CN114971818B - Intelligent restaurant data storage processing method and system - Google Patents
Intelligent restaurant data storage processing method and system Download PDFInfo
- Publication number
- CN114971818B CN114971818B CN202210918820.3A CN202210918820A CN114971818B CN 114971818 B CN114971818 B CN 114971818B CN 202210918820 A CN202210918820 A CN 202210918820A CN 114971818 B CN114971818 B CN 114971818B
- Authority
- CN
- China
- Prior art keywords
- data
- storage
- matching
- ordering
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013500 data storage Methods 0.000 title claims description 30
- 238000003672 processing method Methods 0.000 title claims description 16
- 238000012545 processing Methods 0.000 claims abstract description 82
- 238000004891 communication Methods 0.000 claims abstract description 48
- 230000003993 interaction Effects 0.000 claims abstract description 46
- 238000000034 method Methods 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims description 42
- 238000013507 mapping Methods 0.000 claims description 39
- 238000004458 analytical method Methods 0.000 claims description 35
- 239000011159 matrix material Substances 0.000 claims description 30
- 230000005540 biological transmission Effects 0.000 claims description 18
- 230000004927 fusion Effects 0.000 claims description 17
- 230000007717 exclusion Effects 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 9
- 230000035622 drinking Effects 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Pure & Applied Mathematics (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and a system for storing and processing intelligent restaurant data, wherein the method comprises the following steps: step 1: acquiring a data interface of an intelligent restaurant, and matching a first storage area according to the interface type of the data interface; step 2: determining communication interaction operation of each data interface, and carrying out area processing on the first storage area; step 3: and carrying out data processing on the service data of the intelligent restaurant, matching the data processing result with the area processing result, and storing the corresponding matching data in the related second storage area. The type of the data interface is determined, region matching is performed, region processing is performed through communication interaction operation, reasonable matching of data and regions is performed, reasonable storage of the data is guaranteed, follow-up checking of the data is facilitated, and checking efficiency is improved.
Description
Technical Field
The invention relates to the technical field of data storage and processing, in particular to a method and a system for storing and processing intelligent restaurant data.
Background
Along with the development and progress of society, more and more restaurants begin to be built intelligently, and in-store meal ordering or out-of-store meal ordering is generally carried out for intelligent restaurants, a platform of the intelligent restaurants can automatically reserve and store related orders, so that the intelligent restaurants are convenient for store owners to check, but general users can inquire about a certain time period, sales of certain foods and the like, but the inquiry process is based on the stored whole data content and does not check about a small part of data, so that the checking efficiency is low.
Therefore, the invention provides a method and a system for storing and processing intelligent restaurant data.
Disclosure of Invention
The invention provides a data storage processing method and a data storage processing system for an intelligent restaurant, which are characterized in that the type of a data interface is determined, region matching is carried out, region processing is carried out through communication interaction operation, reasonable matching of data and regions is carried out, reasonable storage of the data is ensured, follow-up data checking is facilitated, and checking efficiency is improved.
The invention provides a data storage processing method of an intelligent restaurant, which comprises the following steps:
step 1: acquiring a data interface of an intelligent restaurant, and matching a first storage area according to the interface type of the data interface;
step 2: determining communication interaction operation of each data interface, and carrying out area processing on the first storage area;
step 3: and carrying out data processing on the service data of the intelligent restaurant, matching the data processing result with the area processing result, and storing the corresponding matching data in the related second storage area.
Preferably, the process of data processing on the service data of the intelligent restaurant includes:
acquiring ordering information of the intelligent restaurant, counting ordering objects according to the ordering information, and acquiring an ordering graph of each ordering object, wherein the ordering graph is related to ordering time, ordering quantity, ordering amount and dining type;
Constructing a first objective function of the same ordering object based on the ordering graph;
constructing a second objective function of the same ordering object in all ordering information containing the ordering object;
based on a function analysis model, analyzing the following vector of each constraint condition corresponding to the second objective function based on the first objective function, and further constructing a following matrix;
acquiring the following characteristics of the following matrix, and determining the accompanying recommendation coefficient X of the same object to be placed;
wherein ,
representing the occurrence probability of the same item corresponding to the ith following vector, wherein when the same item is generated together based on a preset package, the corresponding occurrence probability is 1, otherwise, the corresponding occurrence probability is equal to the occurrence probability of the same item corresponding to the historical order in the historical period; />
Representing the following feature; x1 represents satisfying the following markQuasi-standard features; n1 represents the total number of following vectors in the following matrix; />
Representing the occurrence probability of the j-th following vector in the remaining following vectors whose occurrence probabilities are not 1; n2 represents the total number of remaining following vectors whose occurrence probability is not 1;
and predicting the maximum number of the placed items related to the same item in a preset period according to the accompanying recommendation coefficient X, matching a temporary storage space with the maximum number of the placed items, and setting the item identification of the same item to the temporary storage space.
Preferably, the acquiring the data interface of the intelligent restaurant comprises:
counting the working platforms of the intelligent restaurant and acquiring a platform configurable interface of each working platform;
calling a historical work log of each configurable interface, and determining whether a situation of the dominated work exists or not;
if so, reserving the configurable interface;
otherwise, rejecting the configurable interface;
all reserved interfaces are used as data interfaces.
Preferably, the matching the first storage area according to the interface type of the data interface includes:
determining a type log of the interface type based on a historical database;
analyzing the type log, determining a storage rule of the interface type, and determining a storage area related to the intelligent restaurant according to the storage rule;
and acquiring the work configuration information of the to-be-stored area to obtain a data storage workflow of the to-be-stored area, and screening an area, in which the data storage workflow is completely consistent with the storage rule, from the to-be-stored area to serve as a first storage area.
Preferably, determining the communication interaction operation of each data interface, and performing area processing on the first storage area, including:
Acquiring communication interaction operation with a data interface, and acquiring a communication interaction log of the communication interaction operation;
based on the deep neural network model, acquiring single mapping relations between similar data types and corresponding similar data features in the same-communication interaction log and acquiring full mapping relations between all the similar data types and all the similar data features in the same-communication interaction log;
establishing a relation to be compared based on all single mapping relations, comparing the relation to be compared with a full mapping relation, determining whether the relation to be compared is consistent, and if so, reserving the single mapping relation and the full mapping relation;
otherwise, checking the deep neural network model according to the inconsistent relation, obtaining feedback information, judging whether the feedback information meets a rejection standard, rejecting the single mapping relation if the feedback information meets the rejection standard, and reserving the full mapping relation;
according to the reserved mapping relation, constructing a type-characteristic scene of the data type and the data characteristic of each communication interaction log, and acquiring a first scene of data access, a second scene of data transmission and a third scene of data receiving of the same data type according to the type-characteristic scene;
Performing scene analysis on the first scene, the second scene and the third scene which are of the same data type;
determining a weighting matrix based on a data source of the communication interaction log, wherein the weighting matrix is related to data access, data transmission and data reception;
a first weighting array is called from the weighting matrix based on the scene attribute of the first scene, a second weighting array is called from the weighting matrix based on the scene attribute of the second scene, and a third weighting array is called from the weighting matrix based on the scene attribute of the third scene;
extracting weighting parameters of the first weighting array, the second weighting array and the third weighting array, and carrying out weighting parameter fusion to obtain a fourth weighting array;
predicting access elements, transmission elements and receiving elements corresponding to the same data type according to scene analysis results and a fourth weighting array;
performing first fusion analysis on all access elements of the acquired same-communication interaction log, performing second fusion analysis on all transmission elements, and performing third fusion analysis on all receiving elements;
and determining the region splitting condition corresponding to the first storage region according to the fusion analysis result, and performing region processing on the corresponding first storage region.
Preferably, the storing the corresponding matching data in the associated second storage area further includes:
performing authority analysis on the matching data based on an authority analysis model to obtain a first authority;
acquiring whether the second storage area has the right operation matched with the first right or not;
if so, storing the matching data in a related second storage area;
otherwise, calculating the authority mutual exclusion degree of the storage authority of the second storage area and the first authority;
wherein H11 represents the authority mutex; s0 represents a first authority; s1, representing a storage authority; h0 represents the total index number of the first authority and the second authority;
index value of h1 index in the first authority is 0,0.5]；
Index value of h1 index in storage authority is 0,0.5]；/>
Representing acquisition->
And->
Is a larger value of (a); e represents a constant, and the value is 2.7; />
Representing intersection symbols; />
Representing union symbols;
when the authority mutual exclusion is larger than a preset mutual exclusion, searching a second storage area matched with the first authority again, and storing the area;
otherwise, for H0
Sorting from small to large, screening storage indexes corresponding to the first N storage authorities, and setting correction identifiers for each storage index respectively to correct the storage authorities of the second storage area, so as to realize matching of corresponding matching data and the second storage area for drinking. / >
Preferably, matching the data processing result with the area processing result, storing the corresponding matching data in the related second storage area, including:
calibrating the appearance position of the restaurant object mark of the data processing result based on the type identification model, and determining the mark type of the calibrated position;
determining the identification distribution of the similar identification types based on the identification occurrence positions, and determining the corresponding data distribution based on the identification distribution;
constructing data vectors of the same data distribution based on the data content of the same data distribution and the data occurrence time of each data segment in the data distribution;
determining primary data segments of the same data distribution, acquiring first associated data segments adjacent to the primary data segments, and simultaneously acquiring residual data segments of the same data distribution, and acquiring second associated data segments adjacent to each residual data segment;
setting a first association weight to a first association data segment based on the data type of the first data segment and the data type of the first association data segment, and adjusting the first association weight according to the historical associatable probability of the first data segment to obtain a second association weight;
Setting a third association weight to each second associated data segment based on the historical occurrence probability of each remaining data segment being in the same data distribution as the primary data segment and the data type of each second associated data segment;
based on the second association weight and the third association weight, adjusting the data vectors distributed in the same data to obtain an adjustment vector, and acquiring corresponding features according to the adjustment vector;
based on all the characteristics, constructing a characteristic array for obtaining the data processing result, and matching a corresponding storage mode with each element in the characteristic array;
and according to the storage mode, the second storage area with consistent storage attribute in the processing result of the matching area stores the data processing result of the corresponding feature.
Preferably, according to the storage mode, the second storage area for storing the attribute in a consistent manner in the processing result of the matching area includes:
acquiring a storage thread of the storage mode, analyzing the storage thread, and calibrating storage difficulty of storage according to the storage mode;
based on the storage difficulty, constructing a storage matching condition, and simultaneously, acquiring a storage attribute of the storage mode;
And based on the storage matching condition and the storage attribute, matching a second storage area consistent in the area processing result.
The invention provides an intelligent restaurant data storage processing system, which comprises:
the area matching module is used for acquiring a data interface of the intelligent restaurant and matching a first storage area according to the interface type of the data interface;
the area processing module is used for determining communication interaction operation of each data interface and carrying out area processing on the first storage area;
and the data area matching module is used for carrying out data processing on the service data of the intelligent restaurant, matching the data processing result with the area processing result and storing the corresponding matching data in the related second storage area.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a method for processing intelligent restaurant data storage in an embodiment of the invention;
FIG. 2 is a block diagram of a smart restaurant data storage processing system in accordance with an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
The invention provides a method for storing and processing intelligent restaurant data, as shown in fig. 1, comprising the following steps:
step 1: acquiring a data interface of an intelligent restaurant, and matching a first storage area according to the interface type of the data interface;
step 2: determining communication interaction operation of each data interface, and carrying out area processing on the first storage area;
step 3: and carrying out data processing on the service data of the intelligent restaurant, matching the data processing result with the area processing result, and storing the corresponding matching data in the related second storage area.
In this embodiment, the data interface refers to an interface on a related platform that participates in the intelligent operation of the intelligent restaurant.
In this embodiment, the interface type may be related to the content type of the data transmission, and the matching of the areas is achieved by matching according to the type.
In this embodiment, the communication interaction refers to an operation received by the data interface from a different platform, data transmitted by the different platform, and the like.
In this embodiment, for example, operations 1, 2, and 3 exist in the communication interaction operation, and at this time, since the data interface itself corresponds to the first storage area, the area is subdivided according to different operations.
In this embodiment, the data processing refers to a determination of the type of service data and the corresponding storage mode of the smart restaurant, and by matching with the subdivided area, efficient storage of data is achieved.
The beneficial effects of the technical scheme are as follows: the type of the data interface is determined, region matching is performed, region processing is performed through communication interaction operation, reasonable matching of data and regions is performed, reasonable storage of the data is guaranteed, follow-up checking of the data is facilitated, and checking efficiency is improved.
The invention provides a data storage processing method of an intelligent restaurant, which comprises the following steps of:
acquiring ordering information of the intelligent restaurant, counting ordering objects according to the ordering information, and acquiring an ordering graph of each ordering object, wherein the ordering graph is related to ordering time, ordering quantity, ordering amount and dining type;
constructing a first objective function of the same ordering object based on the ordering graph;
constructing a second objective function of the same ordering object in all ordering information containing the ordering object;
based on a function analysis model, analyzing the following vector of each constraint condition corresponding to the second objective function based on the first objective function, and further constructing a following matrix;
acquiring the following characteristics of the following matrix, and determining the accompanying recommendation coefficient X of the same object to be placed;
wherein ,
representing the occurrence probability of the same item corresponding to the ith following vector, wherein when the same item is generated together based on a preset package, the corresponding occurrence probability is 1, otherwise, the corresponding occurrence probability is equal to the occurrence probability of the same item corresponding to the historical order in the historical period; x0 represents the following feature; x1 represents a standard feature satisfying the following standard; n1 represents the total number of following vectors in the following matrix; / >
Representing the occurrence probability of the j-th following vector in the remaining following vectors whose occurrence probabilities are not 1; n2 represents the total number of remaining following vectors whose occurrence probability is not 1;
and predicting the maximum number of the placed items related to the same item in a preset period according to the accompanying recommendation coefficient X, matching a temporary storage space with the maximum number of the placed items, and setting the item identification of the same item to the temporary storage space.
In this embodiment, the accompanying recommendation coefficient is determined mainly to determine the possibility that the object is ordered when ordering, so that the interval can be effectively estimated, and the regional capacity is ensured.
In this embodiment, the constraint is determined based on a function, such as taste determination, component determination, time determination, etc.
In this embodiment, the function analysis model is pre-trained and is analyzed for models under different conditions.
In this embodiment, n1 is much greater than 1.
The beneficial effects of the technical scheme are as follows: the first objective function is constructed by drawing a graph of the ordering information, the second objective function is constructed according to the conditions based on all the ordering information, and then the following matrix is constructed, so that the recommendation coefficient is calculated, the possibility that the object is ordered when the object is ordered is determined, the interval can be effectively estimated, the area capacity is ensured, and an effective basis is provided for interval allocation.
The invention provides a data storage processing method of an intelligent restaurant, which acquires a data interface of the intelligent restaurant and comprises the following steps:
counting the working platforms of the intelligent restaurant and acquiring a platform configurable interface of each working platform;
calling a historical work log of each configurable interface, and determining whether a situation of the dominated work exists or not;
if so, reserving the configurable interface;
otherwise, rejecting the configurable interface;
all reserved interfaces are used as data interfaces.
The beneficial effects of the technical scheme are as follows: the interface is determined through the determination platform, so that whether the interface is subjected to dominant work is determined, effective determination of the data interface is realized, and a basis is provided for subsequent region division.
The invention provides a data storage processing method of an intelligent restaurant, which matches a first storage area according to the interface type of a data interface, and comprises the following steps:
determining a type log of the interface type based on a historical database;
analyzing the type log, determining a storage rule of the interface type, and determining a storage area related to the intelligent restaurant according to the storage rule;
and acquiring the work configuration information of the to-be-stored area to obtain a data storage workflow of the to-be-stored area, and screening an area, in which the data storage workflow is completely consistent with the storage rule, from the to-be-stored area to serve as a first storage area.
The beneficial effects of the technical scheme are as follows: through log analysis and rule determination, the region to be stored can be determined, and then a consistent region is obtained, so that a basis is provided for determining the first storage region.
The invention provides a method for storing and processing intelligent restaurant data, which determines the communication interaction operation of each data interface and carries out regional processing on a first storage region, and comprises the following steps:
acquiring communication interaction operation with a data interface, and acquiring a communication interaction log of the communication interaction operation;
based on the deep neural network model, acquiring single mapping relations between similar data types and corresponding similar data features in the same-communication interaction log and acquiring full mapping relations between all the similar data types and all the similar data features in the same-communication interaction log;
establishing a relation to be compared based on all single mapping relations, comparing the relation to be compared with a full mapping relation, determining whether the relation to be compared is consistent, and if so, reserving the single mapping relation and the full mapping relation;
otherwise, checking the deep neural network model according to the inconsistent relation, obtaining feedback information, judging whether the feedback information meets a rejection standard, rejecting the single mapping relation if the feedback information meets the rejection standard, and reserving the full mapping relation;
According to the reserved mapping relation, constructing a type-characteristic scene of the data type and the data characteristic of each communication interaction log, and acquiring a first scene of data access, a second scene of data transmission and a third scene of data receiving of the same data type according to the type-characteristic scene;
performing scene analysis on the first scene, the second scene and the third scene which are of the same data type;
determining a weighting matrix based on a data source of the communication interaction log, wherein the weighting matrix is related to data access, data transmission and data reception;
a first weighting array is called from the weighting matrix based on the scene attribute of the first scene, a second weighting array is called from the weighting matrix based on the scene attribute of the second scene, and a third weighting array is called from the weighting matrix based on the scene attribute of the third scene;
extracting weighting parameters of the first weighting array, the second weighting array and the third weighting array, and carrying out weighting parameter fusion to obtain a fourth weighting array;
predicting access elements, transmission elements and receiving elements corresponding to the same data type according to scene analysis results and a fourth weighting array;
Performing first fusion analysis on all access elements of the acquired same-communication interaction log, performing second fusion analysis on all transmission elements, and performing third fusion analysis on all receiving elements;
and determining the region splitting condition corresponding to the first storage region according to the fusion analysis result, and performing region processing on the corresponding first storage region.
In this embodiment, the communication interaction operation is related to communication data, communication mode, data type, data capacity, communication time, and the like, and further a communication interaction log is obtained.
In this embodiment, the deep neural network model is trained in advance, and mainly performs relationship analysis on a communication interaction log corresponding to the same interface, where the relationship analysis includes single mapping between each type of data features of the communication interaction log and the type of data features and full mapping between all types of data features, the former is a one-to-one relationship, the latter is a many-to-many relationship, and the single mapping and the full mapping are two ways, so that comparison is performed to determine which data needs to be reserved.
In this embodiment, the single mapping relationship: 1-01,2-02, multiple mapping relationship: 1. 2-01, 02, at this time, the two are considered to be identical, if the mapping relationships are: 1. 2-01, 02 and 03, wherein the two are regarded as inconsistent, a single mapping relation is obtained through a single mapping mode, and a multi-mapping relation is obtained through a multi-mapping mode.
In this embodiment, the scenario is one scenario of receiving, transmitting, and accessing data according to the operation platform corresponding to the pre-intelligent restaurant, and the sequence is generally: access, transmission, reception.
In this embodiment, the area splitting condition is required to satisfy the elements of access, transmission, reception, and the like included in the same type of data.
In this embodiment, the type-feature scenario is a scenario for different data types and where the type of feature can be applied, so that the scenarios of access, handover reception and transmission can be determined.
In this embodiment, the weighting matrix is preset and can be determined directly by the data source.
In this embodiment, the different scene attributes are matched from the weighting matrix to obtain the corresponding weighting arrays, and then the fusion array including access, interaction and transmission, that is, the fourth array is obtained by extracting the key parameters in each weighting array.
The beneficial effects of the technical scheme are as follows: different scenes of the data with the same data type are determined according to the mapping relation, and then the weighted array is called through scene attributes and the array is fused, so that access, receiving and transmission elements with different data types can be obtained, fusion analysis of all data corresponding to the same interface is facilitated, the condition of reasonable splitting of the region is constructed, reasonable splitting of the region is guaranteed, and follow-up accurate checking of the data is realized.
The invention provides a storage processing method of intelligent restaurant data, which stores corresponding matching data in a relevant second storage area, and further comprises the following steps:
performing authority analysis on the matching data based on an authority analysis model to obtain a first authority;
acquiring whether the second storage area has the right operation matched with the first right or not;
if so, storing the matching data in a related second storage area;
otherwise, calculating the authority mutual exclusion degree of the storage authority of the second storage area and the first authority;
wherein H11 represents the authority mutex; s0 represents a first authority; s1, representing a storage authority; h0 represents the total index number of the first authority and the second authority;
index value of h1 index in the first authority is 0,0.5]；
Index value of h1 index in storage authority is 0,0.5]；/>
Representing acquisition->
And->
Is a larger value of (a); e represents a constant, and the value is 2.7; />
Representing intersection symbols; />
Representing union symbols;
when the authority mutual exclusion is larger than a preset mutual exclusion, searching a second storage area matched with the first authority again, and storing the area;
Otherwise, for H0
Sorting from small to large, screening storage indexes corresponding to the first N storage authorities, and setting correction identifiers for each storage index respectively to correct the storage authorities of the second storage area, so as to realize matching of corresponding matching data and the second storage area for drinking.
In this embodiment, the authority analysis model is trained in advance, and is obtained by training the matching data and various authorities corresponding to the data as samples, and finally, the first authority of the matching data is obtained.
In this embodiment, the authority operation is, for example, data writing, data calling, or the like.
In this embodiment, N is less than H0.
In this embodiment, the storage index is corrected, so that the authority can be corrected, and the matching of the region and the first authority is further ensured.
The beneficial effects of the technical scheme are as follows: the second storage area is determined to be reasonably stored by matching the authority operation of the second storage area with the first authority, and further when the second storage area is not matched, the second storage area is processed in different modes by calculating the authority mutual exclusion degree between the two authorities, so that the second storage area is ensured to be matched with the first authority, the reasonable storage of matched data is further ensured, the storage rationality of the second storage area is ensured, and an effective basis is provided for the follow-up data check.
The invention provides a data storage processing method of an intelligent restaurant, which matches a data processing result with an area processing result and stores corresponding matching data in a related second storage area, and comprises the following steps:
calibrating the appearance position of the restaurant object mark of the data processing result based on the type identification model, and determining the mark type of the calibrated position;
determining the identification distribution of the similar identification types based on the identification occurrence positions, and determining the corresponding data distribution based on the identification distribution;
constructing data vectors of the same data distribution based on the data content of the same data distribution and the data occurrence time of each data segment in the data distribution;
determining primary data segments of the same data distribution, acquiring first associated data segments adjacent to the primary data segments, and simultaneously acquiring residual data segments of the same data distribution, and acquiring second associated data segments adjacent to each residual data segment;
setting a first association weight to a first association data segment based on the data type of the first data segment and the data type of the first association data segment, and adjusting the first association weight according to the historical associatable probability of the first data segment to obtain a second association weight;
Setting a third association weight to each second associated data segment based on the historical occurrence probability of each remaining data segment being in the same data distribution as the primary data segment and the data type of each second associated data segment;
based on the second association weight and the third association weight, adjusting the data vectors distributed in the same data to obtain an adjustment vector, and acquiring corresponding features according to the adjustment vector;
based on all the characteristics, constructing a characteristic array for obtaining the data processing result, and matching a corresponding storage mode with each element in the characteristic array;
and according to the storage mode, the second storage area with consistent storage attribute in the processing result of the matching area stores the data processing result of the corresponding feature.
In this embodiment, the type recognition model is trained in advance, and is obtained by training with different types of identifiers as samples, so that positions of different identifiers of the data can be determined, and further, distribution of the same identifier is obtained.
In this embodiment, the data appearance time refers to an initial point in time of each data segment.
In this embodiment, the data vector is determined primarily in terms of content and time, and each content and time may be an element in the vector.
In this embodiment, the first data segment refers to the data segment in which the identifier first appears, and the remaining data segments refer to other data segments in the same type identifier than the initial data segment.
In this embodiment, since the corresponding data types in the same communication interaction data are different, other data types will affect the data storage, so that corresponding impact weights are set for different data segments to adjust the vector, ensure the reliability of the corresponding vector of each data distribution, and further ensure the rationality of storing different types of data.
The beneficial effects of the technical scheme are as follows: and carrying out type distinction on the held data through a type recognition model to obtain data distribution, and further adjusting the data vector according to the data vector of the same data distribution and the influence weights of different data segments at the end of the same data distribution, so as to ensure the reliability of the acquisition of the corresponding characteristics of each held data, ensure the rationality of the storage of the data and further ensure the follow-up high-efficiency of data verification.
The invention provides a data storage processing method of an intelligent restaurant, which matches a second storage area with consistent storage attribute in an area processing result according to the storage mode, and comprises the following steps:
Acquiring a storage thread of the storage mode, analyzing the storage thread, and calibrating storage difficulty of storage according to the storage mode;
based on the storage difficulty, constructing a storage matching condition, and simultaneously, acquiring a storage attribute of the storage mode;
and based on the storage matching condition and the storage attribute, matching a second storage area consistent in the area processing result.
In this embodiment, for example, the storage threads corresponding to the storage mode 1 are 01, 02, and 03, wherein after the storage threads are analyzed according to the analysis thread model, the determined storage difficulty is 02, and at this time, the storage matching condition is constructed according to the storage related parameter of the storage difficulty 02, and the storage difficulty refers to the situation that special attention is required in the storage process.
In this embodiment, the storage attribute relates to a storage type, a storage capacity, and the like.
In this embodiment, the matched second storage area satisfies both the storage matching condition and the storage attribute.
The beneficial effects of the technical scheme are as follows: the second storage area can be obtained by matching through determining the storage thread of the storage mode, determining the condition according to the storage difficulty and combining the attribute, so that the effective partition storage of the data is ensured, and an effective basis is provided for subsequent checking.
The invention provides a data storage processing system of an intelligent restaurant, as shown in fig. 2, comprising:
the area matching module is used for acquiring a data interface of the intelligent restaurant and matching a first storage area according to the interface type of the data interface;
the area processing module is used for determining communication interaction operation of each data interface and carrying out area processing on the first storage area;
and the data area matching module is used for carrying out data processing on the service data of the intelligent restaurant, matching the data processing result with the area processing result and storing the corresponding matching data in the related second storage area.
The beneficial effects of the technical scheme are as follows: the type of the data interface is determined, region matching is performed, region processing is performed through communication interaction operation, reasonable matching of data and regions is performed, reasonable storage of the data is guaranteed, follow-up checking of the data is facilitated, and checking efficiency is improved.
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 (8)
1. A method for processing intelligent restaurant data storage, comprising:
step 1: acquiring a data interface of an intelligent restaurant, and matching a first storage area according to the interface type of the data interface;
step 2: determining communication interaction operation of each data interface, and carrying out area processing on the first storage area;
step 3: performing data processing on the service data of the intelligent restaurant, matching the data processing result with the area processing result, and storing corresponding matching data in a related second storage area;
wherein, the process of carrying out data processing on the service data of the intelligent restaurant comprises the following steps:
acquiring ordering information of the intelligent restaurant, counting ordering objects according to the ordering information, and acquiring an ordering graph of each ordering object, wherein the ordering graph is related to ordering time, ordering quantity, ordering amount and dining type;
constructing a first objective function of the same ordering object based on the ordering graph;
constructing a second objective function of the same ordering object in all ordering information containing the ordering object;
based on a function analysis model, analyzing the following vector of each constraint condition corresponding to the second objective function based on the first objective function, and further constructing a following matrix;
Acquiring the following characteristics of the following matrix, and determining the accompanying recommendation coefficient X of the same object to be placed;
wherein ,
representing the occurrence probability of the same item corresponding to the ith following vector, wherein when the same item is generated together based on a preset package, the corresponding occurrence probability is 1, otherwise, the corresponding occurrence probability is equal to the occurrence probability of the same item corresponding to the historical order in the historical period;
representing the following feature; x1 represents a standard feature satisfying the following standard; n1 represents the total number of following vectors in the following matrix;
representing the occurrence probability of the j-th following vector in the remaining following vectors whose occurrence probability is not 1; n2 represents the total number of remaining following vectors whose occurrence probability is not 1;
and predicting the maximum number of the placed items related to the same item in a preset period according to the accompanying recommendation coefficient X, matching a temporary storage space with the maximum number of the placed items, and setting the item identification of the same item to the temporary storage space.
2. The intelligent restaurant data storage processing method as claimed in claim 1, wherein obtaining the data interface of the intelligent restaurant comprises:
Counting the working platforms of the intelligent restaurant and acquiring a platform configurable interface of each working platform;
calling a historical work log of each configurable interface, and determining whether a situation of the dominated work exists or not;
if so, reserving the configurable interface;
otherwise, rejecting the configurable interface;
all reserved interfaces are used as data interfaces.
3. The intelligent restaurant data storage processing method as set forth in claim 1, wherein matching the first storage area according to the interface type of the data interface includes:
determining a type log of the interface type based on a historical database;
analyzing the type log, determining a storage rule of the interface type, and determining a storage area related to the intelligent restaurant according to the storage rule;
and acquiring the work configuration information of the to-be-stored area to obtain a data storage workflow of the to-be-stored area, and screening an area, in which the data storage workflow is completely consistent with the storage rule, from the to-be-stored area to serve as a first storage area.
4. The intelligent restaurant data storage processing method as claimed in claim 1, wherein determining communication interaction of each data interface and performing regional processing on said first storage region comprises:
Acquiring communication interaction operation with a data interface, and acquiring a communication interaction log of the communication interaction operation;
based on the deep neural network model, acquiring single mapping relations between similar data types and corresponding similar data features in the same-communication interaction log and acquiring full mapping relations between all the similar data types and all the similar data features in the same-communication interaction log;
establishing a relation to be compared based on all single mapping relations, comparing the relation to be compared with a full mapping relation, determining whether the relation to be compared is consistent, and if so, reserving the single mapping relation and the full mapping relation;
otherwise, checking the deep neural network model according to the inconsistent relation, obtaining feedback information, judging whether the feedback information meets a rejection standard, rejecting the single mapping relation if the feedback information meets the rejection standard, and reserving the full mapping relation;
according to the reserved mapping relation, constructing a type-characteristic scene of the data type and the data characteristic of each communication interaction log, and acquiring a first scene of data access, a second scene of data transmission and a third scene of data receiving of the same data type according to the type-characteristic scene;
Performing scene analysis on the first scene, the second scene and the third scene which are of the same data type;
determining a weighting matrix according to the data source of the communication interaction log, wherein the weighting matrix relates to data access, data transmission and data reception;
a first weighting array is called from the weighting matrix based on the scene attribute of the first scene, a second weighting array is called from the weighting matrix based on the scene attribute of the second scene, and a third weighting array is called from the weighting matrix based on the scene attribute of the third scene;
extracting weighting parameters of the first weighting array, the second weighting array and the third weighting array, and carrying out weighting parameter fusion to obtain a fourth weighting array;
predicting access elements, transmission elements and receiving elements corresponding to the same data type according to scene analysis results and a fourth weighting array;
performing first fusion analysis on all access elements of the acquired same-communication interaction log, performing second fusion analysis on all transmission elements, and performing third fusion analysis on all receiving elements;
and determining the region splitting condition corresponding to the first storage region according to the fusion analysis result, and performing region processing on the corresponding first storage region.
5. The intelligent restaurant data storage processing method as set forth in claim 1, wherein storing the corresponding match data in the associated second storage area further comprises:
performing authority analysis on the matching data based on an authority analysis model to obtain a first authority;
acquiring whether the second storage area has the right operation matched with the first right or not;
if so, storing the matching data in a related second storage area;
otherwise, calculating the authority mutual exclusion degree of the storage authority of the second storage area and the first authority;
wherein H11 represents the authority mutex; s0 represents a first authority; s1, representing a storage authority; h0 represents the total index number of the first authority and the second authority;
index value of h1 index in the first authority is 0,0.5]；
Index value of h1 index in storage authority is 0,0.5]；
Representation acquisition
And (3) with
Is a larger value of (a); e represents a constant, and the value is 2.7;
representing intersection symbols;
representing union symbols;
when the authority mutual exclusion is larger than a preset mutual exclusion, searching a second storage area matched with the first authority again, and storing the area;
Otherwise, to
Sorting from small to large, screening storage indexes corresponding to the first N storage authorities, and setting correction identifiers for each storage index respectively to correct the storage authorities of the second storage areas so as to realize the matching of the corresponding matching data and the corresponding second storage areas.
6. The intelligent restaurant data storage processing method as set forth in claim 1, wherein matching the data processing results with the area processing results, storing the corresponding matching data in the associated second storage area, includes:
calibrating the appearance position of the restaurant object mark of the data processing result based on the type identification model, and determining the mark type of the calibrated position;
determining the identification distribution of the similar identification types based on the identification occurrence positions, and determining the corresponding data distribution based on the identification distribution;
constructing data vectors of the same data distribution based on the data content of the same data distribution and the data occurrence time of each data segment in the data distribution;
determining primary data segments of the same data distribution, acquiring first associated data segments adjacent to the primary data segments, and simultaneously acquiring residual data segments of the same data distribution, and acquiring second associated data segments adjacent to each residual data segment;
Setting a first association weight to a first association data segment based on the data type of the first data segment and the data type of the first association data segment, and adjusting the first association weight according to the historical associatable probability of the first data segment to obtain a second association weight;
setting a third association weight to each second associated data segment based on the historical occurrence probability of each remaining data segment being in the same data distribution as the primary data segment and the data type of each second associated data segment;
based on the second association weight and the third association weight, adjusting the data vectors distributed in the same data to obtain an adjustment vector, and acquiring corresponding features according to the adjustment vector;
based on all the characteristics, constructing a characteristic array for obtaining the data processing result, and matching a corresponding storage mode with each element in the characteristic array;
and according to the storage mode, the second storage area with consistent storage attribute in the processing result of the matching area stores the data processing result of the corresponding feature.
7. The intelligent restaurant data storage processing method as set forth in claim 6, wherein, according to said storage mode, the second storage area matching the storage attributes in the area processing result includes:
Acquiring a storage thread of the storage mode, analyzing the storage thread, and calibrating storage difficulty of storage according to the storage mode;
based on the storage difficulty, constructing a storage matching condition, and simultaneously, acquiring a storage attribute of the storage mode;
and based on the storage matching condition and the storage attribute, matching a second storage area consistent in the area processing result.
8. An intelligent restaurant data storage processing system, comprising:
the area matching module is used for acquiring a data interface of the intelligent restaurant and matching a first storage area according to the interface type of the data interface;
the area processing module is used for determining communication interaction operation of each data interface and carrying out area processing on the first storage area;
the data area matching module is used for carrying out data processing on the service data of the intelligent restaurant, matching the data processing result with the area processing result and storing the corresponding matching data in a related second storage area;
wherein, the process of carrying out data processing on the service data of the intelligent restaurant comprises the following steps:
acquiring ordering information of the intelligent restaurant, counting ordering objects according to the ordering information, and acquiring an ordering graph of each ordering object, wherein the ordering graph is related to ordering time, ordering quantity, ordering amount and dining type;
Constructing a first objective function of the same ordering object based on the ordering graph;
constructing a second objective function of the same ordering object in all ordering information containing the ordering object;
based on a function analysis model, analyzing the following vector of each constraint condition corresponding to the second objective function based on the first objective function, and further constructing a following matrix;
acquiring the following characteristics of the following matrix, and determining the accompanying recommendation coefficient X of the same object to be placed;
wherein ,
representing the occurrence probability of the same item corresponding to the ith following vector, wherein when the same item is generated together based on a preset package, the corresponding occurrence probability is 1, otherwise, the corresponding occurrence probability is equal to the occurrence probability of the same item corresponding to the historical order in the historical period;
representing the following feature; x1 represents a standard feature satisfying the following standard; n1 represents the total number of following vectors in the following matrix;
representing the occurrence probability of the j-th following vector in the remaining following vectors whose occurrence probability is not 1; n2 represents the total number of remaining following vectors whose occurrence probability is not 1;
and predicting the maximum number of the placed items related to the same item in a preset period according to the accompanying recommendation coefficient X, matching a temporary storage space with the maximum number of the placed items, and setting the item identification of the same item to the temporary storage space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210918820.3A CN114971818B (en) | 2022-08-02 | 2022-08-02 | Intelligent restaurant data storage processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210918820.3A CN114971818B (en) | 2022-08-02 | 2022-08-02 | Intelligent restaurant data storage processing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114971818A CN114971818A (en) | 2022-08-30 |
| CN114971818B true CN114971818B (en) | 2023-04-28 |
Family
ID=82969571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210918820.3A Active CN114971818B (en) | 2022-08-02 | 2022-08-02 | Intelligent restaurant data storage processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114971818B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117908684B (en) * | 2024-03-20 | 2024-06-18 | 南昌大学 | Virtual reality implementation method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951572A (en) * | 2017-04-12 | 2017-07-14 | 上海斐讯数据通信技术有限公司 | A kind of food and drink commending system and dining recommending method |
| CN112861149A (en) * | 2021-01-29 | 2021-05-28 | 深圳市鹰硕云科技有限公司 | Data storage method and system of intelligent education platform |
| CN113592674A (en) * | 2021-07-01 | 2021-11-02 | 北京优海网络科技有限公司 | IKMS-based intelligent restaurant system |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10387931B2 (en) * | 2015-10-28 | 2019-08-20 | Under Armour, Inc. | Health tracking system with restaurant matching |
| CN109087230A (en) * | 2018-08-13 | 2018-12-25 | 河南易商谷电子商务有限公司 | A kind of intelligence community service system and its application method |
| CN111444396B (en) * | 2020-03-24 | 2021-06-01 | 深圳市中盛瑞达科技有限公司 | Big data storage system |
| CN113052651B (en) * | 2021-03-17 | 2024-04-23 | 广东便捷神科技股份有限公司 | Intelligent retail management method and system based on big data |
| CN113673757B (en) * | 2021-08-17 | 2022-02-25 | 杭州企智互联科技有限公司 | Intelligent dining room dining rule prediction method and device |
| CN113869677A (en) * | 2021-09-15 | 2021-12-31 | 张家豪 | Catering industry supply and marketing platform based on Internet and control method thereof |
| CN113870063A (en) * | 2021-10-13 | 2021-12-31 | 滨州学院 | Campus wisdom dining room system based on computer vision technique |
| CN114529405B (en) * | 2022-02-24 | 2022-11-15 | 发明之家(北京)科技有限公司 | Information access management method and system based on intelligent transaction |
-
2022
- 2022-08-02 CN CN202210918820.3A patent/CN114971818B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951572A (en) * | 2017-04-12 | 2017-07-14 | 上海斐讯数据通信技术有限公司 | A kind of food and drink commending system and dining recommending method |
| CN112861149A (en) * | 2021-01-29 | 2021-05-28 | 深圳市鹰硕云科技有限公司 | Data storage method and system of intelligent education platform |
| CN113592674A (en) * | 2021-07-01 | 2021-11-02 | 北京优海网络科技有限公司 | IKMS-based intelligent restaurant system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114971818A (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100483333C (en) | Real time data warehousing | |
| US20020032645A1 (en) | System and method for score calculation | |
| US20130249934A1 (en) | Color-based identification, searching and matching enhancement of supply chain and inventory management systems | |
| CN114971818B (en) | Intelligent restaurant data storage processing method and system | |
| CN116523262B (en) | Intelligent planning method, system and medium for production plan based on big data | |
| CN112527972A (en) | Intelligent customer service chat robot implementation method and system based on deep learning | |
| US8977621B1 (en) | Search engine optimizer | |
| CN113052651B (en) | Intelligent retail management method and system based on big data | |
| CN110992124A (en) | House resource recommendation method and system | |
| CN109509228A (en) | Method for positioning one or more candidate digital images | |
| CN111886619A (en) | Vehicle collision damage assessment method and system based on historical case | |
| CN111652661B (en) | Mobile phone client user loss early warning processing method | |
| CN116187524B (en) | Supply chain analysis model comparison method and device based on machine learning | |
| CN113568888A (en) | Index recommendation method and device | |
| CN115934923B (en) | E-commerce replying method and system based on big data | |
| CN117540822A (en) | Federal type incremental learning method, equipment and storage medium across mobile edge network | |
| CN111831892A (en) | Information recommendation method, information recommendation device, server and storage medium | |
| CN113610499B (en) | Method and system for job hunting function team occupational credit archives based on blockchain | |
| CN113961615A (en) | Multi-layer service fusion decision method and system | |
| CN114218499B (en) | Resource recommendation method and device, computer equipment and storage medium | |
| CN116993396B (en) | Risk early warning method based on vehicle user tag and computer equipment | |
| TWI759785B (en) | System and method for recommending audit criteria based on integration of qualitative data and quantitative data | |
| CN115840771B (en) | Data processing system | |
| KR102242587B1 (en) | Method and server for recommending user customized hs code | |
| CN118193753A (en) | Data query method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |