the routing channel in a quick lookup table for quick routing;
the cache comprises a temporary cache, a cache to be processed and a channel cache; the temporary cache is used for storing service data received in real time, and the size of the occupied temporary cache space is different according to the size of the service data; the cache to be processed is used for storing the service data for routing processing, and for the service data already stored in the temporary cache, the data do not need to be moved again, but the temporary cache is directly merged into the cache to be processed in a pointer, index and other modes, so that the storage overhead is saved once, and a new temporary cache space is created at the same time, and the size of the new temporary cache space is the same as that of the service data, so that the size of the original temporary cache space is kept unchanged; in the operation process aiming at the temporary cache space, other parts of the temporary cache space can provide data read-write service in parallel, and the processing pipelining and parallelism are ensured; the channel cache is used for storing the service data of the service data processing result; since the routing operation and the routing decision operation do not belong to one logical step, they usually do not belong to one physical memory space range. For example: the channel cache is arranged to be located in a different cache device from the temporary cache and the to-be-processed cache; the different cache devices have different reading speeds;
step S2: performing routing auxiliary calculation based on the service characteristics; specifically, the method comprises the following steps: acquiring and classifying the service characteristics, inputting the classified service characteristics into an artificial intelligence model according to the classification, and taking the output of the artificial intelligence model as a calculation result of auxiliary calculation;
the classifying the service features specifically includes: dividing service characteristics into three classes, wherein the first class is service main body correlation (such as A-type mobile phone terminal and B-type server), the second class is service type correlation (such as payment service and authentication service), and the third class is service scene correlation (such as operating system and application program operated by current service);
the classified service features are input into the artificial intelligence model according to categories, and the method specifically comprises the following steps: inputting the three service characteristics into three neural network models respectively, and inputting the output of the three neural network models into a top layer neural network model as input;
preferably: before the outputs of the three neural network models are used as inputs, the three outputs are weighted, and the weighted outputs are used as inputs to be input into the top layer neural network model; the output result of the neural network model can be quickly adjusted by dynamically adjusting the weight when the business processing requirement of the business environment is greatly changed through the adjustment of the weight; wherein: in the training process, the three independent training modes are respectively carried out, and after the errors of the three neural network models enter an allowable error range, the training of the whole artificial intelligence model is carried out so that the errors of the whole artificial intelligence model are within the allowable range; in this way, each independent model is relatively well-trained, so that possible post-adjustment can be made by the weights; in the initial process, setting the weights of the three neural network models to be 1, keeping the weight values unchanged in the whole training process, and adjusting the weight values only when the business processing requirements change; in the prior art, the relation representation among different classification characteristics is often introduced by increasing the layer number of a neural network model, but the complexity of an artificial intelligence model is obviously increased, the training and calculation expenses are not paid, and the relation adjustment of dynamic change can be met by setting a weight matrix;
preferably: each neural network model comprises a weight matrix, a bias coefficient, a primary output and a final output;
preferably: the neural network model is a Probabilistic Neural Network (PNN), and also comprises one or more of a Back Propagation Network (BPN), a learning vector quantization network (LV/Q), a radial basis function network (RBF), an adaptive resonance theory model network (ART), an adaptive tissue mapping network (SOM), an LSTM and an RNN;
preferably: the output of the artificial intelligence model is a multivariate vector, each element in the vector corresponds to a routing channel, and the value of each element is any numerical value between 0 and 1, but is a non-deterministic value; the size of the element represents the weight value for selecting the routing channel; for example: the output vector is [0.1, 0.3, 0.6, 0.1], which indicates that the weight value of the third route channel is the maximum, so that the third route channel can be used as a main selection channel; sorting the corresponding routing channels from large to small according to the sizes of the weight values of the element values in the output vector to obtain a list of routing channels to be selected; taking the routing channel list as a calculation result of an auxiliary decision; wherein: only including the route channel corresponding to the element with the weight value larger than the preset value in the route channel list; the number of selectable routing channels can be adjusted by flexibly setting a preset value, and the setting can be dynamically adjusted according to the tolerance time of a user and the number of resources of local decision hardware;
preferably: training the artificial intelligence model before using the artificial intelligence model; performing real-time incremental training on the artificial intelligence model based on the calculation result;
for the routing of the emergency service, the higher routing speed can be obtained mainly according to the matching between the service characteristics and the historical routing results, but for the non-emergency service, better basis can be provided for the subsequent emergency service only by carrying out artificial intelligence-based routing decision according to the current service characteristics; the routing auxiliary computing module provides data analysis for routing decision, and the data comes from the service characteristics of real-time service data. The route auxiliary computing module can calculate based on the service characteristics and then classify and cache the calculation result;
step S3: performing service classification caching and routing processing based on the auxiliary calculation result; specifically, the method comprises the following steps: caching the service data or the service data address in a channel cache corresponding to the routing channel according to the calculation result; the routing channel sequentially performs routing processing on the service data according to the sequence cached in the channel cache, and deletes the service data subjected to the routing processing;
in the service processing device, different routing channels are provided with independent channel caches, and service data can be rapidly routed through the channel caches, the communication and decision overhead between the channel caches and the corresponding channels is low, and the control capability of the channels for the corresponding channel caches is strong; for a service processing device with rich hardware resources, a channel controller of the service processing device can actively route channel data in a channel cache, and different classification caches are more necessary at the moment; the setting of the channel can be a hardware setting or a software setting;
the caching the service data or the service data address in a channel cache corresponding to the routing channel according to the calculation result specifically comprises: the calculation result is a routing channel list, and the service data is read from the cache to be processed into a channel cache corresponding to the routing channel with the first position in the routing channel list; for example: when the channel cache is in a queue structure, reading the service data to the tail part of the channel cache; for other routing channels in the routing channel list, storing the storage addresses of the service data in the channel caches of the other routing channels; wherein: the storage address is the storage position of the service data in the channel cache corresponding to the routing channel with the first position;
the routing channel sequentially performs routing processing on the service data according to the sequence cached in the channel cache, specifically: when actual service data are stored in the channel cache, processing the service data and locking the service data in the process of performing routing processing; when a channel cache corresponding to a service channel stores a storage address, searching corresponding service data according to the storage address, and when the service data is in a deletion state, skipping the processing of the service data corresponding to the storage address and directly processing the next service data; when the service data is in an undeleted state; determining processing for the service data according to the routing channel list of the service data; when the service data is in a locked state, moving the sequencing position of the stored address backwards to wait for a processing result of the service data (if the service data is unsuccessful, other channels are required to perform routing processing);
in the process of processing the service, when one routing channel fails to process the service data, selecting the next channel to be routed to process the service data until all the routing channels are unsuccessful;
determining processing for the service data according to the routing channel list of the service data, specifically: when a storage address is stored in a channel cache corresponding to a service channel (at this time, it is indicated that the service data is the first in the cache position in the service channel), determining the sequence of the routing channel in a routing channel list of the service data, and proportionally moving back the sequence position of the storage address according to the sequence; wherein: the proportion is dynamically set; for each routing channel, the number of backward shifts of the sorting position of the stored address of one service number is limited, and is a preset number, for example: once; when the backward movement times are more than or equal to the preset times, the backward movement of the sequencing position is not carried out any more, and the service data is stored in a channel cache corresponding to a service channel so as to be processed; the service data needs to be locked in the processing process; the service can wait for the priority channel in a simple backward moving mode, but the service is not wait without limit, and the routing congestion condition can be dynamically adjusted in real time while the superiority of intelligent decision is reflected;
step S4: performing routing authentication based on the service scene and the service type; specifically, the method comprises the following steps: before processing the service data, selecting the authentication type according to the service scene and the service type; wherein: the authentication types are different in corresponding different authentication element quantity, and the authentication types comprise two-element, three-element, four-element and five-element authentication; the number of the elements is the number of the authentication factors which need to be considered for authentication; when more authentication factors are considered, the more complicated the authentication is;
selecting an authentication type according to a service scene and a service type, specifically: selecting optional authentication types according to the service types, and determining an authentication type from the optional authentication types based on the service scene to perform routing authentication; the problem of flexibility loss caused by the fact that authentication types are selected only depending on service types in the prior art is solved by simultaneously considering the scenes and the service types, the allowable authentication types are very wide in tolerance for many service types, the service scenes can be used as a key part of safety influence to effectively make up for the service types, and more complex authentication types can be selected within a certain range under the condition of poor service scenes;
the foregoing illustrates and describes the principles, general features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. An intelligent routing method, characterized by: the method comprises the following steps:
step S1: receiving and caching real-time service data;
step S2: performing routing auxiliary calculation based on the service characteristics;
step S3: and performing service classification caching and routing processing based on the auxiliary calculation result.
2. The intelligent routing method according to claim 1, further comprising, step S4: and performing routing authentication based on the service scene and the service type.
3. The intelligent routing method according to claim 1, wherein the step S1 specifically is: receiving real-time service data from a terminal, storing the service data in a temporary cache, extracting service characteristics, setting a weight value for the service characteristics if the service is an emergency service, and selecting one or more routing channels to perform routing processing of the service based on the service characteristics after the weight value is set; otherwise, step S2 is entered, the temporary buffer is merged into the to-be-processed buffer, and the temporary buffer is regenerated to be ready to receive the next real-time service data.
4. The intelligent routing method according to claim 3, wherein the step S2 specifically comprises: and acquiring and classifying the service characteristics, inputting the classified service characteristics into an artificial intelligence model according to the classification, and taking the output of the artificial intelligence model as a calculation result of the auxiliary calculation.
5. The intelligent routing method according to claim 2, wherein the step S3 specifically is: before the service data is processed, the authentication type is selected according to the service scene and the service type.
6. An intelligent routing method according to claim 5, characterized in that: the different authentication types correspond to different authentication elements with different quantities.
7. An intelligent routing method according to claim 6, characterized in that: the authentication type comprises two-element, three-element, four-element and five-element authentication.
8. An intelligent routing method according to claim 7, wherein the number of elements is the number of authentication factors that need to be considered for authentication.
9. The intelligent routing method according to claim 8, wherein the selection of the authentication type is performed according to a service scenario and a service type, and specifically comprises: and selecting the selectable authentication types according to the service types, and determining an authentication type from the selectable authentication types based on the service scene to perform routing authentication.
10. The intelligent routing method of claim 8, wherein in the process of performing service processing, when one routing channel fails to process the service data, the next to-be-routed channel is selected to process the service data until all routing channels are unsuccessful.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911408370.8A CN111107003B (en) | 2019-12-31 | 2019-12-31 | Intelligent routing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911408370.8A CN111107003B (en) | 2019-12-31 | 2019-12-31 | Intelligent routing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111107003A true CN111107003A (en) | 2020-05-05 |
| CN111107003B CN111107003B (en) | 2020-10-27 |
Family
ID=70424185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911408370.8A Active CN111107003B (en) | 2019-12-31 | 2019-12-31 | Intelligent routing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111107003B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580098A (en) * | 2020-12-23 | 2021-03-30 | 光大兴陇信托有限责任公司 | Business data comparison method and system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1913494A (en) * | 2006-08-24 | 2007-02-14 | 华为技术有限公司 | Method of generating service route based on light network service flow |
| CN101110775A (en) * | 2007-07-06 | 2008-01-23 | 中兴通讯股份有限公司 | Method and system for dynamically regulating load distribution |
| CN101771627A (en) * | 2009-01-05 | 2010-07-07 | 武汉烽火网络有限责任公司 | Equipment and method for analyzing and controlling node real-time deep packet on internet |
| CN101801036A (en) * | 2010-03-03 | 2010-08-11 | 华为终端有限公司 | Network traffic management method and system and common node |
| US20110202679A1 (en) * | 2006-06-16 | 2011-08-18 | Bittorrent, Inc. | Classification and Verification of Static File Transfer Protocols |
| CN103259719A (en) * | 2013-05-27 | 2013-08-21 | 重庆邮电大学 | Service awareness route protective method by means of Bayesian classification |
| CN104080112A (en) * | 2014-07-17 | 2014-10-01 | 重庆邮电大学 | Method for improving service reliability of wireless self-organizing network |
| US20150263985A1 (en) * | 2014-03-13 | 2015-09-17 | Jpmorgan Chase Bank, N.A. | Systems and methods for intelligent workload routing |
| CN106453085A (en) * | 2016-12-14 | 2017-02-22 | 国家电网公司 | Business importance-based risk-balancing routing assignment method and system |
| CN106937282A (en) * | 2015-12-29 | 2017-07-07 | 北界创想（北京）软件有限公司 | VPN cut-in methods and system based on mobile terminal |
| CN106993298A (en) * | 2016-12-20 | 2017-07-28 | 广东电网有限责任公司电力调度控制中心 | A kind of intelligent electric power communication service difference dispatching method based on QoS |
| CN107257256A (en) * | 2017-05-03 | 2017-10-17 | 江苏省邮电规划设计院有限责任公司 | A kind of WSON network plannings plan-validation method |
-
2019
- 2019-12-31 CN CN201911408370.8A patent/CN111107003B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110202679A1 (en) * | 2006-06-16 | 2011-08-18 | Bittorrent, Inc. | Classification and Verification of Static File Transfer Protocols |
| CN1913494A (en) * | 2006-08-24 | 2007-02-14 | 华为技术有限公司 | Method of generating service route based on light network service flow |
| CN101110775A (en) * | 2007-07-06 | 2008-01-23 | 中兴通讯股份有限公司 | Method and system for dynamically regulating load distribution |
| CN101771627A (en) * | 2009-01-05 | 2010-07-07 | 武汉烽火网络有限责任公司 | Equipment and method for analyzing and controlling node real-time deep packet on internet |
| CN101801036A (en) * | 2010-03-03 | 2010-08-11 | 华为终端有限公司 | Network traffic management method and system and common node |
| CN103259719A (en) * | 2013-05-27 | 2013-08-21 | 重庆邮电大学 | Service awareness route protective method by means of Bayesian classification |
| US20150263985A1 (en) * | 2014-03-13 | 2015-09-17 | Jpmorgan Chase Bank, N.A. | Systems and methods for intelligent workload routing |
| CN104080112A (en) * | 2014-07-17 | 2014-10-01 | 重庆邮电大学 | Method for improving service reliability of wireless self-organizing network |
| CN106937282A (en) * | 2015-12-29 | 2017-07-07 | 北界创想（北京）软件有限公司 | VPN cut-in methods and system based on mobile terminal |
| CN106453085A (en) * | 2016-12-14 | 2017-02-22 | 国家电网公司 | Business importance-based risk-balancing routing assignment method and system |
| CN106993298A (en) * | 2016-12-20 | 2017-07-28 | 广东电网有限责任公司电力调度控制中心 | A kind of intelligent electric power communication service difference dispatching method based on QoS |
| CN107257256A (en) * | 2017-05-03 | 2017-10-17 | 江苏省邮电规划设计院有限责任公司 | A kind of WSON network plannings plan-validation method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580098A (en) * | 2020-12-23 | 2021-03-30 | 光大兴陇信托有限责任公司 | Business data comparison method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111107003B (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110197258B (en) | Neural network searching method, image processing device, neural network searching apparatus, image processing apparatus, and recording medium | |
| CN108829344A (en) | Date storage method, device and storage medium | |
| CN107305637B (en) | Data clustering method and device based on K-Means algorithm | |
| CN110018786B (en) | System and method for predicting data storage characteristics | |
| JP2023523029A (en) | Image recognition model generation method, apparatus, computer equipment and storage medium | |
| WO2021179631A1 (en) | Convolutional neural network model compression method, apparatus and device, and storage medium | |
| CN112667528A (en) | Data prefetching method and related equipment | |
| CN111625367B (en) | Method for dynamically adjusting read-write resources of file system | |
| CN111242319A (en) | Model prediction result interpretation method and device | |
| CN111107003B (en) | Intelligent routing method | |
| CN114861910A (en) | Neural network model compression method, device, equipment and medium | |
| CN112416368A (en) | Cache deployment and task scheduling method, terminal and computer readable storage medium | |
| CN111221827B (en) | Database table connection method and device based on graphic processor, computer equipment and storage medium | |
| CN107193940A (en) | Big data method for optimization analysis | |
| US7647592B2 (en) | Methods and systems for assigning objects to processing units | |
| CN109871488A (en) | A kind of Web service construction method and Web service for merging availability and user preference | |
| US11663184B2 (en) | Information processing method of grouping data, information processing system for grouping data, and non-transitory computer readable storage medium | |
| WO2022245295A2 (en) | System and method for predicting delivery time for batch orders | |
| CN111444183B (en) | Distributed self-adaptive user request scheduling method in key value storage system | |
| CN110781217B (en) | Method and device for processing ordered data, storage medium and server | |
| CN113342781A (en) | Data migration method, device, equipment and storage medium | |
| CN107103095A (en) | Method for computing data based on high performance network framework | |
| JP4106021B2 (en) | Method and circuit for virtually increasing the number of prototypes in an artificial neural network | |
| CN112214627A (en) | Search method, readable storage medium and electronic device | |
| CN112905782B (en) | Volume assembling method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |