CN113408834B - Communication success rate prediction method and device based on self-learning - Google Patents
Communication success rate prediction method and device based on self-learning Download PDFInfo
- Publication number
- CN113408834B CN113408834B CN202110956067.2A CN202110956067A CN113408834B CN 113408834 B CN113408834 B CN 113408834B CN 202110956067 A CN202110956067 A CN 202110956067A CN 113408834 B CN113408834 B CN 113408834B
- Authority
- CN
- China
- Prior art keywords
- success rate
- prediction
- weight coefficient
- time period
- communication success
- 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.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000004364 calculation method Methods 0.000 claims abstract description 36
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 description 10
- 238000005065 mining Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
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
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Telephonic Communication Services (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a communication success rate prediction method and a communication success rate prediction device based on self-learning, wherein the method comprises the following steps: counting the collection success times and the total times of each device in each time period, and calculating the success rate of each device in each time period; according to the success rate of each device in the current time period and the previous acquisition state, performing weighted calculation to predict the communication success rate of each device; sorting all the devices from high to low according to the predicted values of the communication success rate of the devices, acquiring data according to the sorting sequence, and counting the failure times of prediction; and based on a self-learning mode, adjusting and updating a weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period according to the prediction failure times. According to the technical scheme, the acquisition equipment is sequenced according to the prediction value of the communication success rate of the equipment, so that the acquisition success rate is greatly improved, the equipment which fails in repeated replenishment and acquisition for many times is avoided, and the method and the device are particularly suitable for the situation of unstable acquisition state.
Description
Technical Field
The invention relates to the technical field of data acquisition, in particular to a communication success rate prediction method and device based on self-learning.
Background
The acquisition success rate is the ratio of the number of successful acquisition rates to the total number in a certain time, and is an important index for measuring the performance of the intelligent terminal. In order to improve the acquisition success rate, the devices that can be acquired need to be acquired once in a short time as much as possible, and therefore, the acquisition devices need to be sorted.
In the related art, the design of the intelligent terminal generally has the following sorting modes: the first method is to sort according to the sequence number of the files, skip the current equipment when the acquisition fails, and continue to carry out additional acquisition on the previous failed equipment after one round of copying. This approach is logically simple and clear in programming, but inefficient. The second is to sort according to the previous acquisition state, i.e. the previous successful row is before and the failed row is after. Compared with the first mode, the mode has the advantages that the efficiency is slightly improved, the mode is suitable for being used in a scene with a stable and unchangeable acquisition state, and the best acquisition effect cannot be achieved in a scene with an unstable acquisition state such as carrier waves, wireless and the like.
Disclosure of Invention
The invention aims to provide a communication success rate prediction method based on self-learning, which sequences acquisition equipment through a prediction value of equipment communication success rate, improves the acquisition success rate and avoids equipment which fails in repeated recovery.
In a first aspect of the present invention, a communication success rate prediction method based on self-learning is provided, which includes the following steps:
s11, counting the collection success times and the total times of each device in each time period, and calculating the success rate of each device in each time period;
s12, according to the success rate of each device in the current time period and the previous acquisition state, performing weighted calculation and predicting the communication success rate of each device;
s13, sorting all the devices from high to low according to the predicted values of the communication success rate of the devices, acquiring data according to the sorting sequence, and counting the prediction failure times;
and S14, based on the self-learning mode, adjusting and updating the weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period according to the prediction failure times.
In the scheme, the acquisition equipment is sequenced through the prediction value of the equipment communication success rate, the acquisition success rate is greatly improved, the equipment which fails in repeated supplementary mining for many times is avoided, and the method is particularly suitable for the scene with an unstable acquisition state. The communication success rate of each device is predicted through the success rate of each device in the current time period and the previous acquisition state and weighted calculation, parameters are selected reasonably, and the prediction accuracy of the communication success rate of the device is high. In the acquisition process, the weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period is adjusted and updated according to the prediction failure times based on a self-learning mode, so that the prediction accuracy is further improved, and the data acquisition operation of the equipment is basically not influenced in the weight coefficient adjustment updating process.
Preferably, in step S12, the weighting calculation is performed according to the success rate of each device in the current time period and the previous acquisition state, and the predicting success rate of each device communication specifically includes:
s121, acquiring the success rate and the previous acquisition state of each device in the current time period;
s122, according to the success rate of each device in the current time period and the previous acquisition state of the device, predicting the communication success rate of each device according to a preset formula,
the preset formula comprises:
r = ax + by，
wherein, r represents a predicted value of the communication success rate of the equipment; x represents the previous acquisition state of the equipment, the success is 1, and the failure is 0; the y is characterized by the success rate of the equipment in the current time period, and the value range is (0, 1); a. b is characterized as the weight coefficient of the current time interval, which is respectively marked as a first weight coefficient and a second weight coefficient, and the initial values of a and b are set to be 0.5.
According to the scheme, the communication success rate of each device is calculated and predicted through a preset formula r = ax + by, the prediction success rate is high, and the weight coefficients of different time periods are continuously adjusted and updated in the self-learning process to adapt to the corresponding time periods, so that the prediction accuracy of the different time periods is further guaranteed.
Preferably, in step S14, based on the self-learning manner, the weight coefficient in the device communication success rate prediction weighting calculation for updating the current time period is adjusted according to the prediction failure times, which specifically includes:
s141, based on a self-learning mode, keeping the first weight coefficient unchanged, adjusting the second weight coefficient, repeatedly executing the steps S11 to S13, and generating a relation graph of the prediction failure times and the second weight coefficient;
s142, determining a second weight coefficient value corresponding to the minimum value of the failure prediction times according to the relation curve graph of the failure prediction times and the second weight coefficient, and correspondingly adjusting and updating in the preset formula;
s143, based on a self-learning mode, keeping the second weight coefficient unchanged, adjusting the first weight coefficient, repeatedly executing the steps S11 to S13, and generating a relation graph of the prediction failure times and the first weight coefficient;
s144, determining a first weight coefficient value corresponding to the minimum value of the prediction failure times according to a relation curve graph of the prediction failure times and the first weight coefficient, correspondingly adjusting and updating in the preset formula, and recording the minimum value of the prediction failure times of the current time period under the first weight coefficient value and the second weight coefficient value.
In the scheme, the first weight coefficient and the second weight coefficient are continuously adjusted in a self-learning mode, a relation curve graph of the prediction failure times and the second weight coefficient and a relation curve graph of the prediction failure times and the first weight coefficient are simulated, the first weight coefficient and the second weight coefficient under the condition of the minimum prediction failure times are found, and are correspondingly adjusted and updated in a preset formula, so that the prediction effect and the prediction accuracy are further improved, the prediction failure times are reduced as much as possible, the acquisition success rate is greatly improved, and the repeated supplementary mining failure equipment is avoided. And the minimum value of the failure times of prediction in the current time period is recorded, and whether the prediction is invalid or not can be evaluated in the subsequent process, so that when the prediction is invalid, the self-learning mode can be used for adjusting in time, and the success rate of equipment data acquisition is guaranteed.
Preferably, in step S14, based on the self-learning method, the method further includes adjusting and updating a weight coefficient in the device communication success rate prediction weighting calculation in the current time period according to the prediction failure times, and further includes:
s145, keeping the first weight coefficient and the second weight coefficient unchanged, continuously operating a designated cycle according to the steps S11-S13, and recording the prediction failure times of each collection in each time period in the designated cycle;
s146, counting the number of the prediction failure times larger than the minimum value of the corresponding prediction failure times in the current period of the period, and recording the number as a failure number;
s147, judging whether the failure number is larger than a preset limit value or not;
and S148, if the number of failures is judged to be less than or equal to the preset limit value, keeping the first weight coefficient and the second weight coefficient unchanged, and continuously operating according to the specified period.
According to the scheme, after the appointed period is operated, the prediction failure times acquired in each round at each time interval in the period are analyzed and evaluated, the accuracy of the predicted value of the period is evaluated, the operation can be continued when the prediction is determined to be accurate, the prediction effect and accuracy are further guaranteed, and the acquisition success rate is favorably improved.
Preferably, in step S14, based on the self-learning method, the method further includes adjusting and updating a weight coefficient in the device communication success rate prediction weighting calculation in the current time period according to the prediction failure times, and further includes:
and S149, if the number of failures is judged to be larger than the preset limit value, the steps S141 to S144 are executed, the weight coefficient is adjusted and updated, and then the continuous operation is continued according to the specified period.
In the scheme, when the predicted value is not accurate enough after the accuracy of the predicted value in the period is evaluated, the weight coefficient is adjusted and updated in time based on a self-learning mode, so that the prediction effect is more accurate.
It should be noted that the preset limit is defined according to actual requirements, for example, determined by multiplying the number of acquisition rounds in a specified period by a certain ratio (for example, 1%). In addition, the judgment condition may also be failure rate, that is, the ratio of the number of failures to the number of acquisition rounds in a specified period is compared with the preset failure rate.
Preferably, in step S13, sorting all devices from high to low according to the predicted values of the device communication success rate, performing data acquisition according to the sorting order, and counting the prediction failure times, specifically including:
s131, sequencing all the devices from high to low according to the predicted values of the communication success rate of the devices;
s132, data acquisition is carried out according to the sequencing sequence, the acquisition state is recorded, the success is 1, the failure is 0, if the acquisition of the former equipment fails, the acquisition of the latter equipment succeeds, the failure prediction is recorded, the data are accumulated in sequence, and the prediction failure times of the acquisition in the current round are determined.
According to the scheme, the number of times of failure prediction of each round of collection is counted to serve as data for reflecting the prediction effect, and the weight coefficient in the device communication success rate prediction weighting calculation can be adjusted according to the number of times of failure prediction, so that the prediction accuracy is improved, and the collection success rate is further improved.
Preferably, the respective periods comprise periods 00:00 to 08:00, 08:00 to 16:00, 16:00 to 00:00 of the day; the specified period is one month.
In a second aspect of the present invention, a communication success rate prediction apparatus based on self-learning is provided, including: the statistical calculation unit is used for counting the collection success times and the total times of each device in each time period and calculating the success rate of each device in each time period; the prediction unit is used for carrying out weighted calculation according to the success rate of each device in the current time period and the previous acquisition state and predicting the communication success rate of each device; the data acquisition unit is used for sequencing all the devices from high to low according to the prediction value of the communication success rate of the devices, acquiring data according to the sequencing sequence and counting the failure times of prediction; and the coefficient adjusting unit is used for adjusting and updating the weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period according to the prediction failure times based on a self-learning mode.
In the scheme, the acquisition equipment is sequenced through the prediction value of the equipment communication success rate, the acquisition success rate is greatly improved, the equipment which fails in repeated supplementary mining for many times is avoided, and the method is particularly suitable for the scene with an unstable acquisition state. The communication success rate of each device is predicted through the success rate of each device in the current time period and the previous acquisition state and weighted calculation, parameters are selected reasonably, and the prediction accuracy of the communication success rate of the device is high. In the acquisition process, the weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period is adjusted and updated according to the prediction failure times based on a self-learning mode, so that the prediction accuracy is further improved, and the data acquisition operation of the equipment is basically not influenced in the weight coefficient adjustment updating process.
In a third aspect of the invention, an apparatus is presented, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method as described in the first aspect.
In a fourth aspect of the present invention a computer-readable storage medium is presented, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to the first aspect.
The communication success rate prediction method and the communication success rate prediction device based on self-learning in the technical scheme of the invention have the following beneficial technical effects:
(1) the acquisition equipment is sequenced through the prediction value of the equipment communication success rate, the acquisition success rate is greatly improved, the equipment which fails in repeated supplementary mining for many times is avoided, and the method is particularly suitable for the situation of unstable acquisition state.
(2) The communication success rate of each device is predicted through the success rate of each device in the current time period and the previous acquisition state and weighted calculation, parameters are selected reasonably, and the prediction accuracy of the communication success rate of the device is high.
(3) In the acquisition process, the weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period is adjusted and updated according to the prediction failure times based on a self-learning mode, so that the prediction accuracy is further improved, and the data acquisition operation of the equipment is basically not influenced in the weight coefficient adjustment updating process.
(4) The weight coefficients in different time periods are continuously adjusted and updated in the self-learning process, so that the self-learning method is suitable for corresponding time periods, the prediction accuracy in different time periods is guaranteed, and the integral acquisition success rate is higher.
(5) After the appointed period is operated, the prediction failure times collected in each round of each time period in the period are analyzed and evaluated, the accuracy of the predicted value in the period is evaluated, and when the predicted value is found to be not accurate enough, the updating weight coefficient is adjusted in time based on a self-learning mode, so that the prediction effect is more accurate.
Drawings
FIG. 1 is a flow chart illustrating a self-learning based communication success rate prediction method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating the weight coefficient adjustment updating step of the self-learning based communication success rate prediction method according to an embodiment of the present invention;
FIG. 3 shows an example of a graph of prediction failure times versus weight coefficients;
FIG. 4 is an architecture diagram of a self-learning based communication success rate prediction device according to an embodiment of the present invention;
FIG. 5 illustrates a block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart illustrating a self-learning based communication success rate prediction method according to an embodiment of the present invention. As shown in fig. 1, a communication success rate prediction method based on self-learning according to an embodiment of the present invention includes the following steps:
s11, counting the collection success times and the total times of each device in each time period, and calculating the success rate of each device in each time period;
s12, according to the success rate of each device in the current time period and the previous acquisition state, performing weighted calculation and predicting the communication success rate of each device;
specifically, S121, a success rate and a previous acquisition state of each device in the current time period are obtained; s122, predicting the communication success rate of each device according to the success rate of each device in the current time period and the previous acquisition state of the device and a preset formula, wherein the preset formula comprises: r = ax + by, wherein r is represented as a predicted value of the success rate of equipment communication; x represents the previous acquisition state of the equipment, the success is 1, and the failure is 0; the y is characterized by the success rate of the equipment in the current time period, and the value range is (0, 1); a. b is characterized as the weight coefficient of the current time interval, which is respectively marked as a first weight coefficient and a second weight coefficient, and the initial values of a and b are set to be 0.5.
S13, sorting all the devices from high to low according to the predicted values of the communication success rate of the devices, acquiring data according to the sorting sequence, and counting the prediction failure times;
specifically, S131, all the devices are sorted from high to low according to the predicted value of the device communication success rate; s132, data acquisition is carried out according to the sequencing sequence, the acquisition state is recorded, the success is 1, the failure is 0, if the acquisition of the former equipment fails, the acquisition of the latter equipment succeeds, the failure prediction is recorded, the data are accumulated in sequence, and the prediction failure times of the acquisition in the current round are determined.
And S14, based on the self-learning mode, adjusting and updating the weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period according to the prediction failure times.
The respective periods include a period of 00:00 to 08:00, a period of 08:00 to 16:00, and a period of 16:00 to 00:00 of the day.
The acquisition equipment is sequenced through the prediction value of the equipment communication success rate, the acquisition success rate is greatly improved, the equipment which fails in repeated supplementary mining for many times is avoided, and the method is particularly suitable for the situation of unstable acquisition state. The communication success rate of each device is predicted through the success rate of each device in the current time period and the previous acquisition state and weighted calculation, parameters are selected reasonably, and the prediction accuracy of the communication success rate of the device is high. In the acquisition process, the weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period is adjusted and updated according to the prediction failure times based on a self-learning mode, so that the prediction accuracy is further improved, and the data acquisition operation of the equipment is basically not influenced in the weight coefficient adjustment updating process.
Fig. 2 is a flowchart illustrating a weight coefficient adjustment updating step in a self-learning based communication success rate prediction method according to an embodiment of the present invention. As shown in fig. 2, S14, based on the self-learning method, adjusts and updates the weight coefficient in the device communication success rate prediction weighting calculation of the current time period according to the prediction failure times, including the following steps:
s141, based on a self-learning mode, keeping the first weight coefficient a unchanged, adjusting the second weight coefficient b, repeatedly executing the steps S11 to S13, and generating a relation graph of the prediction failure times t and the second weight coefficient b; fig. 3 is a graph showing a relationship between the number of prediction failures and the weight coefficient.
S142, determining a second weight coefficient value corresponding to the minimum value of the failure prediction times according to a relation curve graph of the failure prediction times t and the second weight coefficient b, and correspondingly adjusting and updating in a preset formula;
s143, based on the self-learning mode, keeping the second weight coefficient b unchanged, adjusting the first weight coefficient a, repeatedly executing the steps S11 to S13, and generating a relation graph of the prediction failure times t and the first weight coefficient a; fig. 3 is a graph showing a relationship between the number of prediction failures and the weight coefficient.
S144, determining a first weight coefficient value corresponding to the minimum value of the prediction failure times according to a relation curve graph of the prediction failure times and the first weight coefficient, correspondingly adjusting and updating in a preset formula, and recording the minimum value t _ min of the prediction failure times of the current time period under the first weight coefficient value and the second weight coefficient value;
s145, keeping the first weight coefficient and the second weight coefficient unchanged, continuously operating a designated cycle according to the steps S11-S13, and recording the prediction failure times of each collection in each time period in the designated cycle; the specified period may be 1 month.
S146, counting the number of the prediction failure times t in the current period of the period, which are greater than the corresponding minimum value t _ min of the prediction failure times, and recording the number as a failure number c;
s147, judging whether the failure number c is larger than a preset limit value c _ min;
if the determination at S147 is no, the process returns to step S145 to continue the continuous operation in the predetermined cycle;
if the determination at S147 is yes, the process returns to the step S141 to S144 to adjust the update weight coefficient, and then the continuous operation is continued in a predetermined cycle.
Through a self-learning mode, the first weight coefficient and the second weight coefficient are continuously adjusted, a relation curve graph of the failure prediction times and the second weight coefficient and a relation curve graph of the failure prediction times and the first weight coefficient are simulated, the first weight coefficient and the second weight coefficient under the condition of the minimum failure prediction times are found, and are correspondingly adjusted and updated in a preset formula, so that the prediction effect and the prediction accuracy are further improved, the failure prediction times are reduced as much as possible, the acquisition success rate is greatly improved, and the repeated supplementary mining failure equipment is avoided. And the minimum value of the failure times of prediction in the current time period is recorded, whether the prediction is invalid or not is evaluated in the subsequent operation process, and when the prediction is invalid, the prediction effect is adjusted in time in a self-learning mode, so that the prediction effect is more accurate, and the success rate of equipment data acquisition is ensured.
Fig. 4 is an architecture diagram of a self-learning based communication success rate prediction apparatus according to an embodiment of the present invention. As shown in fig. 4, a self-learning based communication success rate prediction apparatus 400 according to an embodiment of the present invention includes: a statistic calculation unit 401, configured to count the number of acquisition success times and the total number of times of each device in each time period, and calculate a success rate of each device in each time period; a predicting unit 402, configured to perform weighted calculation according to a success rate of each device in a current time period and a previous acquisition state, and predict a communication success rate of each device; the data acquisition unit 403 is configured to sort all the devices from high to low according to the predicted values of the device communication success rate, acquire data according to the sorted order, and count the prediction failure times; and a coefficient adjusting unit 404, configured to adjust and update a weight coefficient in the device communication success rate prediction weighting calculation in the current time period according to the prediction failure times based on a self-learning manner.
The acquisition equipment is sequenced through the prediction value of the equipment communication success rate, the acquisition success rate is greatly improved, the equipment which fails in repeated supplementary mining for many times is avoided, and the method is particularly suitable for the situation of unstable acquisition state. The communication success rate of each device is predicted through the success rate of each device in the current time period and the previous acquisition state and weighted calculation, parameters are selected reasonably, and the prediction accuracy of the communication success rate of the device is high. In the acquisition process, the weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period is adjusted and updated according to the prediction failure times based on a self-learning mode, so that the prediction accuracy is further improved, and the data acquisition operation of the equipment is basically not influenced in the weight coefficient adjustment updating process.
FIG. 5 shows a schematic block diagram of an electronic device 500 that may be used to implement embodiments of the present disclosure. As shown in fig. 5, device 500 includes a Central Processing Unit (CPU) 501 that may perform various appropriate actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM) 502 or loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the device 500 can also be stored. The CPU501, ROM502, and RAM503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
A number of components in the device 500 are connected to the I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The processing unit 501 performs the various methods and processes described above. For example, in some embodiments, the methods may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 500 via the ROM502 and/or the communication unit 509. When the computer program is loaded into RAM503 and executed by CPU501, one or more steps of the method described above may be performed. Alternatively, in other embodiments, CPU501 may be configured to perform the method by any other suitable means (e.g., by way of firmware).
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a load programmable logic device (CPLD), and the like.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.
Claims (5)
1. A communication success rate prediction method based on self-learning is characterized by comprising the following steps:
s11, counting the collection success times and the total times of each device in each time period, and calculating the success rate of each device in each time period;
s12, according to the success rate of each device in the current time period and the previous acquisition state, performing weighted calculation and predicting the communication success rate of each device;
s13, sorting all the devices from high to low according to the predicted values of the communication success rate of the devices, acquiring data according to the sorting sequence, and counting the prediction failure times;
s14, based on the self-learning mode, according to the prediction failure times, adjusting and updating the weight coefficient in the device communication success rate prediction weighting calculation of the current time period;
in step S12, according to the success rate of each device in the current time period and the previous acquisition state, performing weighted calculation to predict the success rate of each device, which specifically includes:
s121, acquiring the success rate and the previous acquisition state of each device in the current time period;
s122, according to the success rate of each device in the current time period and the previous acquisition state of the device, predicting the communication success rate of each device according to a preset formula,
the preset formula comprises:
r = ax + by，
wherein, r represents a predicted value of the communication success rate of the equipment; x represents the previous acquisition state of the equipment, the success is 1, and the failure is 0; the y is characterized by the success rate of the equipment in the current time period, and the value range is (0, 1); a. b is characterized in that the weight coefficient of the current time interval is respectively recorded as a first weight coefficient and a second weight coefficient, and the initial values of a and b are set to be 0.5;
step S14, based on the self-learning method, according to the prediction failure times, adjusting and updating the weight coefficient in the device communication success rate prediction weighting calculation in the current time period, specifically including:
s141, based on a self-learning mode, keeping the first weight coefficient unchanged, adjusting the second weight coefficient, repeatedly executing the steps S11 to S13, and generating a relation graph of the prediction failure times and the second weight coefficient;
s142, determining a second weight coefficient value corresponding to the minimum value of the failure prediction times according to the relation curve graph of the failure prediction times and the second weight coefficient, and correspondingly adjusting and updating in the preset formula;
s143, based on a self-learning mode, keeping the second weight coefficient unchanged, adjusting the first weight coefficient, repeatedly executing the steps S11 to S13, and generating a relation graph of the prediction failure times and the first weight coefficient;
s144, determining a first weight coefficient value corresponding to the minimum value of the prediction failure times according to a relation curve graph of the prediction failure times and the first weight coefficient, correspondingly adjusting and updating in the preset formula, and recording the minimum value of the prediction failure times of the current time period under the first weight coefficient value and the second weight coefficient value;
further comprising:
s145, keeping the first weight coefficient and the second weight coefficient unchanged, continuously operating a designated cycle according to the steps S11-S13, and recording the prediction failure times of each collection in each time period in the designated cycle;
s146, counting the number of the prediction failure times in the current period of the period which are more than the minimum value of the corresponding prediction failure times,
recording the number of failures;
s147, judging whether the failure number is larger than a preset limit value or not;
s148, if the number of failures is judged to be less than or equal to the preset limit value, keeping the first weight coefficient and the second weight coefficient unchanged, and continuously operating according to a specified period;
wherein, step S14, based on the self-learning manner, according to the prediction failure times, adjusting and updating the weight coefficient in the device communication success rate prediction weighting calculation of the current time period, further includes:
and S149, if the number of failures is judged to be larger than the preset limit value, the steps S141 to S144 are executed, the weight coefficient is adjusted and updated, and then the continuous operation is continued according to the specified period.
2. The self-learning based communication success rate prediction method of claim 1, wherein step S13, according to the predicted value of the device communication success rate, all devices are sorted from high to low, data collection is performed according to the sorted order, and the prediction failure times are counted, which specifically includes:
s131, sequencing all the devices from high to low according to the predicted values of the communication success rate of the devices;
s132, data acquisition is carried out according to the sequencing sequence, the acquisition state is recorded, the success is 1, the failure is 0, if the acquisition of the former equipment fails, the acquisition of the latter equipment succeeds, the failure prediction is recorded, the data are accumulated in sequence, and the prediction failure times of the acquisition in the current round are determined.
3. The self-learning based communication success rate prediction method according to claim 1,
the respective periods include a period of 00:00 to 08:00, a period of 08:00 to 16:00, a period of 16:00 to 00:00 of the day;
the specified period is one month.
4. A communication success rate prediction device based on self-learning is characterized by comprising:
the statistical calculation unit is used for counting the collection success times and the total times of each device in each time period and calculating the success rate of each device in each time period;
the prediction unit is used for carrying out weighted calculation according to the success rate of each device in the current time period and the previous acquisition state and predicting the communication success rate of each device;
the data acquisition unit is used for sequencing all the devices from high to low according to the prediction value of the communication success rate of the devices, acquiring data according to the sequencing sequence and counting the failure times of prediction;
the coefficient adjusting unit is used for adjusting and updating a weight coefficient in the equipment communication success rate prediction weighting calculation of the current time period according to the prediction failure times based on a self-learning mode;
further comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-3.
5. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110956067.2A CN113408834B (en) | 2021-08-19 | 2021-08-19 | Communication success rate prediction method and device based on self-learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110956067.2A CN113408834B (en) | 2021-08-19 | 2021-08-19 | Communication success rate prediction method and device based on self-learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113408834A CN113408834A (en) | 2021-09-17 |
| CN113408834B true CN113408834B (en) | 2021-12-21 |
Family
ID=77688901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110956067.2A Active CN113408834B (en) | 2021-08-19 | 2021-08-19 | Communication success rate prediction method and device based on self-learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408834B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139609A (en) * | 2015-08-18 | 2015-12-09 | 江苏林洋电子股份有限公司 | Dynamic time-sharing meter copying-reading method |
| CN107317605A (en) * | 2017-07-31 | 2017-11-03 | 广东电网有限责任公司电力科学研究院 | The communication success rate computational methods and device of a kind of power wire broadband carrier |
| CN108922157A (en) * | 2018-07-09 | 2018-11-30 | 深圳市科陆电子科技股份有限公司 | A kind of self study intelligent meter reading method and system |
| CN112286962A (en) * | 2020-10-26 | 2021-01-29 | 积成电子股份有限公司 | Electricity consumption information acquisition terminal meter reading success rate statistical method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5570552B2 (en) * | 2012-06-08 | 2014-08-13 | 日本瓦斯株式会社 | Delivery prediction system and delivery prediction method |
| US8912919B2 (en) * | 2013-01-15 | 2014-12-16 | Tata Consultancy Services Limited | Determination of resource consumption |
-
2021
- 2021-08-19 CN CN202110956067.2A patent/CN113408834B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139609A (en) * | 2015-08-18 | 2015-12-09 | 江苏林洋电子股份有限公司 | Dynamic time-sharing meter copying-reading method |
| CN107317605A (en) * | 2017-07-31 | 2017-11-03 | 广东电网有限责任公司电力科学研究院 | The communication success rate computational methods and device of a kind of power wire broadband carrier |
| CN108922157A (en) * | 2018-07-09 | 2018-11-30 | 深圳市科陆电子科技股份有限公司 | A kind of self study intelligent meter reading method and system |
| CN112286962A (en) * | 2020-10-26 | 2021-01-29 | 积成电子股份有限公司 | Electricity consumption information acquisition terminal meter reading success rate statistical method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113408834A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112037930B (en) | Infectious disease prediction equipment, method, device and storage medium | |
| CN108509325B (en) | Method and device for dynamically determining system timeout time | |
| CN112651785B (en) | Transaction amount real-time monitoring method and system | |
| CN112118143A (en) | Traffic prediction model, training method, prediction method, device, apparatus, and medium | |
| CN115034519A (en) | Method and device for predicting power load, electronic equipment and storage medium | |
| CN113516275A (en) | Power distribution network ultra-short term load prediction method and device and terminal equipment | |
| CN114860542A (en) | Trend prediction model optimization method, trend prediction model optimization device, electronic device, and medium | |
| CN111400141B (en) | Abnormity detection method and device | |
| CN116559667A (en) | Model training method and device, battery detection method and device, equipment and medium | |
| CN116539994A (en) | Substation main equipment operation state detection method based on multi-source time sequence data | |
| CN116819352A (en) | Self-adaptive setting method, device and equipment for battery threshold value and storage medium | |
| CN113408834B (en) | Communication success rate prediction method and device based on self-learning | |
| CN113902260A (en) | Information prediction method, information prediction device, electronic equipment and medium | |
| CN117370065B (en) | Abnormal task determining method, electronic equipment and storage medium | |
| CN112802483B (en) | Method, device and storage medium for optimizing intention recognition confidence threshold | |
| CN115577491A (en) | Parameter correction method and device, electronic equipment and storage medium | |
| CN116049765A (en) | Data analysis processing method, device and equipment | |
| CN115905021A (en) | Fuzzy test method and device, electronic equipment and storage medium | |
| CN114372689A (en) | Road network operation characteristic variable point identification method based on dynamic planning | |
| CN112418534A (en) | Method and device for predicting collection quantity, electronic equipment and computer readable storage medium | |
| CN118294818B (en) | Remaining charging time estimation method and device and electronic equipment | |
| CN118425821B (en) | Energy storage battery cell health status early warning method, device and readable medium | |
| CN110688373A (en) | OFFSET method based on logistic regression | |
| CN118494259B (en) | Charging station power optimization method, device and equipment based on zebra optimization algorithm | |
| CN113098129B (en) | Self-adaptive sampling method and system suitable for fluctuation signals |
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 |