CN117829886A - Access trend prediction method and device and electronic equipment - Google Patents
Access trend prediction method and device and electronic equipment Download PDFInfo
- Publication number
- CN117829886A CN117829886A CN202311662261.5A CN202311662261A CN117829886A CN 117829886 A CN117829886 A CN 117829886A CN 202311662261 A CN202311662261 A CN 202311662261A CN 117829886 A CN117829886 A CN 117829886A
- Authority
- CN
- China
- Prior art keywords
- data
- prediction result
- prediction
- result
- user data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 85
- 230000000007 visual effect Effects 0.000 claims abstract description 25
- 238000012512 characterization method Methods 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000012800 visualization Methods 0.000 claims description 7
- 238000007499 fusion processing Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 abstract description 5
- 230000007547 defect Effects 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000013461 design Methods 0.000 description 19
- 230000006870 function Effects 0.000 description 12
- 230000008569 process Effects 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 230000003287 optical effect Effects 0.000 description 6
- 238000007621 cluster analysis Methods 0.000 description 5
- 238000003066 decision tree Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000012300 Sequence Analysis Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000001364 causal effect Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an access trend prediction method, an access trend prediction device and electronic equipment, and relates to the technical field of artificial intelligence, wherein the method comprises the following steps: constructing a prediction model based on the collected historical user data; constructing a visual knowledge graph based on the acquired expert knowledge data; inputting target user data into the prediction model, outputting a first prediction result, inputting the target user data into the visual knowledge graph, and outputting a second prediction result; and determining a final predicted result corresponding to the target user data based on the first predicted result and the second predicted result. By means of the method, the user access trend is predicted by combining the prediction model constructed by the historical user data and the visual knowledge graph constructed by the expert knowledge data, user behaviors and requirements can be better understood, limitations and defects of a single method are avoided, and an accurate prediction result is provided.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to a method and an apparatus for predicting an access trend, and an electronic device.
Background
With the continuous development of internet technology, more and more services are executed on line, such as online ticket purchasing service, online registration service, online reading service, etc. Access trend prediction is also important to many industries. Therefore, how to accurately predict the access trend of the user becomes a problem to be solved.
Disclosure of Invention
The application provides a method and a device for predicting access trend and electronic equipment, which can accurately predict the access trend of a user.
In a first aspect, the present application provides a method for predicting an access trend, the method comprising:
constructing a prediction model based on collected historical user data, wherein the user data at least comprises user information data and historical user operation data;
constructing a visual knowledge graph based on the acquired expert knowledge data;
inputting target user data into the prediction model, outputting a first prediction result, inputting the target user data into the visual knowledge graph, and outputting a second prediction result;
and determining a final predicted result corresponding to the target user data based on the first predicted result and the second predicted result.
By means of the method, the user access trend is predicted by combining the prediction model constructed by the historical user data and the visual knowledge graph constructed by the expert knowledge data, user behaviors and requirements can be better understood, limitations and defects of a single method are avoided, and an accurate prediction result is provided.
In one possible design, the constructing a predictive model based on collected historical user data includes:
preprocessing the historical user data according to a preset rule to obtain sample time sequence data;
extracting features of the sample time sequence data to obtain characterization time sequence data;
and constructing the prediction model based on the characterization time sequence data.
By the method, the historical user data is preprocessed, the quality and the accuracy of the sample time sequence data can be ensured, the sample time sequence data is subjected to characteristic engineering, useful information in the sample time sequence data can be extracted, and the construction efficiency of a prediction model is improved.
In one possible design, the constructing the predictive model based on the characterization timing data includes:
constructing a shallow regression network based on the user information data in the characterization time sequence data;
Constructing a deep memory network based on historical user operation data in the characterization time sequence data;
and carrying out fusion processing on the shallow regression network and the deep memory network to obtain the prediction model.
In one possible design, the constructing a visual knowledge-graph based on the acquired expert knowledge data includes:
constructing an ontology layer and an entity relation table based on the expert knowledge data;
fusing the body layer and the entity relation table to obtain a knowledge graph;
and carrying out visualization processing on the knowledge graph based on a graph database to form the visualized knowledge graph.
In one possible design, the determining the final prediction result corresponding to the target user data based on the first prediction result and the second prediction result includes:
when the first predicted result is compared to be consistent with the second predicted result, determining that the first predicted result or the second predicted result is a final predicted result corresponding to the target user data;
and determining the final prediction result based on the historical user data and the expert knowledge data when the first prediction result is inconsistent with the second prediction result.
By means of the method, the first prediction result and the second prediction result are compared, and the final prediction result is determined based on the comparison result, so that the accuracy of the final prediction result can be guaranteed.
In one possible design, the determining the final prediction result based on the historical user data and the expert knowledge data includes:
determining the first prediction result as the final prediction result when the difference value between the data amount of the historical user data and the data amount of the expert knowledge data belongs to a first range;
when the difference value belongs to a second range, fusing the first prediction result and the second prediction result to obtain the final prediction result, wherein the maximum value of the second range is smaller than the minimum value of the first range;
and when the difference value belongs to a third range, determining the second prediction result as the final prediction result, wherein the maximum value of the third range is smaller than the minimum value of the second range.
In a second aspect, the present application provides an access trend prediction apparatus, the apparatus comprising:
the first construction module is used for constructing a prediction model based on collected historical user data, wherein the user data at least comprises user information data and historical user operation data;
The second construction module is used for constructing a visual knowledge graph based on the acquired expert knowledge data;
the prediction module is used for inputting target user data into the prediction model, outputting a first prediction result, inputting the target user data into the visual knowledge graph and outputting a second prediction result;
and the determining module is used for determining a final prediction result corresponding to the target user data based on the first prediction result and the second prediction result.
In one possible design, the first building block is specifically configured to:
preprocessing the historical user data according to a preset rule to obtain sample time sequence data;
extracting features of the sample time sequence data to obtain characterization time sequence data;
and constructing the prediction model based on the characterization time sequence data.
In one possible design, the first building block is specifically configured to:
constructing a shallow regression network based on the user information data in the characterization time sequence data;
constructing a deep memory network based on historical user operation data in the characterization time sequence data;
and carrying out fusion processing on the shallow regression network and the deep memory network to obtain the prediction model.
In one possible design, the second building block is specifically configured to:
constructing an ontology layer and an entity relation table based on the expert knowledge data;
fusing the body layer and the entity relation table to obtain a knowledge graph;
and carrying out visualization processing on the knowledge graph based on a graph database to form the visualized knowledge graph.
In one possible design, the determining module is specifically configured to:
when the first predicted result is compared to be consistent with the second predicted result, determining that the first predicted result or the second predicted result is a final predicted result corresponding to the target user data;
and determining the final prediction result based on the historical user data and the expert knowledge data when the first prediction result is inconsistent with the second prediction result.
In one possible design, the determining module is specifically configured to:
determining the first prediction result as the final prediction result when the difference value between the data amount of the historical user data and the data amount of the expert knowledge data belongs to a first range;
when the difference value belongs to a second range, fusing the first prediction result and the second prediction result to obtain the final prediction result, wherein the maximum value of the second range is smaller than the minimum value of the first range;
And when the difference value belongs to a third range, determining the second prediction result as the final prediction result, wherein the maximum value of the third range is smaller than the minimum value of the second range.
In a third aspect, the present application provides an electronic device, including:
a memory for storing a computer program;
and a processor, configured to implement the steps of the access trend prediction method according to the first aspect when executing the computer program stored in the memory.
In a fourth aspect, the present application provides a computer readable storage medium having stored therein a computer program which when executed by a processor implements the above-described access trend prediction method steps of the first aspect.
Based on the access trend prediction method, the user access trend is predicted by combining the prediction model constructed by the historical user data and the visual knowledge graph constructed by the expert knowledge data, so that the user behavior and the user requirements can be better understood, the limitations and the defects of a single method are avoided, and an accurate prediction result is provided.
The technical effects of each of the second to fourth aspects and the technical effects that may be achieved by each aspect are described above with reference to the first aspect or the technical effects that may be achieved by each possible aspect in the first aspect, and the description is not repeated here.
Drawings
FIG. 1 is a flowchart of an access trend prediction method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an access trend prediction apparatus according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings. The specific method of operation in the method embodiment may also be applied to the device embodiment or the system embodiment. It should be noted that "a plurality of" is understood as "at least two" in the description of the present application. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a alone, a and B alone, and B alone. A is connected with B, and can be represented as follows: both cases of direct connection of A and B and connection of A and B through C. In addition, in the description of the present application, the words "first," "second," and the like are used merely for distinguishing between the descriptions and not be construed as indicating or implying a relative importance or order.
For the convenience of understanding by those skilled in the art, technical terms related to the embodiments of the present application will be explained first.
(1) The time sequence analysis method is to arrange a group of observed values of the same variables such as economic development, purchasing power, sales change and the like in time sequence to form a statistical time sequence, then apply a certain digital method to extend the time sequence outwards, predict the future development change trend of the market and determine the market predicted value.
(2) The cluster analysis algorithm is a statistical analysis method for researching (sample or index) classification problems, and is also an important algorithm for data mining. Cluster analysis consists of several patterns, typically a vector of metrics, or a point in multidimensional space. Cluster analysis is based on similarity, with more similarity between patterns in one cluster than between patterns not in the same cluster.
In order to further explain the technical solutions provided in the embodiments of the present application, the following details are described with reference to the accompanying drawings and the detailed description. Although the embodiments of the present application provide the method operational steps as shown in the following embodiments or figures, more or fewer operational steps may be included in the method, either on a routine or non-inventive basis. In steps where there is logically no necessary causal relationship, the execution order of the steps is not limited to the execution order provided by the embodiments of the present application. The method may be performed sequentially or and in accordance with the method shown in the embodiments or drawings when the actual process or apparatus is performed.
(3) An autoregressive moving average (ARMA) model is a classical time series model that combines an autoregressive model and a moving average model. The ARMA model is modeled based on the autocorrelation and moving average of a time series, and is typically used to predict future time series values and analyze characteristics of the time series.
(4) The decision tree algorithm is a method of approximating discrete function values. The method is a typical classification method, firstly, data is processed, readable rules and decision trees are generated by using a generalization algorithm, and then new data is analyzed by using decisions. Essentially, a decision tree is a process of classifying data by a series of rules.
(5) The graph database is a novel database based on graph theory implementation. The data storage structure and the data query mode are based on graph theory. The basic elements of the graph in the graph theory are nodes and edges, and the nodes and the relations correspond to each other in the graph database. In a graph database, the relationship between data forms a graph structure through nodes and edges, and all the characteristics of the database are realized on the structure.
With the continuous development of internet technology, more and more services are executed on line, such as online ticket purchasing service, online registration service, online reading service, etc. Access trend prediction is also important to many industries. Therefore, how to accurately predict the access trend of the user becomes a problem to be solved.
In order to solve the problems, the access trend prediction method provided by the embodiment of the application predicts the access trend of the user by combining the prediction model constructed by the historical user data and the visual knowledge graph constructed by the expert knowledge data, so that the user behavior and the requirements can be better understood, the limitation and the defect of a single method are avoided, and an accurate prediction result is provided. The method and the device according to the embodiments of the present application are based on the same technical concept, and because the principles of the problems solved by the method and the device are similar, the embodiments of the device and the method can be referred to each other, and the repetition is not repeated.
In order to further explain the technical solutions provided in the embodiments of the present application, the following details are described with reference to the accompanying drawings and the detailed description. Although the embodiments of the present application provide the method operational steps as shown in the following embodiments or figures, more or fewer operational steps may be included in the method, either on a routine or non-inventive basis. In steps where there is logically no necessary causal relationship, the execution order of the steps is not limited to the execution order provided by the embodiments of the present application. The method may be performed sequentially or and in accordance with the method shown in the embodiments or drawings when the actual process or apparatus is performed.
Fig. 1 is a flowchart of an access trend prediction method provided in an embodiment of the present application, where the process may be performed by an access trend prediction device, and the device may be implemented in a software manner, or may be implemented in a hardware manner, or may be implemented in a combination of software and hardware manner, so as to accurately predict an access trend of a user. As shown in fig. 1, the process includes the steps of:
s11, constructing a prediction model based on collected historical user data;
alternatively, the specific construction method of the prediction model may be:
first, historical user data related to user access is collected through channels of an online platform, mobile application, and the like, wherein the historical user data comprises static user information data such as names, sexes, ages, and the like, and dynamic historical user operation data such as browsing records, search histories, social media interactions, and the like.
And then preprocessing the historical user data according to a preset rule to obtain sample time sequence data, and extracting features of the sample time sequence data to obtain characterization time sequence data.
Specifically, data type limitation or conversion is carried out on the data which is recorded in the history user data and is not normalized, so that standard history user data with a unified structure is obtained; filtering and deleting repeated data in the standard historical user data according to the operation sequence number, and filling the missing data in the standard historical user data by a time sequence analysis method to obtain time sequence data; and detecting an outlier in the time sequence data by adopting a cluster analysis algorithm, and deleting data corresponding to the outlier to obtain sample time sequence data. Further, feature extraction (useful information and patterns) is performed on the sample time series data, such as interests and buying habits of the user, and information dispersed in different fields is integrated to obtain characterization time series data.
And finally, constructing a prediction model based on the characterization time sequence data, wherein the prediction model can be constructed based on the characterization time sequence data only, and can also be constructed based on the characterization time sequence data and the acquired expert knowledge data.
In one aspect, constructing the predictive model based on the characterization temporal data includes: on the basis of a general ARMA model, a shallow regression network is constructed based on user information data in the characterization time sequence data, a deep memory network is constructed based on historical user operation data in the characterization time sequence data, and fusion processing is carried out on the shallow regression network and the deep memory network to obtain a data-driven prediction model.
On the other hand, in order to ensure the accuracy of the data-driven prediction model, the obtained expert knowledge data can be combined to construct a data and knowledge dual-driven prediction model, for example, in a data preprocessing link, industry constraint and human domain knowledge and experience can be embedded; in the model structure design link, adjusting the network structure or the topological structure of the model based on domain knowledge; in the feedback mechanism link, a specially designed loss function is constructed. On one hand, the high-dimensional complex mapping relation between variables is described by means of strong fitting capacity of machine learning, and on the other hand, the prediction result can be ensured to accord with the actual situation by combining expert knowledge data, so that a prediction model which is reasonable in reality, accurate in calculation and stable and efficient in operation is constructed. The specific construction method can be as follows:
Acquiring expert knowledge data about access users, such as tax field application systems or electronic commerce field application systems, acquiring professional financial tax field knowledge, and determining the influence of special time such as a period of time, holidays and the like; and acquiring a commodity and service tax classification coding table and the like so as to classify the user group and the application systems of the application fields and screen special situations in different industry fields.
Further, the historical user data is decomposed into a large trend and local disturbance, the large trend reflecting the internal patterns of the predicted area, such as industry structure, population density, etc., determined from the above-described characterization time series data and expert knowledge data. The local disturbance is the change generated by the system under the influence of external driving force such as holidays, major events and the like, and is predicted by a data-driven prediction model. And then, after the large trend and the small disturbance are combined, a data and knowledge dual-drive prediction model can be obtained.
In some possible designs, the interpretation and confidence of the data-driven predictive model may also be enhanced by optimizing the model by a strongly interpretable algorithm, such as a decision tree algorithm. In short, the collected historical user data is cleaned to remove invalid data, ensure data quality and accuracy, and the cleaned historical user data is subjected to data analysis and pattern extraction, for example, a cluster analysis algorithm, association rule mining and a time sequence analysis method are utilized to carry out deep analysis on the cleaned historical user data, and useful information and patterns of the cleaned historical user data are extracted to obtain sample data. Finally, a predictive model is built based on the sample data and the decision tree algorithm, and a visualization tool is used to expose the decision process and results. In addition, the confidence of the predicted result by the user is enhanced by providing the confidence and the confidence interval of the predicted result.
S12, constructing a visual knowledge graph based on the acquired expert knowledge data;
optionally, expert knowledge data includes industry trends, market dynamics, competitive situations, and the like. The specific construction method of the visual knowledge graph can be as follows:
and constructing an ontology layer and an entity relation table based on expert knowledge data.
Specifically, the scope of the ontology includes two aspects of application system functions and access user groups, and names, sexes, regions, industries, access frequencies, access time intervals, user relationships, application system function names, applicable industries and the like of access users are sorted out according to the two aspects. And after determining the scope of the ontology, carrying out domain knowledge analysis by combining expert knowledge data to determine the ontology, thereby completing the ontology layer construction.
Further, based on the structure of the ontology layer, extracting each entity from expert knowledge data, and forming triples between the entities, and constructing an entity relationship table, wherein each triplet is composed of < entity-relationship-entity >, such as < Zhang San-belongs to-restaurant service industry >.
After the ontology layer and the entity relation table are constructed by the method, the ontology layer and the entity relation table are fused to obtain the knowledge graph. Specifically, the obtained triples are aligned according to the rule with the same semantic meaning, so that the entities with the same semantic meaning are combined into one entity, each entity corresponds to a unique identification number, and all the aligned triples are integrated, so that the unique identification number corresponding to the final entity corresponds to a plurality of triples, and a knowledge graph is formed.
And finally, carrying out visualization processing on the knowledge graph based on a graph database to form a visualized knowledge graph.
S13, inputting target user data into the prediction model, outputting a first prediction result, inputting the target user data into the visual knowledge graph, and outputting a second prediction result;
optionally, the method for predicting the target user data based on the visual knowledge graph may be: and (3) reasoning the target user data in the visual map based on a path reasoning mode to obtain a second prediction result. For example, the target user data is: and the operation data A of the target user is deduced from the visual map, wherein the operation data A relates to a plurality of application system functional entities, and the next time period possibly relates to a plurality of application system functional entities and the respective corresponding conditional probabilities. The respective use probabilities of the plurality of application system functional entities possibly related to the next time period can be further inferred based on the plurality of application system functional entities possibly related to the next time period, the respective conditional probabilities and the triples corresponding to the plurality of target users, and the access trend of the plurality of application system functional entities possibly related to the next time period can be further inferred.
S14, determining a final prediction result corresponding to the target user data based on the first prediction result and the second prediction result.
Optionally, the specific method for determining the final prediction result may be:
and comparing the first predicted result with the second predicted result, and determining the first predicted result or the second predicted result as a final predicted result corresponding to the target user data when the first predicted result is identical to the second predicted result.
And determining the final prediction result based on the historical user data and expert knowledge data when the first prediction result is inconsistent with the second prediction result. Specifically, when the difference between the data amount of the historical user data and the data amount of the expert knowledge data belongs to a first range, determining the first prediction result as the final prediction result; when the difference value between the data amount of the historical user data and the data amount of the expert knowledge data belongs to a second range, fusing the first prediction result and the second prediction result to obtain the final prediction result (for example, taking the average value between the first prediction result and the second prediction result as the final prediction result), wherein the maximum value of the second range is smaller than the minimum value of the first range; and determining the second prediction result as the final prediction result when the difference value between the data amount of the historical user data and the data amount of the expert knowledge data belongs to a third range, wherein the maximum value of the third range is smaller than the minimum value of the second range.
By means of the access trend prediction method, the user access trend is predicted by combining the prediction model constructed by the historical user data and the visual knowledge graph constructed by the expert knowledge data, user behaviors and requirements can be better understood, limitations and defects of a single method are avoided, and an accurate prediction result is provided.
Based on the same inventive concept, an access trend prediction apparatus is further provided in the embodiments of the present application, as shown in fig. 2, which is a schematic structural diagram of the access trend prediction apparatus provided in the embodiments of the present application, where the apparatus includes:
a first construction module 21 for constructing a prediction model based on collected historical user data, wherein the user data at least comprises user information data and historical user operation data;
a second construction module 22, configured to construct a visual knowledge graph based on the acquired expert knowledge data;
a prediction module 23, configured to input target user data into the prediction model, output a first prediction result, input the target user data into the visual knowledge graph, and output a second prediction result;
a determining module 24, configured to determine a final prediction result corresponding to the target user data based on the first prediction result and the second prediction result.
In one possible design, the first building block 21 is specifically configured to:
preprocessing the historical user data according to a preset rule to obtain sample time sequence data;
extracting features of the sample time sequence data to obtain characterization time sequence data;
and constructing the prediction model based on the characterization time sequence data.
In one possible design, the first building block 21 is specifically configured to:
constructing a shallow regression network based on the user information data in the characterization time sequence data;
constructing a deep memory network based on historical user operation data in the characterization time sequence data;
and carrying out fusion processing on the shallow regression network and the deep memory network to obtain the prediction model.
In one possible design, the second building block 22 is specifically configured to:
constructing an ontology layer and an entity relation table based on the expert knowledge data;
fusing the body layer and the entity relation table to obtain a knowledge graph;
and carrying out visualization processing on the knowledge graph based on a graph database to form the visualized knowledge graph.
In one possible design, the determination module 24 is specifically configured to:
When the first predicted result is compared to be consistent with the second predicted result, determining that the first predicted result or the second predicted result is a final predicted result corresponding to the target user data;
and determining the final prediction result based on the historical user data and the expert knowledge data when the first prediction result is inconsistent with the second prediction result.
In one possible design, the determination module 24 is specifically configured to:
determining the first prediction result as the final prediction result when the difference value between the data amount of the historical user data and the data amount of the expert knowledge data belongs to a first range;
when the difference value belongs to a second range, fusing the first prediction result and the second prediction result to obtain the final prediction result, wherein the maximum value of the second range is smaller than the minimum value of the first range;
and when the difference value belongs to a third range, determining the second prediction result as the final prediction result, wherein the maximum value of the third range is smaller than the minimum value of the second range.
It should be noted that, the above device provided in the embodiment of the present application can implement all the method steps in the embodiment of the method and achieve the same technical effects, and the details of the same parts and the advantages as those of the embodiment of the method in the embodiment are not described here.
Based on the same inventive concept, the embodiment of the present application further provides an electronic device, where the electronic device may implement the function of the foregoing access trend prediction apparatus, and referring to fig. 3, the electronic device includes:
the embodiment of the present application does not limit the specific connection medium between the processor 31 and the memory 32, but the connection between the processor 31 and the memory 32 through the bus 30 is exemplified in fig. 3. The connection of the bus 30 to other components is shown in bold lines in fig. 3, and is merely illustrative and not limiting. The bus 30 may be divided into an address bus, a data bus, a control bus, etc., and is represented by only one thick line in fig. 3 for convenience of representation, but does not represent only one bus or one type of bus. Alternatively, the processor 31 may be referred to as a controller, and the names are not limited.
In the embodiment of the present application, the memory 32 stores instructions executable by the at least one processor 31, and the at least one processor 31 may execute the above-described access trend prediction method by executing the instructions stored in the memory 32. The processor 31 may implement the functions of the respective modules in the apparatus shown in fig. 2.
The processor 31 is a control center of the apparatus, and may connect various parts of the entire control device using various interfaces and lines, and by executing or executing instructions stored in the memory 32 and invoking data stored in the memory 32, various functions of the apparatus and processing data, thereby performing overall monitoring of the apparatus.
In one possible design, processor 31 may include one or more processing units, and processor 31 may integrate an application processor that primarily processes operating systems, user interfaces, application programs, and the like, with a modem processor that primarily processes wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 31. In some embodiments, processor 31 and memory 32 may be implemented on the same chip, and in some embodiments they may be implemented separately on separate chips.
The processor 31 may be a general purpose processor such as a Central Processing Unit (CPU), digital signal processor, application specific integrated circuit, field programmable gate array or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, and may implement or perform the methods, steps and logic blocks disclosed in embodiments of the present application. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the access trend prediction method disclosed in connection with the embodiments of the present application may be directly embodied in a hardware processor for execution, or may be executed by a combination of hardware and software modules in the processor.
The memory 32 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The Memory 32 may include at least one type of storage medium, and may include, for example, flash Memory, hard disk, multimedia card, card Memory, random access Memory (Random Access Memory, RAM), static random access Memory (Static Random Access Memory, SRAM), programmable Read-Only Memory (Programmable Read Only Memory, PROM), read-Only Memory (ROM), charged erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory), magnetic Memory, magnetic disk, optical disk, and the like. Memory 32 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 32 in the present embodiment may also be circuitry or any other device capable of implementing a memory function for storing program instructions and/or data.
By programming the processor 31, the code corresponding to the access trend prediction method described in the foregoing embodiment may be cured into the chip, so that the chip can execute the steps of the access trend prediction method of the embodiment shown in fig. 1 at runtime. How to design and program the processor 31 is a technique well known to those skilled in the art, and will not be described in detail herein.
Based on the same inventive concept, embodiments of the present disclosure provide a computer storage medium, the computer storage medium including: computer program code which, when run on a computer, causes the computer to perform a method of access trend prediction as any one of the preceding discussions. Since the principle of solving the problem by the computer storage medium is similar to that of an access trend prediction method, the implementation of the computer storage medium can refer to the implementation of the method, and the repetition is omitted.
In a specific implementation, the computer storage medium may include: a universal serial bus flash disk (USB, universal Serial Bus Flash Drive), a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Based on the same inventive concept, the disclosed embodiments also provide a computer program product comprising: computer program code which, when run on a computer, causes the computer to perform a method of access trend prediction as previously discussed. Since the principle of solving the problem by the computer program product is similar to that of an access trend prediction method, the implementation of the computer program product can refer to the implementation of the method, and the repetition is omitted.
The computer program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The methods in this application may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described herein are performed in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, a network device, a user device, a core network device, an OAM, or other programmable apparatus.
The computer program or instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer program or instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The usable medium may be a magnetic medium, e.g., floppy disk, hard disk, tape; but also optical media such as digital video discs; but also semiconductor media such as solid state disks. The computer readable storage medium may be volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage medium.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (14)
1. A method of access trend prediction, the method comprising:
constructing a prediction model based on collected historical user data, wherein the user data at least comprises user information data and historical user operation data;
constructing a visual knowledge graph based on the acquired expert knowledge data;
inputting target user data into the prediction model, outputting a first prediction result, inputting the target user data into the visual knowledge graph, and outputting a second prediction result;
And determining a final predicted result corresponding to the target user data based on the first predicted result and the second predicted result.
2. The method of claim 1, wherein constructing a predictive model based on the collected historical user data comprises:
preprocessing the historical user data according to a preset rule to obtain sample time sequence data;
extracting features of the sample time sequence data to obtain characterization time sequence data;
and constructing the prediction model based on the characterization time sequence data.
3. The method of claim 2, wherein the constructing the predictive model based on the characterization timing data comprises:
constructing a shallow regression network based on the user information data in the characterization time sequence data;
constructing a deep memory network based on historical user operation data in the characterization time sequence data;
and carrying out fusion processing on the shallow regression network and the deep memory network to obtain the prediction model.
4. The method of claim 1, wherein constructing a visual knowledge-graph based on the acquired expert knowledge data comprises:
constructing an ontology layer and an entity relation table based on the expert knowledge data;
Fusing the body layer and the entity relation table to obtain a knowledge graph;
and carrying out visualization processing on the knowledge graph based on a graph database to form the visualized knowledge graph.
5. The method of claim 1, wherein the determining a final prediction result corresponding to the target user data based on the first prediction result and the second prediction result comprises:
when the first predicted result is compared to be consistent with the second predicted result, determining that the first predicted result or the second predicted result is a final predicted result corresponding to the target user data;
and determining the final prediction result based on the historical user data and the expert knowledge data when the first prediction result is inconsistent with the second prediction result.
6. The method of claim 5, wherein the determining the final prediction result based on the historical user data and the expert knowledge data comprises:
determining the first prediction result as the final prediction result when the difference value between the data amount of the historical user data and the data amount of the expert knowledge data belongs to a first range;
When the difference value belongs to a second range, fusing the first prediction result and the second prediction result to obtain the final prediction result, wherein the maximum value of the second range is smaller than the minimum value of the first range;
and when the difference value belongs to a third range, determining the second prediction result as the final prediction result, wherein the maximum value of the third range is smaller than the minimum value of the second range.
7. An access trend prediction apparatus, the apparatus comprising:
the first construction module is used for constructing a prediction model based on collected historical user data, wherein the user data at least comprises user information data and historical user operation data;
the second construction module is used for constructing a visual knowledge graph based on the acquired expert knowledge data;
the prediction module is used for inputting target user data into the prediction model, outputting a first prediction result, inputting the target user data into the visual knowledge graph and outputting a second prediction result;
and the determining module is used for determining a final prediction result corresponding to the target user data based on the first prediction result and the second prediction result.
8. The apparatus of claim 7, wherein the first building block is specifically configured to:
preprocessing the historical user data according to a preset rule to obtain sample time sequence data;
extracting features of the sample time sequence data to obtain characterization time sequence data;
and constructing the prediction model based on the characterization time sequence data.
9. The apparatus of claim 8, wherein the first building block is specifically configured to:
constructing a shallow regression network based on the user information data in the characterization time sequence data;
constructing a deep memory network based on historical user operation data in the characterization time sequence data;
and carrying out fusion processing on the shallow regression network and the deep memory network to obtain the prediction model.
10. The apparatus of claim 7, wherein the second building block is specifically configured to:
constructing an ontology layer and an entity relation table based on the expert knowledge data;
fusing the body layer and the entity relation table to obtain a knowledge graph;
and carrying out visualization processing on the knowledge graph based on a graph database to form the visualized knowledge graph.
11. The apparatus of claim 7, wherein the determining module is specifically configured to:
when the first predicted result is compared to be consistent with the second predicted result, determining that the first predicted result or the second predicted result is a final predicted result corresponding to the target user data;
and determining the final prediction result based on the historical user data and the expert knowledge data when the first prediction result is inconsistent with the second prediction result.
12. The apparatus of claim 11, wherein the determining module is specifically configured to:
determining the first prediction result as the final prediction result when the difference value between the data amount of the historical user data and the data amount of the expert knowledge data belongs to a first range;
when the difference value belongs to a second range, fusing the first prediction result and the second prediction result to obtain the final prediction result, wherein the maximum value of the second range is smaller than the minimum value of the first range;
and when the difference value belongs to a third range, determining the second prediction result as the final prediction result, wherein the maximum value of the third range is smaller than the minimum value of the second range.
13. An electronic device, comprising:
a memory for storing a computer program;
a processor for carrying out the method steps of any one of claims 1-6 when executing a computer program stored on said memory.
14. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311662261.5A CN117829886A (en) | 2023-12-06 | 2023-12-06 | Access trend prediction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311662261.5A CN117829886A (en) | 2023-12-06 | 2023-12-06 | Access trend prediction method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117829886A true CN117829886A (en) | 2024-04-05 |
Family
ID=90512616
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311662261.5A Pending CN117829886A (en) | 2023-12-06 | 2023-12-06 | Access trend prediction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117829886A (en) |
-
2023
- 2023-12-06 CN CN202311662261.5A patent/CN117829886A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Verenich et al. | Survey and cross-benchmark comparison of remaining time prediction methods in business process monitoring | |
| CN107040397B (en) | Service parameter acquisition method and device | |
| US20190272553A1 (en) | Predictive Modeling with Entity Representations Computed from Neural Network Models Simultaneously Trained on Multiple Tasks | |
| CN112232833A (en) | Lost member customer group data prediction method, model training method and model training device | |
| WO2015103046A1 (en) | A multidimensional recursive learning process and system used to discover complex dyadic or multiple counterparty relationships | |
| CN111681049A (en) | User behavior processing method, storage medium and related equipment | |
| Yun et al. | Predictive Analytics: A Survey, Trends, Applications, Opportunities’ and Challenges for Smart City Planning | |
| Bhardwaj et al. | Health insurance amount prediction | |
| Carlsson et al. | Fuzzy entropy used for predictive analytics | |
| Mendia et al. | A novel approach for the detection of anomalous energy consumption patterns in industrial cyber‐physical systems | |
| Liu et al. | Residual useful life prognosis of equipment based on modified hidden semi-Markov model with a co-evolutional optimization method | |
| Prasidis et al. | Handling uncertainty in predictive business process monitoring with Bayesian networks | |
| Ziegenbein et al. | Machine learning algorithms in machining: A guideline for efficient algorithm selection | |
| CN116501979A (en) | Information recommendation method, information recommendation device, computer equipment and computer readable storage medium | |
| KR20210042709A (en) | Method and server for stock movement prediction using corporate relation data | |
| CN117829886A (en) | Access trend prediction method and device and electronic equipment | |
| Khoshgoftaar et al. | Predicting fault-prone modules in embedded systems using analogy-based classification models | |
| CN114610590A (en) | Method, device and equipment for determining operation time length and storage medium | |
| Shah et al. | Predictive Analytic Modeling: A Walkthrough | |
| Gyamerah et al. | Trend forecasting in financial time series with indicator system | |
| CN112328899A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
| AU2020201689A1 (en) | Cognitive forecasting | |
| CN111737319A (en) | User cluster prediction method and device, computer equipment and storage medium | |
| Schörgenhumer et al. | A Framework for Preprocessing Multivariate, Topology-Aware Time Series and Event Data in a Multi-System Environment | |
| Yedida et al. | Old but Gold: Reconsidering the value of feedforward learners for software analytics |
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 |