CN117217710A - Intelligent management method and system for virtual commodity and shortcut service - Google Patents
Intelligent management method and system for virtual commodity and shortcut service Download PDFInfo
- Publication number
- CN117217710A CN117217710A CN202311351869.6A CN202311351869A CN117217710A CN 117217710 A CN117217710 A CN 117217710A CN 202311351869 A CN202311351869 A CN 202311351869A CN 117217710 A CN117217710 A CN 117217710A
- Authority
- CN
- China
- Prior art keywords
- information
- shortcut
- user
- virtual
- shortcut service
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 34
- 238000012795 verification Methods 0.000 claims abstract description 18
- 239000013598 vector Substances 0.000 claims description 29
- 238000013528 artificial neural network Methods 0.000 claims description 21
- 238000007781 pre-processing Methods 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 14
- 238000004140 cleaning Methods 0.000 claims description 8
- 230000006399 behavior Effects 0.000 claims description 6
- 238000012352 Spearman correlation analysis Methods 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Abstract
The application discloses an intelligent management method and system for virtual goods and shortcut services, comprising the steps of obtaining demand information of a user, judging demand instructions to inquire corresponding virtual goods information and shortcut service information, and reading corresponding target programs and demand instructions to match to generate request information; carrying out shipping pretreatment according to the request information, and writing a shipping command into a message queue and returning to a shipping interface when the shipping command meets a preset standard; and verifying the execution condition of the shipping command, acquiring feedback information according to the verification information in combination with the virtual commodity information and the shortcut service information, importing the feedback information into a recommendation model, and generating and pushing the virtual commodity or the shortcut service with high correlation with the demand information. The application effectively avoids the problem of confusion of matching and calling of the request and the issuing interface in the virtual commodity and shortcut service transaction, improves the management efficiency, and simultaneously analyzes the data of the user demands on the premise of ensuring the privacy of the user, and discovers the user demand preference to realize accurate marketing.
Description
Technical Field
The application relates to the technical field of virtual commodity management, in particular to an intelligent management method and system for virtual commodity and shortcut service.
Background
With the continuous improvement of the production technology level and the continuous increase of the user demands, the living habit and the consumption behavior of people are changed over the sky, and especially the virtual commodity consumption industry is unprecedented. With the rapid development of internet economy and the current world situation and trend, virtual commodity consumption is a subject which cannot be ignored. The meta universe at the present stage determines the position of the virtual commodity consumption industry in the information age. The development opportunity of the virtual commodity transaction is grasped, the core competitiveness of related enterprises is continuously enhanced, and the virtual commodity transaction method is an important foundation for whether the virtual commodity consumption industry can pull economic growth.
Many virtual commodities appear in the interaction process of users and networks, because interfaces between different platforms are different, if the platforms cannot synchronize information of the virtual commodities timely, purchasing experience of the users can be affected, in a scene of a large amount of transaction data, virtual products are diversified, manual management efficiency is low, timeliness is poor, errors are easy to occur, and faults of the virtual commodity transaction process are caused. For the virtual commodity consumption industry, the requirements of virtual commodity consumers can be grasped to effectively ensure the effective innovation of enterprise products, so that the problem that how to avoid interface calling confusion, improve the stability of the virtual commodity process, acquire and divide the requirements of users, analyze data according to the requirements of the users and improve the use experience of the users is needed to be solved.
Disclosure of Invention
In order to solve the technical problems, the application provides an intelligent management method and system for virtual goods and shortcut services.
The first aspect of the present application provides an intelligent management method for virtual goods and shortcut services, comprising:
acquiring demand information of a user, judging a demand instruction based on the demand information, inquiring corresponding virtual commodity information and shortcut service information through the demand instruction, reading target programs of the virtual commodity and the shortcut service, and matching the target degree with the demand instruction to generate request information;
carrying out shipping preprocessing according to the request information, judging whether the request information accords with a preset standard, writing a shipping command into a message queue and returning to a shipping interface when the request information accords with the preset standard, and executing the shipping command;
acquiring historical transaction information of virtual goods and shortcut services of a user, utilizing a graph convolution neural network to mine high-dimensional characteristics according to the historical transaction information, introducing a federal learning algorithm to train the graph convolution neural network under the condition of ensuring the privacy of the user, and constructing a recommendation model;
and verifying the execution condition of the delivery command, acquiring feedback information according to the verification information in combination with the virtual commodity information and the shortcut service information, importing the feedback information into the recommendation model, and generating and pushing the virtual commodity or the shortcut service with high relation with the demand information.
In this scheme, obtain user's demand information, judge the demand instruction based on demand information, inquire corresponding virtual commodity information and swift service information through the demand instruction, read virtual commodity and swift service's target program specifically does:
acquiring inquiry information of a user, performing single-heat encoding on the inquiry information to acquire feature vectors corresponding to the inquiry information, generating requirement information of the user, and judging category information of virtual goods and shortcut services inquired by the user through the requirement information;
generating a demand instruction according to the category information, extracting the identity and the authority of a user, matching the demand instruction with the identity and the authority, and searching virtual commodity information and shortcut service information corresponding to the user identity and the authority by using the matched demand instruction in a distributed search manner;
and acquiring a corresponding target program from a distributed database through the virtual commodity information and the shortcut service information, setting a source identifier according to the source of the target program, and generating request information based on the user identity and the authority by combining the target program marked with the source identifier with user demand instruction matching.
In this scheme, carry out shipment preprocessing according to request information, judge whether request information accords with the standard of predetermineeing, when accords with the standard of predetermineeing, write into message queue and return the shipment interface with the command of shipping, specifically:
acquiring request information to perform shipping preprocessing, wherein the shipping preprocessing comprises judging the legality of the request information, judging whether the residual quantity of the virtual goods meets the required quantity according to the virtual goods information, and judging whether the identity and authority of a user meet the single-user limit of the virtual goods and the shortcut service;
generating a judgment matrix according to the judgment condition of the shipping pretreatment as a row vector, generating a standard matrix according to the preset standard of the judgment condition, and comparing the judgment matrix with the standard matrix to judge whether the request information accords with the preset standard;
when the preset standard is met, writing the delivery command into a message queue and returning to a delivery interface, inquiring ID information of the virtual commodity and the shortcut service corresponding to the basic resource through the message content of the message queue, constructing RPC call based on RDMA, and executing the delivery command.
In the scheme, the historical transaction information of the virtual commodity and the shortcut service of the user is obtained, and the high-dimensional characteristics are mined by utilizing a graph convolutional neural network according to the historical transaction information, specifically comprising the following steps:
searching a release information table corresponding to the virtual commodity and the shortcut service based on the identity and the authority of the user by utilizing data searching, screening historical transaction information of the user from the release information table, extracting multi-mode data in the historical transaction information, and carrying out data cleaning on the multi-mode data;
carrying out feature construction on the multi-mode data subjected to data cleaning by utilizing feature codes to generate feature matrixes, acquiring the feature matrixes corresponding to users and the feature matrixes corresponding to virtual goods and shortcut services, and acquiring the correlation of the feature matrixes through spearman correlation analysis;
converting the feature matrix set in a preset time step into bidirectional propagation graph structure information by utilizing a graph convolution neural network according to the correlation and time sequence correlation;
and obtaining node characteristics in the graph structure information, marking the corresponding graph structure information and the node characteristics by using different platform information, and obtaining high-dimensional characteristics corresponding to historical transaction behaviors of virtual goods and shortcut services of users in different platforms.
In the scheme, a federal learning algorithm is introduced to train a graph convolution neural network under the condition of ensuring the privacy of a user, and a recommendation model is constructed, specifically:
constructing a recommendation model by using a graph convolution neural network, extracting graph structure information and corresponding high-dimensional characteristics corresponding to different platforms by a user, training by using a federal learning algorithm, judging computing power and network environment of the different platforms, and judging whether the data training synchronization time meets a preset period according to the computing power and the network environment;
judging the rounds of participation in training according to different platforms meeting a preset period, acquiring the attention weights of the different platforms by using a multi-head attention mechanism when the training rounds of the different platforms deviate from the preset rounds, setting two layers of attention structures, and carrying out series connection and average operation on the high-dimensional characteristics by using the attention weights;
acquiring characteristic output of an attention layer in a current preset period for nonlinear activation, respectively sending homomorphic encrypted parameters required by calculating gradients to the opposite side according to high-dimensional characteristics of different platforms after nonlinear operation, calculating encryption gradients of different platforms, and protecting privacy information of a user through the encryption gradients;
the encrypted high-dimensional features are aggregated by using corresponding graph structure information, the graph structure information is updated, the updated graph structure is used for continuing to aggregate, the aggregated high-dimensional features are uploaded to a preset global platform, and the encrypted parameters and the encryption gradient are used for decoding and are returned to different platforms;
and outputting a prediction result in different platforms by using the updated user vector, the updated virtual commodity vector and the updated shortcut service vector to recommend the user vector, the virtual commodity vector and the updated shortcut service vector.
In this scheme, according to the check information and combining virtual commodity information and shortcut service information, feedback information is obtained, the feedback information is imported into the recommendation model, and virtual commodity or shortcut service with high relevance to the demand information is generated for pushing, specifically:
acquiring the position of a resource party according to the inquired ID information of the virtual commodity and the shortcut service corresponding to the basic resource, acquiring receipt information of the resource party after the delivery command is executed based on the position of the resource party, judging whether the execution is successful according to the receipt information, and generating check information based on a judgment result;
carrying out delivery again by using the verification information, sending early warning information when the failure times reach a preset threshold value, and obtaining feedback information by using the verification information and virtual commodity information or shortcut service information corresponding to delivery when the failure times are successful;
the feedback information is used as input of a recommendation model, and other virtual goods and shortcut services with high association degree with the current virtual goods or shortcut services are obtained through the recommendation model to be marked and suspended;
extracting long-short-period interest features of a user, extracting suspended virtual commodity information or shortcut service information, calculating the similarity between the virtual commodity information or shortcut service information and the long-short-period interest features, and generating recommendation weights according to the similarity;
and sequencing the suspended virtual goods or shortcut services by using the recommendation weight, and selecting the virtual goods or shortcut services with the highest weight to push to the client of the user.
The second aspect of the present application also provides an intelligent management system for virtual goods and shortcut services, the system comprising: the intelligent management method comprises a memory and a processor, wherein the memory comprises an intelligent management method program of virtual goods and shortcut services, and the intelligent management method program of the virtual goods and the shortcut services realizes the following steps when being executed by the processor:
acquiring demand information of a user, judging a demand instruction based on the demand information, inquiring corresponding virtual commodity information and shortcut service information through the demand instruction, reading target programs of the virtual commodity and the shortcut service, and matching the target degree with the demand instruction to generate request information;
carrying out shipping preprocessing according to the request information, judging whether the request information accords with a preset standard, writing a shipping command into a message queue and returning to a shipping interface when the request information accords with the preset standard, and executing the shipping command;
acquiring historical transaction information of virtual goods and shortcut services of a user, utilizing a graph convolution neural network to mine high-dimensional characteristics according to the historical transaction information, introducing a federal learning algorithm to train the graph convolution neural network under the condition of ensuring the privacy of the user, and constructing a recommendation model;
and verifying the execution condition of the delivery command, acquiring feedback information according to the verification information in combination with the virtual commodity information and the shortcut service information, importing the feedback information into the recommendation model, and generating and pushing the virtual commodity or the shortcut service with high relation with the demand information.
The application discloses an intelligent management method and system for virtual goods and shortcut services, comprising the steps of obtaining demand information of a user, judging demand instructions to inquire corresponding virtual goods information and shortcut service information, and reading corresponding target programs and demand instructions to match to generate request information; carrying out shipping preprocessing according to the request information, judging whether the request information accords with a preset standard, and writing a shipping command into a message queue and returning to a shipping interface when the request information accords with the preset standard; and verifying the execution condition of the shipping command, acquiring feedback information according to the verification information in combination with the virtual commodity information and the shortcut service information, importing the feedback information into a recommendation model, and generating and pushing the virtual commodity or the shortcut service with high correlation with the demand information. The application effectively avoids the problem of confusion of matching and calling of the request and the issuing interface in the virtual commodity and shortcut service transaction, improves the management efficiency, and simultaneously analyzes the data of the user demands on the premise of ensuring the privacy of the user, and discovers the user demand preference to realize accurate marketing.
Drawings
FIG. 1 is a flow chart of an intelligent management method for virtual goods and shortcut service according to the present application;
FIG. 2 illustrates a flow chart of the present application for shipping pre-processing based on request information;
FIG. 3 shows a flowchart for pushing virtual goods or shortcut services with high relevance obtained by using a recommendation model;
fig. 4 shows a block diagram of an intelligent management system for virtual goods and shortcut services according to the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flowchart of an intelligent management method for virtual goods and shortcut service according to the present application.
As shown in fig. 1, a first aspect of the present application provides an intelligent management method for virtual goods and shortcut services, including:
s102, acquiring demand information of a user, judging a demand instruction based on the demand information, inquiring corresponding virtual commodity information and shortcut service information through the demand instruction, reading target programs of the virtual commodity and the shortcut service, and matching the target degree with the demand instruction to generate request information;
s104, carrying out shipping preprocessing according to the request information, judging whether the request information accords with a preset standard, writing a shipping command into a message queue and returning to a shipping interface when the request information accords with the preset standard, and executing the shipping command;
s106, acquiring historical transaction information of the virtual commodity and the shortcut service of the user, utilizing a graph convolution neural network to mine high-dimensional characteristics according to the historical transaction information, introducing a federal learning algorithm to train the graph convolution neural network under the condition of ensuring the privacy of the user, and constructing a recommendation model;
s108, checking the execution condition of the delivery command, acquiring feedback information according to the check information in combination with the virtual commodity information and the shortcut service information, importing the feedback information into the recommendation model, and generating a virtual commodity or shortcut service with high relevance to the demand information for pushing.
In the single-hot coding, if a data point belongs to an ith category, components of the data point corresponding vector are assigned to 0, other components are assigned to 1, demand information after quantitative classification of the user is generated, and category information of virtual goods and shortcut services inquired by the user is judged through the demand information; generating a demand instruction according to the category information, extracting the identity and the authority of a user, displaying the matched virtual commodity and shortcut service for the user according to the identity and the authority, matching the demand instruction with the identity and the authority, and searching the virtual commodity information and the shortcut service information corresponding to the user identity and the authority by using the matched demand instruction in a distributed search mode; the virtual commodity information and the shortcut service information comprise virtual commodity IDs and shortcut service IDs, keys for virtual commodity delivery, creation information of the virtual commodity and the shortcut service, basic resource lists contained in the virtual commodity and the shortcut service, limited quantity, valid period and the like; and acquiring a corresponding target program from a distributed database through the virtual commodity information and the shortcut service information, setting a source identifier according to the source of the target program, and generating request information based on the user identity and the authority by combining the target program marked with the source identifier with user demand instruction matching.
FIG. 2 illustrates a flow chart of the present application for shipping pre-processing based on request information.
According to the embodiment of the application, the shipping preprocessing is carried out according to the request information, whether the request information accords with the preset standard is judged, and when the request information accords with the preset standard, the shipping command is written into the message queue and returned to the shipping interface, specifically:
s202, acquiring request information to perform shipping preprocessing, wherein the shipping preprocessing comprises judging the legality of the request information, judging whether the residual quantity of the virtual goods meets the required quantity according to the virtual goods information, and judging whether the identity and the authority of a user meet the single-user limit of the virtual goods and the shortcut service;
s204, generating a judgment matrix according to the judgment condition of the shipping pretreatment as a row vector, generating a standard matrix according to the preset standard of the judgment condition, and comparing the judgment matrix with the standard matrix to judge whether the request information accords with the preset standard;
s206, when the preset standard is met, writing the delivery command into a message queue and returning to a delivery interface, inquiring ID information of the virtual commodity and the shortcut service corresponding to the basic resource through the message content of the message queue, constructing RPC call based on RDMA, and executing the delivery command.
It should be noted that, a management interface is set for the user, the identity and authority of the user are accessed in the management interface, the user creates a new virtual commodity through the management interface, modifies the virtual commodity information, queries the virtual commodity with the viewing authority, deletes the virtual commodity and shortcut service which are expired or not needed, etc. The ID information of the virtual commodity and the shortcut service is generated by using a Snowflag algorithm to generate globally unique ID information, the ID information is queried, and an RPC request is initiated, so that the purpose of issuing the virtual commodity or the shortcut service to a user is achieved.
FIG. 3 shows a flow chart of the application for pushing by using a recommendation model to obtain highly relevant virtual goods or shortcut services.
According to the embodiment of the application, feedback information is acquired according to the verification information in combination with the virtual commodity information and the shortcut service information, the feedback information is imported into the recommendation model, and the virtual commodity or the shortcut service with high relevance to the demand information is generated for pushing, specifically:
s302, acquiring the position of a resource party according to the queried ID information of the virtual commodity and the shortcut service corresponding to the basic resource, acquiring receipt information of the resource party after the delivery command is executed based on the position of the resource party, judging whether the execution is successful according to the receipt information, and generating check information based on a judgment result;
s304, carrying out delivery again by using the verification information, sending early warning information when the failure times reach a preset threshold value, and acquiring feedback information by using the verification information and virtual commodity information or shortcut service information corresponding to delivery when the failure times are successful;
s306, taking the feedback information as input of a recommendation model, and obtaining other virtual goods and shortcut services with high association degree with the current virtual goods or shortcut services through the recommendation model to carry out marking and suspending;
s308, extracting long-short-period interest features of a user, extracting suspended virtual commodity information or shortcut service information, calculating the similarity between the virtual commodity information or shortcut service information and the long-short-period interest features, and generating recommendation weights according to the similarity;
s310, sorting the suspended virtual goods or shortcut services by using the recommendation weight, and selecting the virtual goods or shortcut services with the highest weight to push to the client of the user.
The method comprises the steps of searching a release information table corresponding to virtual goods and shortcut services based on the identity and authority of a user by utilizing data searching, screening historical transaction information of the user from the release information table, extracting multi-mode data in the historical transaction information, and carrying out data cleaning such as outlier identification filling and missing value processing on the multi-mode data; carrying out feature construction on the multi-mode data subjected to data cleaning by utilizing feature codes to generate feature matrixes, acquiring the feature matrixes corresponding to users and the feature matrixes corresponding to virtual goods and shortcut services, and acquiring the correlation of the feature matrixes through spearman correlation analysis; converting a feature matrix set in a preset time step into bidirectional propagation graph structure information by utilizing a graph convolution neural network according to the correlation and time sequence correlation, and carrying out forward propagation and backward propagation according to the correlation, wherein the directions of corresponding graph data are from top to bottom and from bottom to top, virtual goods and shortcut service are taken as node sets of the graph structure, and transaction relations and correlations are taken as edge structure sets of the graph structure; and obtaining node characteristics in the graph structure information, marking the corresponding graph structure information and the node characteristics by using different platform information, and obtaining high-dimensional characteristics corresponding to historical transaction behaviors of virtual goods and shortcut services of users in different platforms.
The recommendation model is constructed by using a graph convolution neural network, graph structure information and corresponding high-dimensional characteristics corresponding to different platforms by a user are extracted, the user trains by a federal learning algorithm, computing power and network environment of the different platforms are judged, and whether the data training synchronization time meets a preset period is judged according to the computing power and the network environment; because the different platforms correspond to different distributed databases, the training process is asynchronous, the training process has deviation, the training process judges the rounds of participation in training according to the different platforms meeting the preset period, when the training rounds of the different platforms deviate within the preset rounds, the attention weights of the different platforms are acquired by using a multi-head attention mechanism, two layers of attention structures are arranged, and the high-dimensional characteristics are connected in series and subjected to average operation by using the attention weights; acquiring characteristic output of an attention layer in a current preset period for nonlinear activation, respectively sending homomorphic encrypted parameters required by calculating gradients to the opposite side according to high-dimensional characteristics of different platforms after nonlinear operation, calculating encryption gradients of different platforms, and protecting privacy information of a user through the encryption gradients; the encrypted high-dimensional features are aggregated by using corresponding graph structure information, the graph structure information is updated, the updated graph structure is used for continuing to aggregate, a platform which is the first to complete aggregation is promoted to be used as a preset global platform, the aggregated high-dimensional features are uploaded to the preset global platform, the encrypted parameters and the encryption gradient are used for decoding and are returned to different platforms, and the preset global platform is selected by using an election mechanism so as to avoid the fault problem of a platform communication terminal or performance bottleneck; and acquiring preference information of the user at different stages in different platforms by using the updated user vector, the updated virtual commodity vector and the updated shortcut service vector, and outputting a prediction result for recommendation. And the relevance of the recommendation model is obtained by using inner products of different virtual commodity vectors and shortcut service vectors, and the preference information is used for extracting the interest characteristics of the user.
According to the embodiment of the application, when the demand information of the user cannot inquire the corresponding virtual commodity and the shortcut service, the corresponding user interest information is acquired through the demand information of the user, a personal database is constructed according to the historical transaction behavior of the user, the corresponding word vector is extracted by using the evaluation data of the personal database, the word vector is subjected to clustering analysis and is classified into a preset emotion type, the type label of the word vector is set according to the emotion type, and personalized data is generated based on the word frequency and the word vector length of the word vector with the type label; and judging the consistency of the user interest information and the personalized data, acquiring personalized data with high consistency as input of a recommendation model, acquiring a fuzzy recommendation set of user demand information, and adjusting subsequent recommendation based on feedback of the user on each virtual commodity and shortcut service in the fuzzy recommendation set.
Fig. 4 shows a block diagram of an intelligent management system for virtual goods and shortcut services according to the present application.
The second aspect of the present application also provides an intelligent management system 4 for virtual goods and shortcut services, the system comprising: the memory 41 and the processor 42, wherein the memory includes an intelligent management method program of the virtual commodity and the shortcut service, and the intelligent management method program of the virtual commodity and the shortcut service realizes the following steps when being executed by the processor:
acquiring demand information of a user, judging a demand instruction based on the demand information, inquiring corresponding virtual commodity information and shortcut service information through the demand instruction, reading target programs of the virtual commodity and the shortcut service, and matching the target degree with the demand instruction to generate request information;
carrying out shipping preprocessing according to the request information, judging whether the request information accords with a preset standard, writing a shipping command into a message queue and returning to a shipping interface when the request information accords with the preset standard, and executing the shipping command;
acquiring historical transaction information of virtual goods and shortcut services of a user, utilizing a graph convolution neural network to mine high-dimensional characteristics according to the historical transaction information, introducing a federal learning algorithm to train the graph convolution neural network under the condition of ensuring the privacy of the user, and constructing a recommendation model;
and verifying the execution condition of the delivery command, acquiring feedback information according to the verification information in combination with the virtual commodity information and the shortcut service information, importing the feedback information into the recommendation model, and generating and pushing the virtual commodity or the shortcut service with high relation with the demand information.
The third aspect of the present application also provides a computer readable storage medium, where the computer readable storage medium includes an intelligent management method program for virtual goods and shortcut services, where the intelligent management method program for virtual goods and shortcut services implements the steps of the intelligent management method for virtual goods and shortcut services according to any one of the above steps when executed by a processor.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, 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.
Alternatively, the above-described integrated units of the present application may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An intelligent management method for virtual goods and shortcut service is characterized by comprising the following steps:
acquiring demand information of a user, judging a demand instruction based on the demand information, inquiring corresponding virtual commodity information and shortcut service information through the demand instruction, reading target programs of the virtual commodity and the shortcut service, and matching the target degree with the demand instruction to generate request information;
carrying out shipping preprocessing according to the request information, judging whether the request information accords with a preset standard, writing a shipping command into a message queue and returning to a shipping interface when the request information accords with the preset standard, and executing the shipping command;
acquiring historical transaction information of virtual goods and shortcut services of a user, utilizing a graph convolution neural network to mine high-dimensional characteristics according to the historical transaction information, introducing a federal learning algorithm to train the graph convolution neural network under the condition of ensuring the privacy of the user, and constructing a recommendation model;
and verifying the execution condition of the delivery command, acquiring feedback information according to the verification information in combination with the virtual commodity information and the shortcut service information, importing the feedback information into the recommendation model, and generating and pushing the virtual commodity or the shortcut service with high relation with the demand information.
2. The intelligent management method for virtual goods and shortcut service according to claim 1, wherein the method is characterized in that the demand information of the user is obtained, the demand instruction is judged based on the demand information, the corresponding virtual goods information and shortcut service information are inquired through the demand instruction, and the target program of the virtual goods and shortcut service is read, specifically:
acquiring inquiry information of a user, performing single-heat encoding on the inquiry information to acquire feature vectors corresponding to the inquiry information, generating requirement information of the user, and judging category information of virtual goods and shortcut services inquired by the user through the requirement information;
generating a demand instruction according to the category information, extracting the identity and the authority of a user, matching the demand instruction with the identity and the authority, and searching virtual commodity information and shortcut service information corresponding to the user identity and the authority by using the matched demand instruction in a distributed search manner;
and acquiring a corresponding target program from a distributed database through the virtual commodity information and the shortcut service information, setting a source identifier according to the source of the target program, and generating request information based on the user identity and the authority by combining the target program marked with the source identifier with user demand instruction matching.
3. The intelligent management method for virtual goods and shortcut service according to claim 1, wherein the shipping preprocessing is performed according to the request information, and whether the request information meets a preset standard is judged, and when the request information meets the preset standard, a shipping command is written into a message queue and returned to a shipping interface, specifically:
acquiring request information to perform shipping preprocessing, wherein the shipping preprocessing comprises judging the legality of the request information, judging whether the residual quantity of the virtual goods meets the required quantity according to the virtual goods information, and judging whether the identity and authority of a user meet the single-user limit of the virtual goods and the shortcut service;
generating a judgment matrix according to the judgment condition of the shipping pretreatment as a row vector, generating a standard matrix according to the preset standard of the judgment condition, and comparing the judgment matrix with the standard matrix to judge whether the request information accords with the preset standard;
when the preset standard is met, writing the delivery command into a message queue and returning to a delivery interface, inquiring ID information of the virtual commodity and the shortcut service corresponding to the basic resource through the message content of the message queue, constructing RPC call based on RDMA, and executing the delivery command.
4. The intelligent management method for virtual goods and shortcut service according to claim 1, wherein the method is characterized in that the historical transaction information of the virtual goods and the shortcut service of the user is obtained, and the high-dimensional characteristics are mined by utilizing a graph convolutional neural network according to the historical transaction information, specifically:
searching a release information table corresponding to the virtual commodity and the shortcut service based on the identity and the authority of the user by utilizing data searching, screening historical transaction information of the user from the release information table, extracting multi-mode data in the historical transaction information, and carrying out data cleaning on the multi-mode data;
carrying out feature construction on the multi-mode data subjected to data cleaning by utilizing feature codes to generate feature matrixes, acquiring the feature matrixes corresponding to users and the feature matrixes corresponding to virtual goods and shortcut services, and acquiring the correlation of the feature matrixes through spearman correlation analysis;
converting the feature matrix set in a preset time step into bidirectional propagation graph structure information by utilizing a graph convolution neural network according to the correlation and time sequence correlation;
and obtaining node characteristics in the graph structure information, marking the corresponding graph structure information and the node characteristics by using different platform information, and obtaining high-dimensional characteristics corresponding to historical transaction behaviors of virtual goods and shortcut services of users in different platforms.
5. The intelligent management method for virtual goods and shortcut service according to claim 1, wherein the federal learning algorithm is introduced to train a graph roll neural network under the condition of ensuring the privacy of a user, and a recommendation model is constructed, specifically:
constructing a recommendation model by using a graph convolution neural network, extracting graph structure information and corresponding high-dimensional characteristics corresponding to different platforms by a user, training by using a federal learning algorithm, judging computing power and network environment of the different platforms, and judging whether the data training synchronization time meets a preset period according to the computing power and the network environment;
judging the rounds of participation in training according to different platforms meeting a preset period, acquiring the attention weights of the different platforms by using a multi-head attention mechanism when the training rounds of the different platforms deviate from the preset rounds, setting two layers of attention structures, and carrying out series connection and average operation on the high-dimensional characteristics by using the attention weights;
acquiring characteristic output of an attention layer in a current preset period for nonlinear activation, respectively sending homomorphic encrypted parameters required by calculating gradients to the opposite side according to high-dimensional characteristics of different platforms after nonlinear operation, calculating encryption gradients of different platforms, and protecting privacy information of a user through the encryption gradients;
the encrypted high-dimensional features are aggregated by using corresponding graph structure information, the graph structure information is updated, the updated graph structure is used for continuing to aggregate, the aggregated high-dimensional features are uploaded to a preset global platform, and the encrypted parameters and the encryption gradient are used for decoding and are returned to different platforms;
and outputting a prediction result in different platforms by using the updated user vector, the updated virtual commodity vector and the updated shortcut service vector to recommend the user vector, the virtual commodity vector and the updated shortcut service vector.
6. The intelligent management method for virtual goods and shortcut service according to claim 1, wherein the feedback information is obtained by combining virtual goods information and shortcut service information according to the verification information, and the feedback information is imported into the recommendation model to generate and push the virtual goods or shortcut service with high relevance to the demand information, specifically comprising:
acquiring the position of a resource party according to the inquired ID information of the virtual commodity and the shortcut service corresponding to the basic resource, acquiring receipt information of the resource party after the delivery command is executed based on the position of the resource party, judging whether the execution is successful according to the receipt information, and generating check information based on a judgment result;
carrying out delivery again by using the verification information, sending early warning information when the failure times reach a preset threshold value, and obtaining feedback information by using the verification information and virtual commodity information or shortcut service information corresponding to delivery when the failure times are successful;
the feedback information is used as input of a recommendation model, and other virtual goods and shortcut services with high association degree with the current virtual goods or shortcut services are obtained through the recommendation model to be marked and suspended;
extracting long-short-period interest features of a user, extracting suspended virtual commodity information or shortcut service information, calculating the similarity between the virtual commodity information or shortcut service information and the long-short-period interest features, and generating recommendation weights according to the similarity;
and sequencing the suspended virtual goods or shortcut services by using the recommendation weight, and selecting the virtual goods or shortcut services with the highest weight to push to the client of the user.
7. An intelligent management system for virtual goods and shortcut services, comprising: the intelligent management method comprises a memory and a processor, wherein the memory comprises an intelligent management method program of virtual goods and shortcut services, and the intelligent management method program of the virtual goods and the shortcut services realizes the following steps when being executed by the processor:
acquiring demand information of a user, judging a demand instruction based on the demand information, inquiring corresponding virtual commodity information and shortcut service information through the demand instruction, reading target programs of the virtual commodity and the shortcut service, and matching the target degree with the demand instruction to generate request information;
carrying out shipping preprocessing according to the request information, judging whether the request information accords with a preset standard, writing a shipping command into a message queue and returning to a shipping interface when the request information accords with the preset standard, and executing the shipping command;
acquiring historical transaction information of virtual goods and shortcut services of a user, utilizing a graph convolution neural network to mine high-dimensional characteristics according to the historical transaction information, introducing a federal learning algorithm to train the graph convolution neural network under the condition of ensuring the privacy of the user, and constructing a recommendation model;
and verifying the execution condition of the delivery command, acquiring feedback information according to the verification information in combination with the virtual commodity information and the shortcut service information, importing the feedback information into the recommendation model, and generating and pushing the virtual commodity or the shortcut service with high relation with the demand information.
8. The intelligent management system for virtual goods and shortcut service according to claim 7, wherein the shipping preprocessing is performed according to the request information, and whether the request information meets a preset standard is judged, and when the request information meets the preset standard, the shipping command is written into the message queue and returned to the shipping interface, specifically:
acquiring request information to perform shipping preprocessing, wherein the shipping preprocessing comprises judging the legality of the request information, judging whether the residual quantity of the virtual goods meets the required quantity according to the virtual goods information, and judging whether the identity and authority of a user meet the single-user limit of the virtual goods and the shortcut service;
generating a judgment matrix according to the judgment condition of the shipping pretreatment as a row vector, generating a standard matrix according to the preset standard of the judgment condition, and comparing the judgment matrix with the standard matrix to judge whether the request information accords with the preset standard;
when the preset standard is met, writing the delivery command into a message queue and returning to a delivery interface, inquiring ID information of the virtual commodity and the shortcut service corresponding to the basic resource through the message content of the message queue, constructing RPC call based on RDMA, and executing the delivery command.
9. The intelligent management system for virtual goods and shortcut service according to claim 7, wherein the historical transaction information of the virtual goods and the shortcut service of the user is obtained, and the high-dimensional characteristics are mined by utilizing a graph convolutional neural network according to the historical transaction information, specifically:
searching a release information table corresponding to the virtual commodity and the shortcut service based on the identity and the authority of the user by utilizing data searching, screening historical transaction information of the user from the release information table, extracting multi-mode data in the historical transaction information, and carrying out data cleaning on the multi-mode data;
carrying out feature construction on the multi-mode data subjected to data cleaning by utilizing feature codes to generate feature matrixes, acquiring the feature matrixes corresponding to users and the feature matrixes corresponding to virtual goods and shortcut services, and acquiring the correlation of the feature matrixes through spearman correlation analysis;
converting the feature matrix set in a preset time step into bidirectional propagation graph structure information by utilizing a graph convolution neural network according to the correlation and time sequence correlation;
and obtaining node characteristics in the graph structure information, marking the corresponding graph structure information and the node characteristics by using different platform information, and obtaining high-dimensional characteristics corresponding to historical transaction behaviors of virtual goods and shortcut services of users in different platforms.
10. The intelligent management system for virtual goods and shortcut service according to claim 7, wherein the feedback information is obtained by combining virtual goods information and shortcut service information according to the verification information, and the feedback information is imported into the recommendation model to generate and push the virtual goods or shortcut service with high relevance to the demand information, specifically comprising:
acquiring the position of a resource party according to the inquired ID information of the virtual commodity and the shortcut service corresponding to the basic resource, acquiring receipt information of the resource party after the delivery command is executed based on the position of the resource party, judging whether the execution is successful according to the receipt information, and generating check information based on a judgment result;
carrying out delivery again by using the verification information, sending early warning information when the failure times reach a preset threshold value, and obtaining feedback information by using the verification information and virtual commodity information or shortcut service information corresponding to delivery when the failure times are successful;
the feedback information is used as input of a recommendation model, and other virtual goods and shortcut services with high association degree with the current virtual goods or shortcut services are obtained through the recommendation model to be marked and suspended;
extracting long-short-period interest features of a user, extracting suspended virtual commodity information or shortcut service information, calculating the similarity between the virtual commodity information or shortcut service information and the long-short-period interest features, and generating recommendation weights according to the similarity;
and sequencing the suspended virtual goods or shortcut services by using the recommendation weight, and selecting the virtual goods or shortcut services with the highest weight to push to the client of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311351869.6A CN117217710A (en) | 2023-10-19 | 2023-10-19 | Intelligent management method and system for virtual commodity and shortcut service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311351869.6A CN117217710A (en) | 2023-10-19 | 2023-10-19 | Intelligent management method and system for virtual commodity and shortcut service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117217710A true CN117217710A (en) | 2023-12-12 |
Family
ID=89046289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311351869.6A Pending CN117217710A (en) | 2023-10-19 | 2023-10-19 | Intelligent management method and system for virtual commodity and shortcut service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117217710A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808562A (en) * | 2024-02-29 | 2024-04-02 | 南京特沃斯高科技有限公司 | Network marketing method and platform based on metaspace |
| CN117808562B (en) * | 2024-02-29 | 2024-05-10 | 南京特沃斯高科技有限公司 | Network marketing method and platform based on metaspace |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2700015A1 (en) * | 2007-10-04 | 2009-04-09 | Xiam Technologies Limited | Recommendation generation systems, apparatus, and methods |
| WO2014135034A1 (en) * | 2013-03-06 | 2014-09-12 | 腾讯科技（深圳）有限公司 | Method for processing order, transaction server and computer readable storage medium |
| US20180040012A1 (en) * | 2016-08-05 | 2018-02-08 | Linctronix Ltd. | Virtual and real market commodity recommendation and reward system |
| JP2018181326A (en) * | 2017-04-06 | 2018-11-15 | ネイバー コーポレーションＮＡＶＥＲ Ｃｏｒｐｏｒａｔｉｏｎ | Personalized products recommendation using deep learning |
| CN109544131A (en) * | 2018-10-22 | 2019-03-29 | 深圳市创梦天地科技有限公司 | A kind of game merchandise control method and device |
| CN111340587A (en) * | 2020-02-21 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Virtual commodity management method and related device |
| CN112199719A (en) * | 2020-10-10 | 2021-01-08 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN112541111A (en) * | 2020-11-09 | 2021-03-23 | 武汉蝌蚪信息技术有限公司 | Commodity retrieval and commodity recommendation system based on decentralized big data retrieval market |
| CN113240490A (en) * | 2021-05-18 | 2021-08-10 | 中国人民大学 | Intelligent service transaction recommendation method and system based on graph neural network |
| CN113688252A (en) * | 2021-08-09 | 2021-11-23 | 广西师范大学 | Safe cross-domain recommendation method based on multi-feature collaborative knowledge map and block chain |
| CN113688855A (en) * | 2020-05-19 | 2021-11-23 | 华为技术有限公司 | Data processing method, federal learning training method, related device and equipment |
| WO2022083332A1 (en) * | 2020-10-23 | 2022-04-28 | 华为技术有限公司 | Commodity data management method and apparatus, and server |
| CN114780831A (en) * | 2022-03-25 | 2022-07-22 | 中国科学院自动化研究所 | Sequence recommendation method and system based on Transformer |
| CN115330509A (en) * | 2022-04-22 | 2022-11-11 | 北京邮电大学 | Credit investigation service classification method and system based on credit investigation service transaction platform integration |
| CN115375382A (en) * | 2021-05-18 | 2022-11-22 | 京东科技控股股份有限公司 | Commodity recommendation method and device and related equipment |
| CN115601772A (en) * | 2022-12-15 | 2023-01-13 | 南京邮电大学（Cn） | Multi-mode learning-based aesthetic quality evaluation model and method |
| US20230014937A1 (en) * | 2021-07-13 | 2023-01-19 | Capital One Services, Llc | Virtual Warehouse Query Monitoring and Reporting |
| CN115878904A (en) * | 2023-02-22 | 2023-03-31 | 深圳昊通技术有限公司 | Intellectual property personalized recommendation method, system and medium based on deep learning |
| WO2023141809A1 (en) * | 2022-01-26 | 2023-08-03 | 深圳技术大学 | Metaverse-based shared information privacy protection method and related apparatus |
-
2023
- 2023-10-19 CN CN202311351869.6A patent/CN117217710A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2700015A1 (en) * | 2007-10-04 | 2009-04-09 | Xiam Technologies Limited | Recommendation generation systems, apparatus, and methods |
| WO2014135034A1 (en) * | 2013-03-06 | 2014-09-12 | 腾讯科技（深圳）有限公司 | Method for processing order, transaction server and computer readable storage medium |
| US20180040012A1 (en) * | 2016-08-05 | 2018-02-08 | Linctronix Ltd. | Virtual and real market commodity recommendation and reward system |
| JP2018181326A (en) * | 2017-04-06 | 2018-11-15 | ネイバー コーポレーションＮＡＶＥＲ Ｃｏｒｐｏｒａｔｉｏｎ | Personalized products recommendation using deep learning |
| CN109544131A (en) * | 2018-10-22 | 2019-03-29 | 深圳市创梦天地科技有限公司 | A kind of game merchandise control method and device |
| CN111340587A (en) * | 2020-02-21 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Virtual commodity management method and related device |
| CN113688855A (en) * | 2020-05-19 | 2021-11-23 | 华为技术有限公司 | Data processing method, federal learning training method, related device and equipment |
| CN112199719A (en) * | 2020-10-10 | 2021-01-08 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and computer readable storage medium |
| WO2022083332A1 (en) * | 2020-10-23 | 2022-04-28 | 华为技术有限公司 | Commodity data management method and apparatus, and server |
| CN112541111A (en) * | 2020-11-09 | 2021-03-23 | 武汉蝌蚪信息技术有限公司 | Commodity retrieval and commodity recommendation system based on decentralized big data retrieval market |
| CN113240490A (en) * | 2021-05-18 | 2021-08-10 | 中国人民大学 | Intelligent service transaction recommendation method and system based on graph neural network |
| CN115375382A (en) * | 2021-05-18 | 2022-11-22 | 京东科技控股股份有限公司 | Commodity recommendation method and device and related equipment |
| US20230014937A1 (en) * | 2021-07-13 | 2023-01-19 | Capital One Services, Llc | Virtual Warehouse Query Monitoring and Reporting |
| CN113688252A (en) * | 2021-08-09 | 2021-11-23 | 广西师范大学 | Safe cross-domain recommendation method based on multi-feature collaborative knowledge map and block chain |
| WO2023141809A1 (en) * | 2022-01-26 | 2023-08-03 | 深圳技术大学 | Metaverse-based shared information privacy protection method and related apparatus |
| CN114780831A (en) * | 2022-03-25 | 2022-07-22 | 中国科学院自动化研究所 | Sequence recommendation method and system based on Transformer |
| CN115330509A (en) * | 2022-04-22 | 2022-11-11 | 北京邮电大学 | Credit investigation service classification method and system based on credit investigation service transaction platform integration |
| CN115601772A (en) * | 2022-12-15 | 2023-01-13 | 南京邮电大学（Cn） | Multi-mode learning-based aesthetic quality evaluation model and method |
| CN115878904A (en) * | 2023-02-22 | 2023-03-31 | 深圳昊通技术有限公司 | Intellectual property personalized recommendation method, system and medium based on deep learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808562A (en) * | 2024-02-29 | 2024-04-02 | 南京特沃斯高科技有限公司 | Network marketing method and platform based on metaspace |
| CN117808562B (en) * | 2024-02-29 | 2024-05-10 | 南京特沃斯高科技有限公司 | Network marketing method and platform based on metaspace |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111339433B (en) | Information recommendation method and device based on artificial intelligence and electronic equipment | |
| CN109492772A (en) | The method and apparatus for generating information | |
| CN111831636A (en) | Data processing method, device, computer system and readable storage medium | |
| CN114722281B (en) | Training course configuration method and device based on user portrait and user course selection behavior | |
| CN109962975A (en) | Information-pushing method, device, electronic equipment and system based on object identification | |
| CN111932267A (en) | Enterprise financial service risk prediction method and device | |
| CN112036483B (en) | AutoML-based object prediction classification method, device, computer equipment and storage medium | |
| CN106407381A (en) | Method and device for pushing information based on artificial intelligence | |
| CN109615504A (en) | Products Show method, apparatus, electronic equipment and computer readable storage medium | |
| CN111898767A (en) | Data processing method, device, equipment and medium | |
| CN114266443A (en) | Data evaluation method and device, electronic equipment and storage medium | |
| CN113656699B (en) | User feature vector determining method, related equipment and medium | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN112199374B (en) | Data feature mining method for data missing and related equipment thereof | |
| CN112100491A (en) | Information recommendation method, device and equipment based on user data and storage medium | |
| CN116629423A (en) | User behavior prediction method, device, equipment and storage medium | |
| CN116484105A (en) | Service processing method, device, computer equipment, storage medium and program product | |
| CN110597977A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN116522131A (en) | Object representation method, device, electronic equipment and computer readable storage medium | |
| CN117217710A (en) | Intelligent management method and system for virtual commodity and shortcut service | |
| CN115187330A (en) | Product recommendation method, device, equipment and medium based on user label | |
| CN114519505A (en) | Equipment management strategy generation method and system for railway passenger station | |
| CN116205700A (en) | Recommendation method and device for target product, computer equipment and storage medium | |
| CN115329183A (en) | Data processing method, device, storage medium and equipment | |
| CN112035740A (en) | Project use duration prediction 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 |