CN113836291B - Data processing method, device, equipment and storage medium - Google Patents
Data processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113836291B CN113836291B CN202111154874.9A CN202111154874A CN113836291B CN 113836291 B CN113836291 B CN 113836291B CN 202111154874 A CN202111154874 A CN 202111154874A CN 113836291 B CN113836291 B CN 113836291B
- Authority
- CN
- China
- Prior art keywords
- data
- online
- offline
- recommendation model
- difference
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 71
- 230000000007 visual effect Effects 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims description 46
- 238000012800 visualization Methods 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 16
- 238000003012 network analysis Methods 0.000 claims description 12
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000003058 natural language processing Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- 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
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Information Transfer Between Computers (AREA)
- Debugging And Monitoring (AREA)
Abstract
The disclosure provides a data processing method, a device, equipment and a storage medium, relates to the technical field of computers, and in particular relates to the artificial intelligent fields of intelligent recommendation, natural language processing, deep learning and the like. The data processing method comprises the following steps: responding to the difference between an online recommendation model and an offline recommendation model, and acquiring data to be compared based on the online recommendation model and the offline recommendation model; acquiring difference data of the difference based on the data to be compared; performing a processing operation based on the difference data, the processing operation comprising: and displaying the visual image and text corresponding to the difference data, and/or positioning the reason of the difference based on the difference data. The present disclosure may enable automated processing of differences between offline and online recommendation models.
Description
Technical Field
The disclosure relates to the technical field of computers, in particular to the field of artificial intelligence such as intelligent recommendation, natural language processing, deep learning and the like, and particularly relates to a data processing method, device, equipment and storage medium.
Background
With the development of intelligence, a user can be recommended with a suitable recommended resource based on a recommendation model, and the recommended resource is an article. The recommendation model may include an offline recommendation model and an online recommendation model for the same batch of samples. An offline predicted value may be obtained based on the offline recommendation model, and an online predicted value may be obtained based on the online recommendation model.
In the related art, when the offline predicted value is inconsistent with the online predicted value, the difference between the offline recommendation model and the online recommendation model is detected manually.
Disclosure of Invention
The present disclosure provides a data processing method, apparatus, device, and storage medium.
According to an aspect of the present disclosure, there is provided a data processing method including: responding to the difference between an online recommendation model and an offline recommendation model, and acquiring data to be compared based on the online recommendation model and the offline recommendation model; acquiring difference data of the difference based on the data to be compared; performing a processing operation based on the difference data, the processing operation comprising: and displaying the visual image and text corresponding to the difference data, and/or positioning the reason of the difference based on the difference data.
According to another aspect of the present disclosure, there is provided a data processing apparatus including: the first acquisition module is used for responding to the difference between an online recommendation model and an offline recommendation model and acquiring data to be compared based on the online recommendation model and the offline recommendation model; the second acquisition module is used for acquiring difference data of the difference based on the data to be compared; a processing module for performing processing operations based on the difference data, the processing operations comprising: and displaying the visual image and text corresponding to the difference data, and/or positioning the reason of the difference based on the difference data.
According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the above aspects.
According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method according to any one of the above aspects.
According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method according to any of the above aspects.
According to the technical scheme, the automatic processing of the difference between the offline recommendation model and the online recommendation model can be realized.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure;
FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure;
FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure;
FIG. 5 is a schematic diagram according to a fifth embodiment of the present disclosure;
FIG. 6 is a schematic diagram according to a sixth embodiment of the present disclosure;
FIG. 7 is a schematic diagram according to a seventh embodiment of the present disclosure;
fig. 8 is a schematic diagram of an electronic device for implementing any of the data processing methods of the embodiments of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In the related art, when the offline predicted value is inconsistent with the online predicted value, the difference between the offline recommendation model and the online recommendation model is detected manually, and automatic processing of the difference between the offline recommendation model and the online recommendation model cannot be realized.
In order to enable automated handling of the differences described above, the present disclosure provides the following embodiments.
Fig. 1 is a schematic diagram of a first embodiment of the present disclosure, where the present embodiment provides a data processing method, the method includes:
101. and responding to the difference between the online recommendation model and the offline recommendation model, and acquiring data to be compared based on the online recommendation model and the offline recommendation model.
102. And acquiring difference data of the difference based on the data to be compared.
103. Performing a processing operation based on the difference data, the processing operation comprising: and displaying the visual image and text corresponding to the difference data, and/or positioning the reason of the difference based on the difference data.
The application environment of the data processing method provided in this embodiment may be as shown in fig. 2, where the application environment may include: an online system 201, an offline system 202, and a visualization system 203.
The execution body of this embodiment may be referred to as a data processing apparatus, which may be located in the visualization system 203, and the visualization system may be software, hardware, or a combination of both. The visualization system can be located in an electronic device, the electronic device can be a server or a user terminal, the server can be a cloud server or a local server, and the user terminal can comprise a mobile device (such as a mobile phone and a tablet computer), a wearable device (such as a smart watch and a smart bracelet), a smart home device (such as a smart television and a smart sound box) and the like.
With respect to models, the model is generally divided into an offline phase and an online phase, where the offline phase refers to training the model offline to generate the model to be employed online. The online stage refers to inputting online inputs (such as recommended resources) into an online model to generate corresponding model outputs (such as recommendation probabilities corresponding to the recommended resources), the recommended resources being, for example, articles, short videos, etc. to be recommended to the user.
The input of the recommendation model is a recommendation resource, the output is a recommendation probability of the recommendation resource, and the recommendation model can be a deep neural network (Deep Neural Networks, DNN) model.
The model of the offline phase may be referred to as an offline recommendation model, and the model of the online phase may be referred to as an online recommendation model.
The system corresponding to the online phase may be referred to as an online system 201 with an online recommendation model therein, and the system corresponding to the offline phase may be referred to as an offline system 202 with an offline recommendation model therein.
In order to improve the accuracy of recommended resources, tests may be performed prior to formal application.
During the test, the same batch of estimated samples can be adopted, and the offline estimated value and the online estimated value are obtained through an offline recommended model and an online recommended model respectively.
The predicted samples may include recommended resource samples, and the predicted value is a recommended probability value for the recommended resource samples.
If the offline predicted value is inconsistent with the online predicted value, the source of the discrepancy may be located.
In the related art, a manual mode is generally adopted to locate the difference source, however, the manual mode has poor intuitiveness and cannot be automatically attributed, namely, an automatic processing scheme for the difference is lacked.
In this embodiment, the estimated samples may be input into the online recommendation model and the offline recommendation model respectively to obtain the online prediction value and the offline prediction value, and if the online prediction value and the offline prediction value are different, or the difference value of the online prediction value and the offline prediction value is outside the threshold value of the preset range, it is determined that the online recommendation model and the offline recommendation model have differences.
The data to be compared may include data describing the network topology and/or forward output data of nodes in the model.
The difference data may be obtained based on the to-be-compared data, and the difference data may be used to describe network topology differences between the online recommendation model and the offline recommendation model and/or forward output data differences of the nodes.
Visualization (Visualization) is the conversion of data into graphics or text that is displayed on a screen using computer graphics and image processing techniques.
Visual graphics refer to the fact that the visual content can be graphics and/or text.
For example, referring to FIG. 3, dots represent nodes in the model, black dots correspond to the online recommendation model, and white dots correspond to the offline recommendation model. The value of the dot edge is the forward output data of the corresponding node. The differences between the two can comprise network differences and data differences, the differences can be displayed, and the differences can be attributed.
In this embodiment, by acquiring the data to be compared, acquiring the difference data based on the data to be compared, and performing the processing operation based on the difference data, the automatic processing of the difference between the offline recommendation model and the online recommendation model can be realized.
In some embodiments, the data to be compared comprises: the obtaining the data to be compared based on the online recommendation model and the offline recommendation model comprises the following steps:
acquiring online node data from an online log of an online system of the online recommendation model, wherein the online node data are acquired for the online system and recorded in the online log, the online node data are forward output data of nodes in the online recommendation model, and the forward output data are acquired when the online system takes samples to be adopted as input of the online recommendation model and the online recommendation model is adopted to carry out forward output processing on the samples to be adopted;
the offline node data are obtained for the offline system and recorded in the offline log, the offline node data are forward output data of nodes in the offline recommendation model, the forward output data are obtained when the offline system takes samples to be adopted as input of the offline recommendation model and the offline recommendation model is adopted to carry out forward output processing on the samples to be adopted.
In some embodiments, the data to be compared comprises: the obtaining the data to be compared based on the online recommendation model and the offline recommendation model comprises the following steps: acquiring a pre-stored online network topology file from an online system of the online recommendation model, and carrying out network analysis on the online network topology file to acquire the online network description data; and acquiring a pre-stored offline network topology file from an offline system of the offline recommendation model, and carrying out network analysis on the offline network topology file to acquire the offline network description data.
As shown in fig. 4, an online log may be stored in an online system (not shown in fig. 4), online node data may be recorded in the online log, an offline log may be stored in an offline system (not shown in fig. 4), and offline node data may be recorded in the offline log.
As shown in fig. 4, an online network topology file may be stored in an online system (not shown in fig. 4), online network description data may be recorded in the online network topology file, an offline network topology file may be stored in an offline system (not shown in fig. 4), and offline network description data may be recorded in the offline network topology file.
The online network description data is used for describing the network topological relation of the online recommendation model, and the offline network description data is used for describing the network topological relation of the offline recommendation model.
Taking online network description data as an example, the online network description data may include node information in an online recommendation model, where the node information includes: node name, the number of neurons a node comprises, the input relationship of the node, the output relationship, etc. The offline network description data is similar.
The visualization system may obtain online logs from the online system and offline logs from the offline system.
After the visualization system obtains the online log and the offline log, a data analysis service may be started, and the online log and the offline log are subjected to log analysis by the data analysis service to obtain online node data and offline node data, where the node data in fig. 4 includes the online node data and the offline node data.
After the visualization system acquires the online network topology file and the offline network topology file, a network analysis service may be started, and the network analysis service performs network analysis on the online network topology file and the offline network topology file to obtain online network description data and offline network description data, where the network description data in fig. 4 includes the online network description data and the offline network description data.
When the network is analyzed, the input-output relationship of each node of the network can be analyzed, so that a directed network topological graph is formed, the topological relationship is put in storage, and the nodes are marked with the belonged relationship, for example, the node belongs to online and offline, is marked as common, only belongs to online, is marked as on, only belongs to offline and is marked as off.
Further, as shown in fig. 4, the network description data and node data may be stored in a database, such as Mysql, for subsequent data.
The steps before the data is stored in the database are described by taking the execution of the visualization system as an example, or other systems may perform the processing, and the data is stored in the database, and then the visualization system may acquire the data from the database to perform subsequent processing such as calculation, display, and attribution of differences.
By log-based parsing, online node data and offline node data can be obtained.
The online network description data and the offline network description data can be obtained based on network parsing.
The online network topology file and the offline network topology file may be pre-stored in the corresponding systems.
The online node data in the online log may be obtained by an online system using an online recommendation model, and the offline node data in the offline log may be obtained by an offline system using an offline recommendation model.
Wherein the recommendation model is typically a deep neural network model, which may include multiple layers, each of which may include multiple nodes, each of which may include one or more neurons.
Further, the multi-layer recommendation model may be divided into an input layer, a hidden layer and an output layer, and the pre-estimated sample is input from the input layer, passes through the input layer to the hidden layer, and then passes through the hidden layer to the output layer, which may be referred to as forward output processing. In the forward output processing, the forward output data of each node can be used as the node data of the corresponding model.
The node data of the recommendation model may be a value between [0,1], such as 0.2,0.6, etc.
The description of the recommendation model applies to both online recommendation models and offline recommendation models, unless otherwise specified. Similarly, the description of node data applies to both online node data and offline node data. The description of the network description data is applicable to online network description data, offline network description data, and the like.
In some embodiments, the method may further comprise: obtaining an estimated value difference value of each estimated sample in a plurality of estimated samples, wherein the estimated value difference value is a difference value between an online estimated value and an offline estimated value, the online estimated value is obtained after the online recommended model performs the estimated processing on each estimated sample, and the offline estimated value is obtained after the offline recommended model performs the estimated processing on each estimated sample; and taking the estimated sample with the largest difference value of the estimated values as the sample to be adopted.
The same batch of estimated samples can be respectively used as the input of an online recommendation model and an offline recommendation model, the online recommendation model performs the estimated processing on the batch of estimated samples to obtain online estimated values of all the estimated samples, and similarly, the offline recommendation model outputs offline estimated values of all the estimated samples. The estimated sample may be a recommended resource, for example, an article, and the estimated value (online or offline) is a recommended probability corresponding to the article.
The online predicted value and the offline predicted value can be values between 0 and 1, and the absolute value of the difference between the online predicted value and the offline predicted value is taken as the difference value of the predicted values.
It will be appreciated that if there are a plurality of estimated samples of the maximum predicted value difference, one may be randomly selected as the sample to be employed.
It will be appreciated that selecting the estimated sample with the largest difference between the estimated values as the sample to be employed is an example, and other manners may be adopted, such as selecting the sample to be employed with the next highest difference, based on the difference between the estimated values.
By taking the estimated sample with the largest difference of the estimated values as the sample to be adopted, the sample with more representativeness can be selected to analyze the difference between the online recommendation model and the offline recommendation model.
In some embodiments, the online recommendation model performs a forward output process of the online recommendation model after a first pre-estimated switch is turned on, and the offline recommendation model performs a forward output process of the offline recommendation model after a second pre-estimated switch is turned on, the method further comprising: generating a request based on the sample to be employed; and based on the request, starting the first pre-estimated switch of the online recommendation model and the second pre-estimated switch of the offline recommendation model.
As shown in fig. 5, it is assumed that the predictive value is represented by q, and the q-difference is the largest and the absolute value of the difference of the offline predictive value and the online predictive value is the largest. Different estimated samples can be identified by nid, so that the estimated sample of nid with the largest q difference value can be obtained.
After obtaining the estimated sample of nid with the largest q difference, the estimated sample can be carried in a request and sent to an online system and an offline system, the request is used for triggering and starting an estimated switch of an online recommendation model and an estimated switch of an offline recommendation model, the estimated switch of the online recommendation model can be called a first estimated switch for distinguishing, the estimated switch of the offline recommendation model can be called a second estimated switch, and accordingly corresponding online node data and offline node data are obtained through the online recommendation model and the offline recommendation model and recorded in an online log and an offline log respectively.
Specifically, for an online system, dump can be started, the dump-started system prints out the forward output of each node of each layer from the input layer to the output layer in the model estimation process, and starts a debug, and the debug records a sample (sample or feasign) after a request (request) is read in, an online pre-estimated value (q) and the like in an online log (log).
For the offline system, format conversion can be performed on the samples in the online log, that is, the estimated samples serving as the input of the online recommendation model and the estimated samples serving as the input of the offline recommendation model are consistent in sample content, but the formats may not be consistent due to respective requirements, so that during offline processing, format conversion can be performed first, the samples in the online log are converted into input sample formats recognized by the offline training environment, offline training is started, dump is started, offline estimation can be performed on the samples, and the output of each layer of the estimation process is recorded in a designated file to serve as offline log.
After the online log and the offline log are obtained, subsequent processing can be performed. The subsequent processing is, for example, to obtain online node data and offline node data based on the online log and the offline log, to obtain node difference data based on the online node data and the offline node data, and the like.
The specific process may include: the platform interface is requested, the platform back-end processing, the task link is returned, and the task link is inserted into the pipeline report. The platform may refer to a visualization system, and back-end processing such as log parsing obtains node data. Wherein different processes can be implemented based on different tasks, and thus the task related processes described above can be performed.
The processing flow of the online recommendation model and the offline recommendation model can be triggered by starting the pre-estimated switch.
In some embodiments, the data to be compared comprises: online and offline network description data, and online and offline node data, the difference data comprising: topology difference data and node difference data, the obtaining the difference data of the difference based on the data to be compared includes: if the online network description data and the offline network description data corresponding to the same node identifier are different, using the different online network description data and offline network description data as the topology difference data; and/or if the online node data and the offline node data corresponding to the same node identifier are different, using the different online node data and the offline node data as the node difference data.
As shown in fig. 4, the online network description data and the offline network description data, and the online node data and the offline node data may be stored in Mysql, the visualization system may acquire the data from Mysql, perform data processing on the data, where the data processing includes a process of acquiring difference data, and further may generate a visual image based on the data, and so on.
Further, as shown in fig. 4, after data processing, the full-scale network, the difference network, the data details, the difference data, the difference attribution, and the like may be displayed.
As shown in fig. 3, the network difference and the data difference are shown, and for the network difference, a node marked as on, a node marked as off, a node marked as common, but there are different nodes of input and output are included for illustration. For data differences, nodes with different node data may be presented.
Specifically, referring to fig. 3, the model corresponding to the black filled node is an online recommendation model, the model corresponding to the white filled node is an offline recommendation model, and for the node C, there is a difference in the topological relationship, that is, there is a difference between the online network description data and the offline network data, and therefore, there is topology difference data between the two. The online node data and the offline node data are different for the node D, E, F, and thus there is node difference data between them.
It will be appreciated that for visual distinction, taking node C as an example, node C of the online recommendation model and node C of the offline recommendation model 1 Not symbolically represented, however, both correspond to the same node identification in the data record for differential comparison.
By obtaining the topology difference data and the node difference data, the comparison of the difference of the network topology and the difference of the node data can be carried out, and the difference sources are enriched.
In some embodiments, the visual graphics include: and (3) a difference topological graph and/or node difference data, wherein the visual graph corresponding to the difference data is displayed, and the method comprises the following steps:
if the difference data comprise topology difference data, generating a difference topological graph corresponding to the difference based on the topology difference data, and displaying the difference topological graph; and/or if the difference data comprises node difference data, displaying the node difference data.
Visualization (Visualization) is the conversion of data into graphics or text that is displayed on a screen using computer graphics and image processing techniques.
Visual graphics refer to the fact that the visual content can be graphics and/or text.
As shown in fig. 3, the differences may include network differences and data differences, and for the network differences, since the output relationships of the nodes C are different, the corresponding network topologies may be generated based on the nodes C and their related nodes for presentation. In addition, the network difference may also show node data of each node, such as node data of C being 0.2, in addition to the network topology (nodes and relationships between nodes). For the data difference, the nodes with the difference and the corresponding node data can be displayed.
Further, the difference attribution may also be performed based on the difference data. The difference attribution is a cause of specifying a difference between the online recommendation model and the offline recommendation model, and includes, for example: network topology reasons, forward output data reasons, etc.
By displaying the topology map and/or the node data, the visualization is strong. In addition, the automatic attribution can be realized based on the difference data, and the attribution efficiency is high.
In some embodiments, at least one of the following is also included: generating an online panoramic topological graph based on the online network description data, and displaying the online panoramic topological graph; generating an offline panoramic topological graph based on the offline network description data, and displaying the offline panoramic topological graph; based on the online node data, displaying the data details of the nodes in the online recommendation model; and displaying the data details of the nodes in the offline recommendation model based on the offline node data.
Besides the above-mentioned difference display, full-scale display, that is, display of network topology corresponding to the online recommendation model, network topology corresponding to the offline recommendation model, data details of nodes in the online recommendation model and the offline recommendation model, and the like, may also be displayed.
In addition, the graph and the data may be combined during the display, for example, as shown in fig. 3, taking an online network model as an example, not only an online panoramic topological graph (upper left corner) of the online network model, but also node data of each node (for example, node data of node a is 0.5) are displayed.
In addition, for the data details, besides the node data (e.g., 0.5), the relationship of the nodes, such as on, off, common, or the like, may be included.
Through multiple display modes, richer information can be displayed.
The above describes the relevant steps of the method, respectively, and examples combining the various steps are given below. It will be understood that the steps in the following embodiments are not necessarily all selected, and may be reasonably selected and replaced according to actual requirements, and if there is no strong dependency relationship between the time sequence relationships of the steps, and not specifically described, there is no time sequence limitation relationship.
Fig. 6 is a schematic diagram of a sixth embodiment of the present disclosure, where the present embodiment provides a data processing method, the method includes:
601. the visualization system obtains a predicted value difference value of each predicted sample in the plurality of predicted samples.
602. If the difference value of the predicted value is larger than a preset threshold value, the visualization system determines that the difference exists between the online recommendation model and the offline recommendation model, and takes a predicted sample with the largest difference value of the predicted value as the sample to be adopted.
603. And the visualization system responds to the difference, generates a request based on the sample to be adopted, and starts the first estimated switch of the online recommendation model and the second estimated switch of the offline recommendation model based on the request.
604. And after the first pre-estimated switch of the online recommendation model of the online system is started, adopting the online recommendation model to perform forward output processing on the input sample to be adopted so as to obtain online node data and recording the online node data in an online log.
605. And after the second pre-estimated switch of the offline recommendation model of the offline system is started, performing forward output processing on the input sample to be adopted by adopting the offline recommendation model so as to obtain offline node data and recording the offline node data in an offline log.
606. The visualization system obtains an online log and an offline log, and performs data analysis on the online log and the offline log to obtain online node data and offline node data.
607. The visualization system acquires an online network topology file from the online system, acquires an offline network topology file from the offline system, and performs network analysis on the online network topology file and the offline network topology file to obtain online network description data and offline network description data.
608. The visualization system acquires topology difference data based on the online network description data and the offline network description data, and acquires node difference data based on the online node data and the offline node data.
609. The visualization system generates a difference topology map based on the topology difference data and presents the difference topology map, and the node difference data.
In the embodiment, the method can replace manual work, automatically locate whether the network topology has differences, locate difference reasons and the like, has high locating efficiency and strong visualization, can trace to the problem source node directly according to the topology, and gives the approximate possibility of occurrence of the problem.
Fig. 7 is a schematic diagram of a seventh embodiment of the present disclosure, the present embodiment provides a data processing apparatus 700, including: a first acquisition module 701, a second acquisition module 702, and a processing module 703.
The first obtaining module 701 is configured to obtain data to be compared based on the online recommendation model and the offline recommendation model in response to a difference between the online recommendation model and the offline recommendation model; the second obtaining module 702 is configured to obtain difference data of the difference based on the data to be compared; the processing module 703 is configured to perform processing operations based on the difference data, where the processing operations include: and displaying the visual image and text corresponding to the difference data, and/or positioning the reason of the difference based on the difference data.
In some embodiments, the data to be compared comprises: the first acquisition module is specifically configured to:
acquiring online node data from an online log of an online system of the online recommendation model, wherein the online node data are acquired for the online system and recorded in the online log, the online node data are forward output data of nodes in the online recommendation model, and the forward output data are acquired when the online system takes samples to be adopted as input of the online recommendation model and the online recommendation model is adopted to carry out forward output processing on the samples to be adopted;
the offline node data are obtained for the offline system and recorded in the offline log, the offline node data are forward output data of nodes in the offline recommendation model, the forward output data are obtained when the offline system takes samples to be adopted as input of the offline recommendation model and the offline recommendation model is adopted to carry out forward output processing on the samples to be adopted.
In some embodiments, further comprising:
the determining module is used for obtaining the pre-estimated value difference value of each estimated sample in the plurality of estimated samples, wherein the pre-estimated value difference value is the difference value between an online pre-estimated value and an offline pre-estimated value, the online pre-estimated value is obtained after the online recommendation model performs pre-estimated processing on each estimated sample, and the offline pre-estimated value is obtained after the offline recommendation model performs pre-estimated processing on each estimated sample; and taking the estimated sample with the largest difference value of the estimated values as the sample to be adopted.
In some embodiments, the online recommendation model performs a forward output process of the online recommendation model after a first pre-estimated switch is turned on, and the offline recommendation model performs a forward output process of the offline recommendation model after a second pre-estimated switch is turned on, the apparatus further comprising:
the generation module is used for generating a request based on the sample to be adopted;
and the starting module is used for starting the first estimated switch of the online recommendation model and the second estimated switch of the offline recommendation model based on the request.
In some embodiments, the data to be compared comprises: the first acquisition module is specifically configured to:
Acquiring a pre-stored online network topology file from an online system of the online recommendation model, and carrying out network analysis on the online network topology file to acquire the online network description data;
and acquiring a pre-stored offline network topology file from an offline system of the offline recommendation model, and carrying out network analysis on the offline network topology file to acquire the offline network description data.
In some embodiments, the data to be compared comprises: online and offline network description data, and online and offline node data, the difference data comprising: the second acquisition module is specifically configured to:
if the online network description data and the offline network description data corresponding to the same node identifier are different, using the different online network description data and offline network description data as the topology difference data; and/or the number of the groups of groups,
and if the online node data and the offline node data corresponding to the same node identification are different, taking the different online node data and the offline node data as the node difference data.
In some embodiments, the visual graphics include: the processing module is specifically configured to:
If the difference data comprise topology difference data, generating the difference topological graph corresponding to the difference based on the topology difference data, and displaying the difference topological graph;
and if the difference data comprises node difference data, displaying the node difference data.
In some embodiments, the processing module is further to perform at least one of:
generating an online panoramic topological graph based on the online network description data, and displaying the online panoramic topological graph;
generating an offline panoramic topological graph based on the offline network description data, and displaying the offline panoramic topological graph;
based on the online node data, displaying the data details of the nodes in the online recommendation model;
and displaying the data details of the nodes in the offline recommendation model based on the offline node data.
In this embodiment, by acquiring the data to be compared, acquiring the difference data based on the data to be compared, and performing the processing operation based on the difference data, the automatic processing of the difference between the offline recommendation model and the online recommendation model can be realized.
In the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public order colloquial is not violated.
It is to be understood that in the embodiments of the disclosure, the same or similar content in different embodiments may be referred to each other.
It can be understood that "first", "second", etc. in the embodiments of the present disclosure are only used for distinguishing, and do not indicate the importance level, the time sequence, etc.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 8 illustrates a schematic block diagram of an example electronic device 800 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile apparatuses, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing apparatuses. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 8, the electronic device 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.
Various components in electronic device 800 are connected to I/O interface 805, including: an input unit 806 such as a keyboard, mouse, etc.; an output unit 807 such as various types of displays, speakers, and the like; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, or the like. The communication unit 809 allows the electronic device 800 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 801 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the respective methods and processes described above, such as a data processing method. For example, in some embodiments, the data processing method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 800 via the ROM 802 and/or the communication unit 809. When a computer program is loaded into RAM 803 and executed by computing unit 801, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the data processing method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code 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 code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. 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. The 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.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (18)
1. A data processing method, comprising:
responding to the difference between an online recommendation model and an offline recommendation model, and acquiring data to be compared based on the online recommendation model and the offline recommendation model;
acquiring difference data of the difference based on the data to be compared;
performing a processing operation based on the difference data, the processing operation comprising: displaying the visual image-text corresponding to the difference data and/or positioning the reason of the difference based on the difference data;
Wherein the data to be compared includes: online and offline network description data, and online and offline node data, the difference data comprising: topology difference data and node difference data;
the online node data and the offline node data are obtained based on a sample to be taken, the method further comprising:
obtaining an estimated value difference value of each estimated sample in a plurality of estimated samples, wherein the estimated value difference value is a difference value between an online estimated value and an offline estimated value; and taking the estimated sample with the largest difference value of the estimated values as the sample to be adopted.
2. The method of claim 1, wherein the obtaining data to be compared based on the online recommendation model and the offline recommendation model comprises:
acquiring online node data from an online log of an online system of the online recommendation model, wherein the online node data are acquired for the online system and recorded in the online log, the online node data are forward output data of nodes in the online recommendation model, and the forward output data are acquired when the online system takes samples to be adopted as input of the online recommendation model and the online recommendation model is adopted to carry out forward output processing on the samples to be adopted;
The offline node data are obtained for the offline system and recorded in the offline log, the offline node data are forward output data of nodes in the offline recommendation model, the forward output data are obtained when the offline system takes samples to be adopted as input of the offline recommendation model and the offline recommendation model is adopted to carry out forward output processing on the samples to be adopted.
3. The method of claim 2, wherein the online pre-estimated value is obtained by pre-estimating the pre-estimated samples by the online recommendation model, and the offline pre-estimated value is obtained by pre-estimating the pre-estimated samples by the offline recommendation model;
and taking the estimated sample with the largest difference value of the estimated values as the sample to be adopted.
4. The method of claim 2, wherein the online recommendation model performs a forward output process of the online recommendation model after a first predictive switch is turned on, and the offline recommendation model performs a forward output process of the offline recommendation model after a second predictive switch is turned on, the method further comprising:
Generating a request based on the sample to be employed;
and based on the request, starting the first pre-estimated switch of the online recommendation model and the second pre-estimated switch of the offline recommendation model.
5. The method of claim 1, wherein the obtaining data to be compared based on the online recommendation model and the offline recommendation model comprises:
acquiring a pre-stored online network topology file from an online system of the online recommendation model, and carrying out network analysis on the online network topology file to acquire the online network description data;
and acquiring a pre-stored offline network topology file from an offline system of the offline recommendation model, and carrying out network analysis on the offline network topology file to acquire the offline network description data.
6. The method of any of claims 1-5, wherein the obtaining difference data for the difference based on the data to be compared comprises:
if the online network description data and the offline network description data corresponding to the same node identifier are different, using the different online network description data and offline network description data as the topology difference data; and/or the number of the groups of groups,
And if the online node data and the offline node data corresponding to the same node identification are different, taking the different online node data and the offline node data as the node difference data.
7. The method of claim 6, wherein the visualization comprises: and (3) a difference topological graph and/or node difference data, wherein the visual graph corresponding to the difference data is displayed, and the method comprises the following steps:
if the difference data comprise topology difference data, generating the difference topological graph corresponding to the difference based on the topology difference data, and displaying the difference topological graph; and/or the number of the groups of groups,
and if the difference data comprises node difference data, displaying the node difference data.
8. The method of claim 6, wherein the processing operation further comprises at least one of:
generating an online panoramic topological graph based on the online network description data, and displaying the online panoramic topological graph;
generating an offline panoramic topological graph based on the offline network description data, and displaying the offline panoramic topological graph;
based on the online node data, displaying the data details of the nodes in the online recommendation model;
And displaying the data details of the nodes in the offline recommendation model based on the offline node data.
9. A data processing apparatus comprising:
the first acquisition module is used for responding to the difference between an online recommendation model and an offline recommendation model and acquiring data to be compared based on the online recommendation model and the offline recommendation model;
the second acquisition module is used for acquiring difference data of the difference based on the data to be compared;
a processing module for performing processing operations based on the difference data, the processing operations comprising: displaying the visual image-text corresponding to the difference data and/or positioning the reason of the difference based on the difference data;
wherein the data to be compared includes: online and offline network description data, and online and offline node data, the difference data comprising: topology difference data and node difference data;
the online node data and the offline node data are obtained based on samples to be taken, the apparatus further comprising:
the determining module is used for obtaining the difference value of the predicted value of each predicted sample in the plurality of predicted samples, wherein the difference value of the predicted value is the difference value between an online predicted value and an offline predicted value; and taking the estimated sample with the largest difference value of the estimated values as the sample to be adopted.
10. The apparatus of claim 9, wherein the first acquisition module is specifically configured to:
acquiring online node data from an online log of an online system of the online recommendation model, wherein the online node data are acquired for the online system and recorded in the online log, the online node data are forward output data of nodes in the online recommendation model, and the forward output data are acquired when the online system takes samples to be adopted as input of the online recommendation model and the online recommendation model is adopted to carry out forward output processing on the samples to be adopted;
the offline node data are obtained for the offline system and recorded in the offline log, the offline node data are forward output data of nodes in the offline recommendation model, the forward output data are obtained when the offline system takes samples to be adopted as input of the offline recommendation model and the offline recommendation model is adopted to carry out forward output processing on the samples to be adopted.
11. The apparatus of claim 10, wherein the online pre-estimated value is obtained by pre-estimating the each pre-estimated sample by the online recommendation model, and the offline pre-estimated value is obtained by pre-estimating the each pre-estimated sample by the offline recommendation model.
12. The apparatus of claim 10, wherein the online recommendation model performs a forward output process of the online recommendation model after a first predictive switch is turned on, and the offline recommendation model performs a forward output process of the offline recommendation model after a second predictive switch is turned on, the apparatus further comprising:
the generation module is used for generating a request based on the sample to be adopted;
and the starting module is used for starting the first estimated switch of the online recommendation model and the second estimated switch of the offline recommendation model based on the request.
13. The apparatus of claim 10, wherein the first acquisition module is specifically configured to:
acquiring a pre-stored online network topology file from an online system of the online recommendation model, and carrying out network analysis on the online network topology file to acquire the online network description data;
and acquiring a pre-stored offline network topology file from an offline system of the offline recommendation model, and carrying out network analysis on the offline network topology file to acquire the offline network description data.
14. The apparatus according to any one of claims 9-13, wherein the second acquisition module is specifically configured to:
If the online network description data and the offline network description data corresponding to the same node identifier are different, using the different online network description data and offline network description data as the topology difference data; and/or the number of the groups of groups,
and if the online node data and the offline node data corresponding to the same node identification are different, taking the different online node data and the offline node data as the node difference data.
15. The apparatus of claim 14, wherein the visual graphics comprise: the processing module is specifically configured to:
if the difference data comprise topology difference data, generating the difference topological graph corresponding to the difference based on the topology difference data, and displaying the difference topological graph;
and if the difference data comprises node difference data, displaying the node difference data.
16. The apparatus of claim 14, wherein the processing module is further to perform at least one of:
generating an online panoramic topological graph based on the online network description data, and displaying the online panoramic topological graph;
generating an offline panoramic topological graph based on the offline network description data, and displaying the offline panoramic topological graph;
Based on the online node data, displaying the data details of the nodes in the online recommendation model;
and displaying the data details of the nodes in the offline recommendation model based on the offline node data.
17. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
18. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111154874.9A CN113836291B (en) | 2021-09-29 | 2021-09-29 | Data processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111154874.9A CN113836291B (en) | 2021-09-29 | 2021-09-29 | Data processing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113836291A CN113836291A (en) | 2021-12-24 |
| CN113836291B true CN113836291B (en) | 2023-08-15 |
Family
ID=78967607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111154874.9A Active CN113836291B (en) | 2021-09-29 | 2021-09-29 | Data processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113836291B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104216950A (en) * | 2014-08-18 | 2014-12-17 | 苏州同元软控信息技术有限公司 | Model comparison method based on physical topology |
| CN111105014A (en) * | 2019-11-27 | 2020-05-05 | 联想(北京)有限公司 | Data processing method, equipment and computer readable storage medium |
| CN112580823A (en) * | 2020-12-17 | 2021-03-30 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device, readable storage medium and electronic equipment |
| CN112994940A (en) * | 2019-05-29 | 2021-06-18 | 华为技术有限公司 | Network anomaly detection method and device |
| CN113051479A (en) * | 2021-04-19 | 2021-06-29 | 北京百度网讯科技有限公司 | File processing and recommendation information generation method, device, equipment and storage medium |
| WO2021135588A1 (en) * | 2019-12-31 | 2021-07-08 | 百果园技术(新加坡)有限公司 | Recommendation method, model generation method and apparatus, medium and device |
| CN113190746A (en) * | 2021-04-27 | 2021-07-30 | 北京百度网讯科技有限公司 | Recommendation model evaluation method and device and electronic equipment |
-
2021
- 2021-09-29 CN CN202111154874.9A patent/CN113836291B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104216950A (en) * | 2014-08-18 | 2014-12-17 | 苏州同元软控信息技术有限公司 | Model comparison method based on physical topology |
| CN112994940A (en) * | 2019-05-29 | 2021-06-18 | 华为技术有限公司 | Network anomaly detection method and device |
| CN111105014A (en) * | 2019-11-27 | 2020-05-05 | 联想(北京)有限公司 | Data processing method, equipment and computer readable storage medium |
| WO2021135588A1 (en) * | 2019-12-31 | 2021-07-08 | 百果园技术(新加坡)有限公司 | Recommendation method, model generation method and apparatus, medium and device |
| CN112580823A (en) * | 2020-12-17 | 2021-03-30 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device, readable storage medium and electronic equipment |
| CN113051479A (en) * | 2021-04-19 | 2021-06-29 | 北京百度网讯科技有限公司 | File processing and recommendation information generation method, device, equipment and storage medium |
| CN113190746A (en) * | 2021-04-27 | 2021-07-30 | 北京百度网讯科技有限公司 | Recommendation model evaluation method and device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 郭玉荣 等.基于离线模型参数修正的结构混合试验方法.自然灾害学报.2021,第30卷(第2期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113836291A (en) | 2021-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114445047A (en) | Workflow generation method and device, electronic equipment and storage medium | |
| CN113704058B (en) | Service model monitoring method and device and electronic equipment | |
| CN113821433A (en) | Method, device, equipment, medium and product for testing cloud mobile phone application program | |
| CN117573507A (en) | Test case generation method and device, electronic equipment and storage medium | |
| US10296527B2 (en) | Determining an object referenced within informal online communications | |
| CN115186738B (en) | Model training method, device and storage medium | |
| CN115481594B (en) | Scoreboard implementation method, scoreboard, electronic equipment and storage medium | |
| CN114141236B (en) | Language model updating method and device, electronic equipment and storage medium | |
| CN113836291B (en) | Data processing method, device, equipment and storage medium | |
| CN114116688B (en) | Data processing and quality inspection method and device and readable storage medium | |
| CN116229211A (en) | Sample generation method, model training method, object detection method and device | |
| CN113032251B (en) | Method, device and storage medium for determining service quality of application program | |
| CN113554062A (en) | Training method, device and storage medium of multi-classification model | |
| CN115102850B (en) | Configuration comparison method, device, electronic equipment and storage medium | |
| CN113835893B (en) | Data processing method, device, equipment, storage medium and program product | |
| CN114677564B (en) | Training sample generation method, deep learning model training method and device | |
| CN116991737A (en) | Software testing method, system, electronic equipment and storage medium | |
| CN116225943A (en) | Interactive interface testing method and device, electronic equipment and storage medium | |
| CN115858367A (en) | Test case screening method, device, equipment and medium | |
| CN117472774A (en) | Interface testing method, device, electronic equipment and storage medium | |
| CN117827194A (en) | Method, apparatus, device and storage medium for inspecting elements | |
| CN116701571A (en) | Page display method and device, electronic equipment and storage medium | |
| CN114997329A (en) | Method, apparatus, device, medium and product for generating a model | |
| CN114238149A (en) | Batch testing method of accounting system, electronic device and storage medium | |
| CN114416678A (en) | Resource processing method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |