CN112835770B - Method for evaluating working condition of court self-service marking terminal based on dense neural network model - Google Patents
Method for evaluating working condition of court self-service marking terminal based on dense neural network model Download PDFInfo
- Publication number
- CN112835770B CN112835770B CN202110433086.7A CN202110433086A CN112835770B CN 112835770 B CN112835770 B CN 112835770B CN 202110433086 A CN202110433086 A CN 202110433086A CN 112835770 B CN112835770 B CN 112835770B
- Authority
- CN
- China
- Prior art keywords
- neural network
- self
- dense neural
- working condition
- service
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3013—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is an embedded system, i.e. a combination of hardware and software dedicated to perform a certain function in mobile devices, printers, automotive or aircraft systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3051—Monitoring arrangements for monitoring the configuration of the computing system or of the computing system component, e.g. monitoring the presence of processing resources, peripherals, I/O links, software programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Machine Translation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a dense neural network model-based court self-service examination paper marking terminal working condition evaluation method, which comprises the following steps of: collecting the running state of a self-service marking terminal, and inputting the running state into a dense neural network in a nominal variable form; establishing a data set for training a dense neural network according to the historical work order; according to the rule of the service, a corresponding abnormal working condition reporting scheme is formulated; pre-training by using the large Chinese-English translation data widely existing on the Internet, and extracting the dense neural network parameters of the state conversion part in the translation problem as initial parameters; training the dense neural network by adopting a preset method; and evaluating the working condition of the self-service marking terminal by using the trained dense neural network, and determining a handling team needing intervention in the abnormal state handling work. Has the advantages that: the method can effectively reduce the time required by the abnormal recovery of the self-service marking terminal and greatly improve the service efficiency of the self-service marking terminal.
Description
Technical Field
The invention relates to the technical field of working condition evaluation, in particular to a method for evaluating the working condition of a court self-service marking terminal based on a dense neural network model.
Background
The deep neural network has wide application in classification problems, the dense neural network is always concerned by the research and industrial fields with strong expression capacity, the historical worksheet data of the dense neural network is in the magnitude of thousands of aiming at the problem of working condition evaluation, and the dense neural network is used for evaluation and is a proper technical scheme.
With the comprehensive improvement of the knowledge level of common people and law authority awareness and the comprehensive popularization and application of the marking-up registration system, the number of cases accepted by the court in the year is high for a long time, and 3084.5 thousands of cases accepted by the court at all levels in the year 2020, the few cases and the many cases are more and more prominent under the double pressure of the reform of the corporate officer. Therefore, in 2014, the highest people court guides all levels of people court to build litigation service halls, and the self-service terminal is introduced to provide self-service litigation service for the parties and relieve the working pressure of judges. Along with the rapid increase of the number of the terminal devices and the continuous improvement of the utilization rate of the self-service terminals, the frequency of the faults of the terminal devices is higher and higher, and partial faults even affect the development of normal business of a court, so that the working condition detection is carried out on the terminal devices, a rapid response mechanism is established, the faults are sensed in advance, and a proper disposal scheme is formulated, which is an urgent need.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a method for evaluating the working condition of a court self-service marking terminal based on a dense neural network model, so as to overcome the technical problems in the prior related art.
Therefore, the invention adopts the following specific technical scheme:
a court self-service examination paper marking terminal working condition evaluation method based on a dense neural network model comprises the following steps:
s1, collecting the running state of the self-service marking terminal, and inputting the running state into a dense neural network in a nominal variable form;
s2, establishing a data set for training a dense neural network according to the historical work order of the self-service marking terminal;
s3, making a corresponding abnormal working condition reporting scheme according to the self rule of the service in the self-service marking terminal;
s4, pre-training by utilizing Chinese-English translation big data widely existing on the Internet, and extracting dense neural network parameters of a state conversion part in a translation problem as initial parameters;
s5, training the dense neural network by adopting a preset method;
s6, evaluating the working condition of the self-service marking terminal by using the trained dense neural network, and determining a treatment team needing intervention in the abnormal state treatment work;
wherein, the training of the dense neural network by adopting a preset method in S5 specifically includes the following steps:
s51, setting iteration step size
；
S52, setting the objective function as the mean square error, namely
Wherein
In order to be a real label, the label,
labels given for the models;
s53, setting an iteration exit condition that the residual error of the verification set is less than
；
S54, setting the number of nodes of each layer of the dense neural network to be 64, 128 and 64 respectively, the number of input nodes to be 19 and the number of output nodes to be 7;
s55, selecting a relay linear activation function by each neuron node activation function of the dense neural network, namely
，
Is the activation value of the jth neuron of the ith layer,
is the output of the jth neuron at the ith layer;
s56, calculating the activation value of each neuron in a weighted bias mode, namely
Wherein
And
respectively calculating a weight vector and an offset for the jth neuron of the ith layer,
an input vector of the jth neuron of the ith layer;
s57, setting forgetting parameters
；
S58 setting moment parameters
；
S59, setting the activation function of the output layer node as a symbolic function, i.e.
Wherein
Is the activation value of the ith output layer node.
Further, the names of the modules of the self-service paper reading terminal in S1 include that the second-generation id card reader is abnormal, the microphone is abnormal, the barcode scanner is abnormal, the high scanning scan fails, the camera is abnormal, the printer lacks ink, the printer is jammed, the printer lacks paper, the module detects abnormal, the network is disconnected, the abnormal shutdown is performed, the dongle fails to verify, the dongle is not inserted, the authorization file is abnormal, the server authorization file is abnormal, the paper reading fails, the page is misaligned, the page data is lacking, and the like.
Further, the step of establishing a data set for training the dense neural network according to the historical work order of the self-service marking terminal by the S2 specifically includes the following steps:
s21, identifying the running state of the self-help marking terminal when the work order is generated according to the processing process of the historical work order;
s22, adopting a preset coding rule to code and express the running state of the self-service marking terminal, tracking the processing process of the worksheet, and knowing the intervention conditions of each part and position;
and S23, constructing a data set by taking the running state code of the self-service marking terminal as a characteristic and taking the intervention condition as a label.
Further, the preset encoding rule in S22 is: the code of +1 represents that the running state of the self-service marking terminal is normal, and the code of-1 represents that the running state of the self-service marking terminal is abnormal.
Further, the intervention in S22 is as follows: the-1 expression is adopted when the corresponding department or position is not involved, and the +1 expression is adopted when the corresponding department or position is involved.
Further, the abnormal working condition reporting scheme in S3 is specifically as follows:
for the abnormal working condition caused by the improper operation of the user, the report is not needed;
reporting is needed for the abnormal working condition which can cause negative influence on the work of the client.
Furthermore, the working condition abnormality to be reported needs to be properly solved after sale, part of the abnormality even needs to be mobilized to research and development departments for bottom layer repair, and a local team, an agent, a sales manager, a sub-main manager and even a main manager are required to work to eliminate adverse consequences caused by the working condition abnormality, so that a working condition abnormality reporting mechanism with classification needs to be established.
Further, the pre-training in S4 by using the inter-Chinese-English translation big data widely existing on the internet, and extracting the dense neural network parameter of the state transformation part in the translation problem as the initial parameter specifically includes the following steps:
s41, pre-training the dense neural network by utilizing Chinese and English translation problems widely existing on the Internet;
s42, searching Chinese and English sentence pairs on the Internet, and coding the Chinese sentences by using a long-time and short-time memory model;
s43, performing state conversion by using a dense neural network, and decoding the converted state by using a long-time and short-time memory model to obtain English sentences;
s44, training a neural network consisting of an encoder, a dense neural network and a decoder by using the correct English sentences and the cross entropy for generating the English sentences;
and S45, after the iteration of the preset times, extracting the parameters of the dense neural network part, and taking the parameters as the initial parameters of the dense neural network when the working condition is evaluated.
Further, each neuron in S56 comprises a dense neural network neuron and an output layer neuron.
The invention has the beneficial effects that: by providing the method for evaluating the working condition of the self-service marking terminal of the court litigation service hall, the working condition of the self-service marking terminal can be defined according to the working condition of the module, the working condition of the self-service marking terminal can be comprehensively and completely described, the incidence relation between the working condition of the self-service marking terminal and an intervention department in the abnormal handling process can be established, support is provided for the coordination and movement of teams, and the handling teams needing intervention in the abnormal handling work are determined.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of a method for evaluating the working condition of a court self-service scoring terminal based on a dense neural network model according to an embodiment of the invention;
FIG. 2 is a schematic network structure diagram of a method for evaluating the working condition of a court self-service marking terminal based on a dense neural network model according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a network structure adopted by a pre-training problem in a method for evaluating the working condition of a court self-service scoring terminal based on a dense neural network model according to an embodiment of the invention;
FIG. 4 is a flowchart of abnormal condition handling in a dense neural network model-based court self-service marking terminal condition evaluation method according to an embodiment of the invention;
fig. 5 is a schematic diagram showing comparison of corresponding time of faults in synchronous comparison after a model is on line in the method for evaluating the working condition of the court self-service marking terminal based on the dense neural network model according to the embodiment of the invention.
Detailed Description
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
According to the embodiment of the invention, a method for evaluating the working condition of the court self-service marking terminal based on a dense neural network model is provided.
Referring to the drawings and the detailed description, the invention is further explained, as shown in fig. 1 to 5, according to the method for evaluating the working condition of the court self-help scoring terminal based on the dense neural network model, the method for evaluating the working condition of the court self-help scoring terminal based on the dense neural network model comprises the following steps:
s1, collecting the running state of the self-service marking terminal, and inputting the running state into a dense neural network in the form of nominal variables;
the names of the modules of the self-service paper reading terminal in the S1 include second-generation ID card reader abnormity, microphone abnormity, bar code scanner abnormity, high scanning failure, camera abnormity, printer ink shortage, printer paper jam, printer paper shortage, module detection abnormity, network disconnection, abnormal shutdown, dongle verification failure, dongle non-insertion, authorized document abnormity, server authorized document abnormity, paper reading failure, page dislocation, page data shortage and the like.
Specifically, the self-service marking terminal module and the identification thereof are shown in the following table:
the second-generation ID card reading abnormity is marked as AIC, the code of the AIC is +1 to represent that the ID card runs normally, -1 to represent that the ID card runs abnormally, and the like.
S2, establishing a data set for training a dense neural network according to a historical work order (the recorded fault information and the corresponding relation between departments or personnel mobilized in the process of actually solving the work order) of the self-service marking terminal;
the S2 specifically comprises the following steps of establishing a data set for training the dense neural network according to the historical work order of the self-service marking terminal:
s21, identifying the running state of the self-help marking terminal when the work order is generated according to the processing process of the historical work order;
s22, adopting the coding rule in S1 to code and express the running state of the self-service marking terminal, tracking the processing process of the work order and knowing the intervention condition of each part and position;
specifically, the intervention in S22 is as follows: the-1 expression is adopted when the corresponding department or position is not involved, and the +1 expression is adopted when the corresponding department or position is involved.
And S23, constructing a data set by taking the running state code of the self-service marking terminal as a characteristic and taking the intervention condition as a label.
S3, making a corresponding abnormal working condition reporting scheme according to the self rule of the service in the self-service marking terminal;
in the actual business development process, some working condition abnormalities may be generated by improper operations of users, the abnormalities are slight and even can not be reported, some working condition abnormalities can cause great negative effects on the work of customers, the abnormalities of the working condition abnormalities firstly need to be properly solved after sale, part of the abnormalities even need to invoke research and development departments to carry out bottom layer repair, and meanwhile, local teams, agents, sales managers, subsidiary managers and even general managers need to develop work to eliminate adverse consequences caused by the working condition abnormalities, so a graded classified working condition abnormality reporting mechanism needs to be established.
S4, pre-training by utilizing Chinese-English translation big data widely existing on the Internet, and extracting dense neural network parameters of a state conversion part in a translation problem as initial parameters;
due to the fact that the data volume of the historical work order is limited, the problem that the application is wide is considered to be used for pre-training the parameters of the dense network, and the initial parameters of the dense network are obtained. Analysis on the problems shows that the data forms of the module fault information and the text have similarity, namely the data forms are nominal variables, so that the large data of Chinese-English translation widely existing on the Internet are utilized to perform pre-training, and dense neural network parameters of a state conversion part in the translation problem are extracted and used as initial parameters.
Specifically, the pre-training in S4 by using the inter-Chinese-English translation big data widely existing on the internet, and extracting the dense neural network parameter of the state transformation part in the translation problem as the initial parameter includes the following steps:
s41, pre-training the dense neural network by utilizing Chinese and English translation problems widely existing on the Internet;
s42, collecting Chinese and English sentence pairs on the Internet, and coding the Chinese sentences by using a long-time and short-time memory model (LSTM);
s43, performing state conversion by using a dense neural network, and decoding the converted state by using a long-time and short-time memory model to obtain a final English sentence;
s44, training a neural network consisting of an encoder, a dense neural network and a decoder by using the correct English sentences and the cross entropy for generating the English sentences;
and S45, after the iteration of the preset times, extracting the parameters of the dense neural network part, and taking the parameters as the initial parameters of the dense neural network when the working condition is evaluated.
S5, training the dense neural network by adopting a preset method;
wherein, the training of the dense neural network by adopting a preset method in S5 specifically includes the following steps:
s51, setting iteration step size
；
S52, setting the objective function as the mean square error, namely
Wherein
In order to be a real label, the label,
labels given for the models;
s53, setting an iteration exit condition that the residual error of the verification set is less than
；
S54, setting the number of nodes of each layer of the dense neural network to be 64, 128 and 64 respectively, the number of input nodes to be 19 and the number of output nodes to be 7;
s55, selecting a relay linear activation function by each neuron node activation function of the dense neural network, namely
，
Is the activation value of the jth neuron of the ith layer,
is the output of the jth neuron at the ith layer;
s56, calculating each neuron (including dense spirit) by adopting a weighted bias modeVia network neurons and output layer neurons), i.e., the activation value
Wherein
And
respectively calculating a weight vector and an offset for the jth neuron of the ith layer,
an input vector of the jth neuron of the ith layer;
s57, setting forgetting parameters
；
S58 setting moment parameters
；
S59, setting the activation function of the output layer node as a symbolic function, i.e.
Wherein
Is the activation value of the ith output layer node.
And S6, evaluating the working condition of the self-service marking terminal by using the trained dense neural network, and determining a treatment team needing intervention in the abnormal state treatment work.
In summary, by means of the technical scheme provided by the invention, by providing the method for evaluating the working condition of the self-service examination paper marking terminal of the court litigation service hall, the working condition of the self-service examination paper marking terminal can be defined according to the running state of the module, the working condition of the self-service examination paper marking terminal can be comprehensively and completely described, the incidence relation between the working condition of the self-service examination paper marking terminal and an intervention department in an abnormal handling process can be established, support is provided for coordination and movement of teams, and a handling team needing intervention in the abnormal handling work is determined.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. The method for evaluating the working condition of the court self-service marking terminal based on the dense neural network model is characterized by comprising the following steps of:
s1, collecting the running state of the self-service marking terminal, and inputting the running state into a dense neural network in a nominal variable form;
s2, establishing a data set for training a dense neural network according to the historical work order of the self-service marking terminal;
s3, making a corresponding abnormal working condition reporting scheme according to the self rule of the service in the self-service marking terminal;
s4, pre-training by utilizing Chinese-English translation big data widely existing on the Internet, and extracting dense neural network parameters of a state conversion part in a translation problem as initial parameters;
s5, training the dense neural network by adopting a preset method;
s6, evaluating the working condition of the self-service marking terminal by using the trained dense neural network, and determining a treatment team needing intervention in the abnormal state treatment work;
wherein, the training of the dense neural network by adopting a preset method in S5 specifically includes the following steps:
s51, setting iteration step size
；
S52, setting the objective function as the mean square error, namely
Wherein
In order to be a real label, the label,
labels given for the models;
s53, setting an iteration exit condition that the residual error of the verification set is less than
；
S54, setting the number of nodes of each layer of the dense neural network to be 64, 128 and 64 respectively, the number of input nodes to be 19 and the number of output nodes to be 7;
s55, selecting a relay linear activation function by each neuron node activation function of the dense neural network, namely
，
Is the activation value of the jth neuron of the ith layer,
is the output of the jth neuron at the ith layer;
s56, calculating the activation value of each neuron in a weighted bias mode, namely
Wherein
And
respectively calculating a weight vector and an offset for the jth neuron of the ith layer,
an input vector of the jth neuron of the ith layer;
s57, setting forgetting parameters
；
S58 setting moment parameters
；
S59, setting the activation function of the output layer node as a symbolic function, i.e.
Wherein
Is the activation value of the ith output layer node.
2. The method for evaluating the working condition of the dense neural network model-based court self-service marking terminal, according to claim 1, wherein names of modules of the self-service marking terminal in the S1 include second-generation identity card reader abnormality, microphone abnormality, barcode scanner abnormality, high-scan scanning failure, camera abnormality, printer ink shortage, printer paper jam, printer paper shortage, module detection abnormality, network disconnection, abnormal shutdown, dongle verification failure, dongle non-insertion, authorization file abnormality, server authorization file abnormality, marking failure, page dislocation, page data shortage and the like.
3. The method for evaluating the working condition of the dense neural network model-based court self-service scoring terminal according to claim 1, wherein the step of S2 establishing the data set for training the dense neural network according to the historical work order of the self-service scoring terminal specifically comprises the following steps:
s21, identifying the running state of the self-help marking terminal when the work order is generated according to the processing process of the historical work order;
s22, adopting a preset coding rule to code and express the running state of the self-service marking terminal, tracking the processing process of the worksheet, and knowing the intervention conditions of each part and position;
and S23, constructing a data set by taking the running state code of the self-service marking terminal as a characteristic and taking the intervention condition as a label.
4. The method for evaluating the working condition of the dense neural network model-based court self-service marking terminal, according to claim 3, wherein the preset coding rule in the S22 is as follows: the code of +1 represents that the running state of the self-service marking terminal is normal, and the code of-1 represents that the running state of the self-service marking terminal is abnormal.
5. The method for evaluating the working condition of the court self-service marking terminal based on the dense neural network model as claimed in claim 3, wherein the intervention condition in S22 is as follows: the-1 expression is adopted when the corresponding department or position is not involved, and the +1 expression is adopted when the corresponding department or position is involved.
6. The method for evaluating the working condition of the courthouse self-service marking terminal based on the dense neural network model as claimed in claim 1, wherein the reporting scheme of the abnormal working condition in the S3 is as follows:
for the abnormal working condition caused by the improper operation of the user, the report is not needed;
reporting is needed for the abnormal working condition which can cause negative influence on the work of the client.
7. The method for evaluating the working condition of the dense neural network model-based court self-service examination paper terminal, as claimed in claim 6, is characterized in that the working condition abnormality to be reported needs to be properly solved after sale, part of the abnormality even needs to mobilize research and development departments to perform bottom layer repair, and a local team, an agent, a sales manager, a vice manager and even a main manager need to work to eliminate adverse consequences caused by the working condition abnormality, so that a working condition abnormality reporting mechanism with classification needs to be established.
8. The method for evaluating the working condition of the court self-service marking terminal based on the dense neural network model as claimed in claim 1, wherein the step of pre-training by using the widely existing Chinese-English translation big data on the Internet in S4 and extracting the dense neural network parameters of the state transformation part in the translation problem as initial parameters specifically comprises the following steps:
s41, pre-training the dense neural network by utilizing Chinese and English translation problems widely existing on the Internet;
s42, searching Chinese and English sentence pairs on the Internet, and coding the Chinese sentences by using a long-time and short-time memory model;
s43, performing state conversion by using a dense neural network, and decoding the converted state by using a long-time and short-time memory model to obtain English sentences;
s44, training a neural network consisting of an encoder, a dense neural network and a decoder by using the correct English sentences and the cross entropy for generating the English sentences;
and S45, after the iteration of the preset times, extracting the parameters of the dense neural network part, and taking the parameters as the initial parameters of the dense neural network when the working condition is evaluated.
9. The method for assessing the working condition of the court self-service marking terminal based on the dense neural network model as claimed in claim 1, wherein each neuron in the S56 comprises a dense neural network neuron and an output layer neuron.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110433086.7A CN112835770B (en) | 2021-04-22 | 2021-04-22 | Method for evaluating working condition of court self-service marking terminal based on dense neural network model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110433086.7A CN112835770B (en) | 2021-04-22 | 2021-04-22 | Method for evaluating working condition of court self-service marking terminal based on dense neural network model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112835770A CN112835770A (en) | 2021-05-25 |
| CN112835770B true CN112835770B (en) | 2021-08-06 |
Family
ID=75929834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110433086.7A Active CN112835770B (en) | 2021-04-22 | 2021-04-22 | Method for evaluating working condition of court self-service marking terminal based on dense neural network model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112835770B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113554077A (en) * | 2021-07-13 | 2021-10-26 | 南京铉盈网络科技有限公司 | Working condition evaluation and traffic prediction method based on multi-mode neural network model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108490904A (en) * | 2018-05-10 | 2018-09-04 | 东北大学 | A kind of energy resource system Optimization Scheduling based on the operation of equipment multi-state |
| CN109948858A (en) * | 2019-03-25 | 2019-06-28 | 东北大学 | Operating mode's switch method based on data-driven |
| CN111222549A (en) * | 2019-12-30 | 2020-06-02 | 航天时代飞鸿技术有限公司 | Unmanned aerial vehicle fault prediction method based on deep neural network |
-
2021
- 2021-04-22 CN CN202110433086.7A patent/CN112835770B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108490904A (en) * | 2018-05-10 | 2018-09-04 | 东北大学 | A kind of energy resource system Optimization Scheduling based on the operation of equipment multi-state |
| CN109948858A (en) * | 2019-03-25 | 2019-06-28 | 东北大学 | Operating mode's switch method based on data-driven |
| CN111222549A (en) * | 2019-12-30 | 2020-06-02 | 航天时代飞鸿技术有限公司 | Unmanned aerial vehicle fault prediction method based on deep neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112835770A (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200034689A1 (en) | A method for retrieving a recommendation from a knowledge database of a ticketing system | |
| CN109992668A (en) | A kind of enterprise's the analysis of public opinion method and apparatus based on from attention | |
| CN112232252B (en) | Transmission chain unsupervised domain adaptive fault diagnosis method based on optimal transportation | |
| CN112835770B (en) | Method for evaluating working condition of court self-service marking terminal based on dense neural network model | |
| CN110781672A (en) | Question bank production method and system based on machine intelligence | |
| CN113676343B (en) | Fault source positioning method and device for power communication network | |
| CN116402630B (en) | Financial risk prediction method and system based on characterization learning | |
| CN112487786A (en) | Natural language model pre-training method based on disorder rearrangement and electronic equipment | |
| CN114722190A (en) | Deep learning based automatic ontology extraction to detect new domain knowledge | |
| CN113537200A (en) | Information backfill method, device, equipment and medium based on image recognition | |
| CN115062117A (en) | Method for automatically generating and classifying documents based on natural language processing technology | |
| CN114357171A (en) | Emergency event processing method and device, storage medium and electronic equipment | |
| Rajkumar et al. | Bridge infrastructure management system: autoencoder approach for predicting bridge condition ratings | |
| Qamar et al. | Detecting compliance of privacy policies with data protection laws | |
| CN117688488A (en) | Log anomaly detection method based on semantic vectorization representation | |
| CN117290508A (en) | Post-loan text data processing method and system based on natural language processing | |
| Čepin | Comparison of methods for dependency determination between human failure events within human reliability analysis | |
| CN113554077A (en) | Working condition evaluation and traffic prediction method based on multi-mode neural network model | |
| Larsson et al. | Automated invoice handling with machine learning and OCR | |
| EP4085343A1 (en) | Domain based text extraction | |
| Wang et al. | Knockoffs-SPR: Clean Sample Selection in Learning With Noisy Labels | |
| Alexander et al. | Digitizing hand-written data with automated methods: A pilot project using the 1990 US Census | |
| CN112487211B (en) | Rail transit knowledge base construction method and system | |
| CN115906768B (en) | Enterprise informatization data compliance assessment method, system and readable storage medium | |
| CN116956168B (en) | Text watermark processing method and device, electronic 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 |