CN113283680B - Address selection method, device, equipment and storage medium thereof - Google Patents
Address selection method, device, equipment and storage medium thereof Download PDFInfo
- Publication number
- CN113283680B CN113283680B CN202110818356.6A CN202110818356A CN113283680B CN 113283680 B CN113283680 B CN 113283680B CN 202110818356 A CN202110818356 A CN 202110818356A CN 113283680 B CN113283680 B CN 113283680B
- Authority
- CN
- China
- Prior art keywords
- address
- addresses
- recommended
- candidate
- determining
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000010187 selection method Methods 0.000 title description 3
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 230000006870 function Effects 0.000 claims description 69
- 238000012549 training Methods 0.000 claims description 26
- 230000002860 competitive effect Effects 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008707 rearrangement Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000010267 cellular communication Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/043—Optimisation of two dimensional placement, e.g. cutting of clothes or wood
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Remote Sensing (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides an addressing method, device, equipment and storage medium thereof. The method comprises the steps of determining an initial model containing decision variables, an objective function and constraint conditions; carrying out approximate optimization on the objective function and the constraint condition to generate an optimized objective model; acquiring basic data, wherein the basic data comprises candidate addresses taking the decision variables as characteristics; and generating a recommended address sequence containing a plurality of recommended addresses according to the values of the decision variables of the candidate addresses and the optimized target model, so that the method can be widely applied to various industries and site selection of different regions, and has strong universality.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an address selection method, apparatus, device, and storage medium thereof.
Background
As industries develop, various industries (e.g., offline education, restaurant alliance, etc.) may face the problem of requiring large-scale site selection. The existing addressing algorithm generally adopts experience based on self service to select addresses. For example, in different industries, the variables on which addressing depends may differ; even in the same education industry, when school district address selection is carried out in different areas, address selection is often carried out depending on local business experience of each city, a unified mathematical optimization model is lacked, and universality is not provided.
Based on this, a universal addressing scheme with wider azimuth is needed.
Disclosure of Invention
In view of the above, the embodiments of the present disclosure provide an address selection scheme with stronger universality, so as to at least partially solve the above problems.
According to an aspect of the present disclosure, there is provided an addressing method, including: determining an initial model containing decision variables, an objective function and constraint conditions; carrying out approximate optimization on the objective function and the constraint condition to generate an optimized objective model; acquiring basic data, wherein the basic data comprises candidate addresses taking the decision variables as characteristics; generating a recommended address sequence containing a plurality of recommended addresses according to the values of the decision variables of the candidate addresses and the optimized target model
According to a second aspect of the present disclosure, there is provided an addressing device comprising: the determining module is used for determining an initial model containing decision variables, an objective function and constraint conditions; the optimization module is used for carrying out approximate optimization on the target function and the constraint condition to generate an optimized target model; the acquisition module is used for acquiring basic data, wherein the basic data comprises candidate addresses taking the decision variables as characteristics; and the recommending module is used for generating a recommending address sequence containing a plurality of recommending addresses according to the values of the decision variables of the candidate addresses and the optimized target model.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: a processor; and a memory storing a program, wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of the first aspect.
According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program performs the method according to the first aspect when being executed by a processor.
According to one or more technical schemes provided by the embodiment of the disclosure, an initial model containing decision variables, an objective function and constraint conditions is determined; carrying out approximate optimization on the objective function and the constraint condition to generate an optimized objective model; acquiring basic data, wherein the basic data comprises candidate addresses taking the decision variables as characteristics; and generating a recommended address sequence containing a plurality of recommended addresses according to the values of the decision variables of the candidate addresses and the optimized target model. The method and the system firstly comprehensively consider the influence of decision variables, determine the objective function according to the business target, abstract out a uniform initial model, approximately optimize the objective function and the constraint condition in the initial model based on the actual situation, can be widely applied to various industries and the site selection of various regions, and have strong universality.
Drawings
Further details, features and advantages of the disclosure are disclosed in the following description of exemplary embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a schematic flow chart of an addressing method according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram of an address engineering architecture according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram illustrating candidate addresses selected from basic data according to an embodiment of the disclosure;
fig. 4 is a schematic structural diagram of an address selecting device according to an embodiment of the present disclosure;
FIG. 5 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description. It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise. The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The following describes a scheme of the present disclosure with reference to the accompanying drawings, as shown in fig. 1, fig. 1 is a schematic flow chart of an addressing method provided in an embodiment of the present disclosure, which specifically includes:
s101, determining an initial model containing decision variables, an objective function and constraint conditions.
In different business contexts, decision variables may be chosen based on need. Decision variables may be various characteristics contained in a particular address or Point of Interest (POI). For example, the interest point may be a cell, an office building, a mall, or the like, and the decision variables may include location coordinates of the interest point, traffic, hygiene, traffic volume, noise level, and the like.
The constraint conditions are constraints on the interest points generated by the relative relationship of the interest points, and the constraint conditions can depend on the values of decision variables in the interest points. When candidate addresses are selected in some service scenes, in reality, there may already be interest points having an association relationship with the service to be addressed, and therefore, the selection of the interest points needs to be restricted based on the restriction conditions.
For example, in a scenario where a product a needs to make a service affiliate or open a product affiliate, a certain affiliate of the product a already exists at address 1, or a certain competitor of the product B (or can become a competitive product) already exists at address 2, then the constraint condition may be to constrain the selection of other nearby points of interest based on the service already existing at address 1 or address 2, and the constraint may be strong for nearby addresses (e.g., the service opened by the competitive product at address 2 does not conflict with or even complement the service of itself at all), or weak (e.g., the type of the service opened by the product a at address 1 is completely the same as the type of the service to be opened). That is, the influence of the bids may be forward or reverse, and the constraint condition may generate a forward or reverse constraint on the selection of the candidate address based on the service requirement and the value of the decision variable in the interest point.
The objective function may be a certain index selected based on actual needs, or an empirical function fitted based on actual experience. For example, in the online education scenario, the final goal may be to satisfy multiple satisfaction of the final school, parent, student, teacher, etc. at the candidate address (this may require an experience function to be characterized as an objective function), or the final goal may be to maximize the income of the school (the income of the school may be obtained by comprehensively evaluating the corresponding index, that is, a function that can be fitted by the corresponding index is used as the objective function), or an index that is highly related to the performance may be selected as the objective function (for example, by calculating actual data, the relevance of the student number to the performance of the school is 0.99 or more, and the student number predicted based on the values of the decision variables of the candidate address may be directly used as the objective function).
The initial model determined can be expressed as follows:
wherein,
；……（2）
wherein
That is, the objective function, formula (1) represents that the first N smallest values are taken
Corresponding to
As the recommended address.
The constraint condition is given by the formula (2).
Is a candidate address of the address to be selected,
is another candidate address.
Is the address of the product and is used as the address of the product,
is the address of the competitive products,
a set of candidate addresses of a specified type (e.g., in the context of addressing for online education, the specified type may be a cell or a mall, etc., in the context of addressing consumer goods affiliations, the specified type may be a shopping mall or a department store, etc.).
The 4 inequalities in the formula (2) respectively represent self constraint conditions, product constraint conditions, competitive product constraint teaching and business constraint conditions. Therein
、
And
the respective constraint thresholds may be given based on experience. i. j, k and N, M, P are all natural numbers.
S103, carrying out approximate optimization on the objective function and the constraint condition to generate an optimized objective model.
In the foregoing manner, a general form of optimization modeling of addressing is given above, and based on actual needs, an objective function and constraint conditions can be optimized approximately. Specifically, the method may include using an approximately optimized fitting function or an empirical function instead of the aforementioned objective function.
For example, the objective function is formed by adopting a business experience to select a linear weighting form of core features, or an output function of a prediction model is trained to be determined as the objective function.
The constraint condition can also be constrained in an approximate way, so that the product constraint, the competitive product constraint condition or the service constraint condition which is more in line with the service type can be obtained. For example, for the self-constraint, a recommended address sequence of a candidate address may be obtained by approximation using, for example, a sequence greedy algorithm, and for the bid constraint, the approximation may be converted into a characteristic constraint, for example, the number of bids is smaller than a specified number within several km of the candidate address, and so on.
And S105, acquiring basic data, wherein the basic data comprises candidate addresses taking the decision variables as characteristics.
The basic data may be data acquired from a Geographic Information System (GIS). The geographic information system is based on geographic spatial data, adopts a geographic model analysis method, provides various spatial and dynamic geographic information timely, and collects, stores, analyzes and visually expresses various geographic spatial information. For example, a GIS system may give its closest school distance, closest cell distance, traffic situation at an address, and geographic environmental attributes of the address (e.g., urban, suburban, populated areas, mountains, rivers), etc.
Therefore, the value of the corresponding decision variable can be given based on the basic data according to the longitude and latitude coordinates of each candidate address. For example, for address 3, the value of its decision variable may be (school district score 8, traffic score 8, people flow score 10), and so on.
And S107, generating a recommended address sequence containing a plurality of recommended addresses according to the values of the decision variables of the candidate addresses and the optimized target model.
After obtaining a plurality of candidate addresses containing decision variables, the candidate addresses can be input into the target model, the values of the target functions corresponding to the candidate addresses are respectively calculated based on the constraint conditions of the target model and the values of the decision variables of the candidate addresses, and then the first N smallest candidate addresses are selected and obtained
Corresponding to
As a recommendation address, and may be based on
The values of the recommended addresses are sorted from small to large, so that a recommended address sequence containing a plurality of recommended addresses is obtained. In the sequence of recommended addresses, the address of the user is,
the smaller, the recommended address
The further forward the ordering, the address is also characterized
May be in an objective boxThe less excellent address.
According to one or more technical schemes provided by the embodiment of the disclosure, an initial model containing decision variables, an objective function and constraint conditions is determined; carrying out approximate optimization on the objective function and the constraint condition to generate an optimized objective model; acquiring basic data, wherein the basic data comprises candidate addresses taking the decision variables as characteristics; and generating a recommended address sequence containing a plurality of recommended addresses according to the values of the decision variables of the candidate addresses and the optimized target model. The method and the system firstly comprehensively consider the influence of decision variables, determine the objective function according to the business target, abstract out a uniform initial model, approximately optimize the objective function and the constraint condition in the initial model based on the actual situation, can be widely applied to various industries and the site selection of various regions, and have strong universality.
In one embodiment, the optimized target model can be realized by adopting an actual engineering architecture. Fig. 2 is a schematic diagram of an address engineering architecture according to an embodiment of the present disclosure, as shown in fig. 2. In the framework, an application platform with the target model as an online policy layer is mainly required to be constructed, and meanwhile, a matched back end is connected with a base and a data layer, and an application layer (namely a service layer and a user layer) is connected with a front end.
Specifically, the application platform may obtain basic data including a school, a cell, or a point of interest POI from a docked geographic information system, may directly use the obtained school, cell, or point of interest POI as a candidate point, and may also directly obtain a value of a decision variable of a corresponding candidate address from the geographic information system to form a base layer, which may be completed in advance on an offline basis.
Further, on the basis of the base, the obtained basic data may be further preprocessed, including forming entity data (coordinates of each entity in the geographic system), recall data (possible candidate addresses), blacklist data (that is, a certain location has been listed as an unsuitable address), feature data (optimized values of decision variables on each address), and the like.
Therefore, the application platform can directly generate a recommended address sequence according to the basic data and the target model in the online strategy layer, and the recommended address sequence is displayed to the user in the application layer. The site selection is carried out by the application platform, the reusability and the expansibility are high, and the method can be directly applied to site selection of various industries.
In one embodiment, for the built application platform, an evaluation index may also be established to evaluate the performance of the built application platform. Specifically, when the application platform presents the recommended address, the user may not always choose from the recommended address sequence. For example, the recommended address sequence gives address 1, address 2 and address 10, whereas the user himself selects address 3 and address 10 in the map as the final opening address. Thus, the total number of addresses in the recommended address sequence may be determined; and determining an evaluation index according to the total number of the addresses and the number of the addresses selected by the user in the recommended address sequence, wherein the evaluation index is used for evaluating the performance of the application platform. The evaluation index is usually inversely related to the total number of addresses and positively related to the number of selected addresses.
In an implementation manner, a ratio of the number of addresses selected by the user in the recommended address sequence to the total number of addresses may be determined as a user point location adoption rate, and the user point location adoption rate may be determined as an evaluation index. That is, user acceptance rate = num (recommended address set)
Set of user-selected addresses)/num (user-selected address). For example, the recommended address set gives 10 addresses from address 1 to address 10, and the user selects the address set of address 1, address 2 and address 11, so that the user acceptance rate =2/3= 66.6%.
And the evaluation index = max user acceptance rate & min (num recommended address set), i.e., the evaluation index is higher when the number of recommended address sets is smaller and the user acceptance rate is larger. Assuming that in another example, if the recommended address set gives 20 addresses from address 1 to address 20, and the user selects the address set as address 1, address 2, address 11, address 12, address 21, and address 22, the user acceptance rate =4/6=66.6%, but since the number of recommended address sets is smaller in the previous example, the performance of the application platform corresponding to the previous example is higher.
In one embodiment, the optimization for the objective model may be an optimization for an objective function. For example, a part of the decision variables is selected, and an objective function for linearly weighting the part of the decision variables is constructed.
Here, the characteristics may be school type characteristics (presence or absence of a school nearby, quality evaluation of a school), cell type characteristics (presence or absence of a cell nearby, type of a cell, population of a cell, and the like), traffic characteristics (traffic convenience degree, traffic noise degree, and the like), and the like included in the candidate address. Thereby forming a linear weighting function formed by partial features, i.e.
。
Wherein,
and
i.e. the longitude and latitude coordinates of the candidate address,
characterized in the longitude and latitude coordinates of
And
the r-th feature in case of (2), l is the dimension of the feature.
Alternatively, a prediction model may be trained in advance to predict a target function corresponding to a candidate addressThe value of the number. For example, given a training sample set X which takes school income or student number as a label and takes decision variables corresponding to school addresses as characteristics, model training is carried out, and therefore training is achieved to meet the requirements
Wherein G is an objective function of the prediction model, and W is a value of each parameter of the objective function of the prediction model. In particular, the method of manufacturing a semiconductor device,
wherein h (Xi, W) is the predicted value of the training sample Xi (i.e. the candidate address Xi) when the parameter value is W, yi represents the label value of the training sample Xi, L is the loss function,
is a pre-set empirical term used to prevent over-fitting of the predictive model. When the finally calculated W can satisfy
In the process, the training of the prediction model can be considered to be completed, and then the value of a candidate address under the target function can be predicted based on the values of the decision variables of the candidate address, and whether the candidate address is suitable to be used as the recommended address or not is judged according to the difference between the value and the preset value.
In an embodiment, the constraint condition may specifically include:
the self-constraint condition is used for constraining the geographical distribution among the recommended addresses obtained in the recommended address sequence, for example, the distance among the recommended addresses is constrained to be not smaller than a preset value;
and/or the product constraint condition is used for constraining the geographical distribution of each recommended address in the recommended address sequence and the first type address when the first type address related to the self service exists in the basic data. For example, the distance between each recommended address and the first type address is restricted to be not less than a preset value;
and/or a competitive product constraint condition, wherein when a second type of address related to a competitor exists in the basic data, the competitive product constraint condition is used for the geographical distribution of each recommended address and the second type of address in the recommended address sequence, for example, if a competitive product is the same as a service type to be opened, the distance between each recommended address and the second type of address is constrained not to be lower than a preset value, and if the competitive product is complementary to the service type to be opened, the distance between each recommended address and the second type of address is constrained not to be greater than the preset value;
and/or, the interest point constraint condition is used for constraining the selection mode of determining the candidate address according to the interest point in the obtained basic data, for example, directly selecting the interest point from the basic data as the candidate address, or further dividing the grid of the basic map data, and selecting the candidate address from the divided grid;
and/or business constraint conditions used for constraining the geographic environment attribute of the recommended address in the recommended address sequence, for example, constraining the geographic environment in which the recommended address is located not to be a mountain, a river, etc.
In an embodiment, approximately optimizing the constraint condition may include approximately optimizing the self constraint condition, and specifically, may use a sequence greedy algorithm to approximate a sequence algorithm for jointly generating the recommendation point. After an ith recommended address is determined in the recommended address sequence, determining other candidate addresses which are more than a preset distance from the ith recommended address, wherein i is a natural number more than 1; and determining the candidate address with the minimum distance from the ith recommended address in the rest candidate addresses as the (i-1) th recommended address in the recommended address sequence. In this way, the efficiency of the generated recommended address sequence can be improved.
In one embodiment, approximately optimizing the constraints may include approximately optimizing the artifact constraints. For example, for an offline education scenario, the geographical distribution of the teaching points of the product is required to satisfy a certain network structure, so that the average distance for the user to learn does not exceed a preset value. Therefore, the product constraint can be approximately optimized as: within a preset range, the number of the first type of address and the recommended address exceeds a preset number range (namely the density of the product reaches a certain value); or the average distance between the specified type of interest points (including cells or schools) and the nearest first-class addresses and recommended addresses around the specified type of interest points does not exceed a preset value, so that the actual scene requirements can be more closely met.
Of course, in other scenarios, for example, a chain of food stores may be joined, in order to avoid a serious competition among the products, it may be necessary that the number of the first type address and the recommended address is within a preset range, and the density of the products needs to be controlled.
In one embodiment, approximately optimizing the constraints may include approximately optimizing the bid constraints. For example, the competitive product constraint condition may be directly converted into a characteristic constraint, that is, within a preset distance range of the second type address, the number of recommended addresses in the recommended address sequence does not exceed a preset number threshold, so that within the preset distance range of the recommended addresses, the number of competitive products is smaller than a specified threshold.
In one embodiment, the approximately optimizing the point of interest constraint when the basic data is geospatial data (i.e., map data) obtained from a geographic information system includes: and carrying out grid division on the geographic space data, and if a school, a cell or a point of interest (POI) exists in a grid, determining the school, the cell or the POI as a candidate address.
If no school, cell or point of interest POI exists in a grid, further evaluation may be performed based on the values of decision variables of other entity data in the grid, that is, selecting other entity addresses from the grid as candidate addresses, for example, selecting the vicinity of a certain bus stop in the grid as candidate addresses.
Further, if a plurality of candidate addresses can be selected from one grid, only a specified number (e.g., 1) of addresses can be selected from one grid as the candidate addresses, so as to avoid over-secrecy of the candidate addresses. As shown in fig. 3, fig. 3 is a schematic diagram illustrating a candidate address selected from basic data according to an embodiment of the disclosure. In this illustration, black dots represent schools, cells, or POIs, while white dots represent other physical addresses (including transportation sites, etc.) and some grids may have multiple black dots, and finally only one of the black dots is selected as a candidate address, and for some grids that do not have schools, cells, or POIs, the position of the white dot or the position of the center point of the grid may be selected as a candidate address.
In an embodiment, for an application platform that has been built, the rearrangement may be performed based on service requirements, for example, for a recommended address sequence that has been obtained, the rearrangement may be performed based on the relative distance to a certain cell, so that the actual service requirements may be met. Furthermore, recommendation information can be associated with the recommendation address in the recommendation address sequence, and the recommendation address and the recommendation information can be displayed. For example, the distance between the address and the xx cell is 300m, and the fact that students can reach 600 persons within 3 months of starting business is predicted, so that the address selection experience of the user is improved.
In a second aspect of the embodiment of the present disclosure, there is also provided an address selecting apparatus, as shown in fig. 4, fig. 4 is a schematic structural diagram of the address selecting apparatus provided in the embodiment of the present disclosure, and the address selecting apparatus includes:
a determining module 401, configured to determine an initial model including decision variables, an objective function, and constraint conditions;
an optimization module 403, which performs approximate optimization on the objective function and constraint conditions to generate an optimized objective model;
an obtaining module 405, configured to obtain basic data, where the basic data includes a candidate address that is characterized by the decision variable;
and the recommending module 407 generates a recommending address sequence containing a plurality of recommending addresses according to the values of the decision variables of the candidate addresses and the optimized target model.
In a third aspect of the embodiments of the present disclosure, exemplary embodiments of the present disclosure also provide an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program, when executed by the at least one processor, is for causing the electronic device to perform a method according to an embodiment of the disclosure.
The disclosed exemplary embodiments also provide a non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is adapted to cause the computer to perform a method according to an embodiment of the present disclosure.
The exemplary embodiments of the present disclosure also provide a computer program product comprising a computer program, wherein the computer program, when executed by a processor of a computer, is adapted to cause the computer to perform a method according to an embodiment of the present disclosure.
Referring to fig. 5, a block diagram of a structure of an electronic device 800, which may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 5, the electronic device 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The calculation unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.
A number of components in the electronic device 800 are connected to the I/O interface 805, including: an input unit 806, an output unit 807, a storage unit 808, and a communication unit 809. The input unit 806 may be any type of device capable of inputting information to the electronic device 800, and the input unit 806 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device. Output unit 807 can be any type of device capable of presenting information and can include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. The storage unit 804 may include, but is not limited to, a magnetic disk, an optical disk. The communication unit 809 allows the electronic device 800 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth (TM) devices, WiFi devices, WiMax devices, cellular communication devices, and/or the like.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
Claims (13)
1. An addressing method, comprising:
determining an initial model containing decision variables, an objective function and constraint conditions;
carrying out approximate optimization on the objective function and the constraint condition to generate an optimized objective model;
acquiring basic data, wherein the basic data comprises candidate addresses taking the decision variables as characteristics;
generating a recommended address sequence containing a plurality of recommended addresses according to the values of the decision variables of the candidate addresses and the optimized target model;
the approximately optimizing the objective function includes: training by adopting a training sample with the decision variable as a characteristic to obtain a prediction model, and determining an output function of the prediction model as the target function;
prior to the obtaining the base data, the method further comprises: constructing an application platform with the target model as an online strategy layer; the acquiring of the basic data comprises: the application platform acquires basic data including schools, cells or POI (point of interest) from a geographic information system;
the training by using the training sample with the decision variable as the characteristic to obtain a prediction model, and determining the output function of the prediction model as the target function, includes:
giving a set X of training samples which take school income or student number as a label and take decision variables corresponding to school addresses as characteristics, carrying out model training, and training to obtain a training sample which meets the requirements
Wherein G is an objective function of the prediction model, W is a value of each parameter of the objective function of the prediction model,
wherein,h (Xi, W) is the predicted value of the training sample Xi when the parameter is W, yi represents the label value of the training sample Xi, L is the loss function,
is a preset empirical term for preventing over-fitting of the predictive model; when the finally calculated W can satisfy
And then, the prediction model is trained, the value of the candidate address under the target function is predicted based on the value of each decision variable of the candidate address, and whether the candidate address is suitable for being used as the recommended address is judged according to the difference between the value of the candidate address under the target function and the preset value.
2. The method of claim 1, wherein the generating a recommended address sequence including a plurality of recommended addresses according to the values of the decision variables of the candidate addresses and the optimized target model comprises: and the application platform generates a recommended address sequence according to the basic data and the online strategy layer and displays the recommended address sequence.
3. The method of claim 2, wherein the method further comprises:
determining a total number of addresses in the recommended address sequence;
and determining an evaluation index according to the total address amount and the number of the addresses selected by the user in the recommended address sequence, wherein the evaluation index is used for evaluating the performance of the application platform.
4. The method of claim 3, wherein determining an evaluation index according to the total number of addresses and the number of addresses selected by the user in the recommended address sequence comprises:
and determining the ratio of the number of the addresses selected by the user in the recommended address sequence to the total number of the addresses as a user point location adoption rate, and determining the user point location adoption rate as an evaluation index.
5. The method of claim 1, wherein the constraints comprise:
the self constraint condition is used for constraining the geographical distribution among the obtained recommended addresses in the recommended address sequence; and/or the presence of a gas in the gas,
the product constraint condition is used for constraining the geographical distribution of each recommended address in the recommended address sequence and a first type address when the first type address related to self business exists in the basic data; and/or the presence of a gas in the gas,
a bid constraint for geographic distribution of each referral address in the referral address sequence and a second type of address associated with a competitor party when the second type of address exists in the base data; and/or the presence of a gas in the gas,
the interest point constraint condition is used for constraining the selection mode of determining the candidate address according to the interest point in the obtained basic data; and/or the presence of a gas in the gas,
and the business constraint condition is used for constraining the geographic environment attribute of the recommended address in the recommended address sequence.
6. The method of claim 5, wherein approximately optimizing the constraints comprises:
performing approximate optimization on the self constraint condition, specifically comprising: after an ith recommended address is determined in the recommended address sequence, determining other candidate addresses which are more than a preset distance from the ith recommended address, wherein i is a natural number more than 1;
and determining the candidate address with the minimum distance from the ith recommended address in the rest candidate addresses as the (i-1) th recommended address in the recommended address sequence.
7. The method of claim 5, wherein approximately optimizing the constraints comprises:
performing approximate optimization on the product constraint condition, specifically comprising: in a preset range, the number of the first type of addresses and the number of the recommended addresses exceed a preset number range; or the average distance between the specified type of interest point and the plurality of first type addresses and recommended addresses which are nearest to the specified type of interest point does not exceed a preset value.
8. The method of claim 5, wherein approximately optimizing the constraints comprises:
performing approximate optimization on the competitive product constraint conditions, specifically comprising: and in the preset distance range of the recommended address, the number of the second type of addresses does not exceed a preset number threshold.
9. The method of claim 5, wherein, when the basic data is geospatial data obtained from a geographic information system, performing approximate optimization on the point of interest constraint includes:
carrying out grid division on the geographic space data, and if a school, a cell or a point of interest (POI) exists in a grid, determining the school, the cell or the POI as a candidate address;
and if no school, cell or POI exists in the grid, selecting to obtain a candidate address according to the values of decision variables of other addresses contained in the grid.
10. The method of claim 2, wherein the method further comprises:
the application platform rearranges the recommended addresses in the recommended address sequence according to the service requirement and displays the rearranged recommended address sequence; or the application platform associates recommendation information with the recommendation address in the recommendation address sequence and displays the recommendation address and the recommendation information.
11. An addressing device comprising:
the determining module is used for determining an initial model containing decision variables, an objective function and constraint conditions;
the optimization module is used for carrying out approximate optimization on the target function and the constraint condition to generate an optimized target model;
the acquisition module is used for acquiring basic data, wherein the basic data comprises candidate addresses taking the decision variables as characteristics;
the recommending module generates a recommending address sequence containing a plurality of recommending addresses according to the values of the decision variables of the candidate addresses and the optimized target model;
the approximately optimizing the objective function includes: training by adopting a training sample with the decision variable as a characteristic to obtain a prediction model, and determining an output function of the prediction model as the target function;
the address selecting device further comprises: the building module is used for building an application platform with the target model as an online strategy layer; the acquiring of the basic data comprises: the application platform acquires basic data including schools, cells or POI (point of interest) from a geographic information system;
the training by using the training sample with the decision variable as the characteristic to obtain a prediction model, and determining the output function of the prediction model as the target function, includes:
giving a set X of training samples which take school income or student number as a label and take decision variables corresponding to school addresses as characteristics, carrying out model training, and training to obtain a training sample which meets the requirements
Wherein G is an objective function of the prediction model, W is a value of each parameter of the objective function of the prediction model,
wherein h (Xi, W) is the predicted value of the training sample Xi when the parameter value is W, yi represents the label value of the training sample Xi, L is the loss function,
is a preset empirical term for preventing over-fitting of the predictive model; when the finally calculated W can satisfy
And then, the prediction model is trained, the value of the candidate address under the target function is predicted based on the value of each decision variable of the candidate address, and whether the candidate address is suitable for being used as the recommended address is judged according to the difference between the value of the candidate address under the target function and the preset value.
12. An electronic device, comprising:
a processor; and
a memory for storing a program, wherein the program is stored in the memory,
wherein the program comprises instructions which, when executed by the processor, cause the processor to carry out the method according to any one of claims 1-10.
13. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110818356.6A CN113283680B (en) | 2021-07-20 | 2021-07-20 | Address selection method, device, equipment and storage medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110818356.6A CN113283680B (en) | 2021-07-20 | 2021-07-20 | Address selection method, device, equipment and storage medium thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113283680A CN113283680A (en) | 2021-08-20 |
| CN113283680B true CN113283680B (en) | 2021-11-12 |
Family
ID=77286800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110818356.6A Active CN113283680B (en) | 2021-07-20 | 2021-07-20 | Address selection method, device, equipment and storage medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113283680B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822556A (en) * | 2021-09-08 | 2021-12-21 | 上海天正软件有限公司 | Method and device for rapidly planning service points and electronic equipment |
| CN114611020B (en) * | 2022-05-09 | 2023-06-16 | 支付宝(杭州)信息技术有限公司 | Travel recommendation method and system |
| CN114648372A (en) * | 2022-05-23 | 2022-06-21 | 浙江口碑网络技术有限公司 | Data processing method and device, storage medium and electronic equipment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853332B (en) * | 2010-05-12 | 2011-12-28 | 中国农业大学 | Multi-facility fair site selecting method and system |
| CN109377265A (en) * | 2018-09-21 | 2019-02-22 | 金蝶蝶金云计算有限公司 | Site selecting method, device, equipment and storage medium |
| CN112868036B (en) * | 2018-11-06 | 2023-12-05 | 北京嘀嘀无限科技发展有限公司 | System and method for location recommendation |
| CN110413722B (en) * | 2019-08-06 | 2021-03-30 | 京东城市(北京)数字科技有限公司 | Address selection method, device and non-transient storage medium |
| CN110837930B (en) * | 2019-11-07 | 2023-09-19 | 腾讯科技（深圳）有限公司 | Site selection method, device, equipment and storage medium |
-
2021
- 2021-07-20 CN CN202110818356.6A patent/CN113283680B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113283680A (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113283680B (en) | Address selection method, device, equipment and storage medium thereof | |
| US11605305B2 (en) | Method, system, and computer-readable recording medium for providing education service based on knowledge units | |
| Miao et al. | Balancing quality and budget considerations in mobile crowdsourcing | |
| US10395646B2 (en) | Two-stage training of a spoken dialogue system | |
| CN111768231B (en) | Product information recommendation method and device | |
| US20190220969A1 (en) | Information processing device, data structure, information processing method, and non-transitory computer readable storage medium | |
| CN109446171B (en) | Data processing method and device | |
| CN110472798A (en) | Prediction technique, device and the computer readable storage medium of time series data | |
| CN111737439B (en) | Question generation method and device | |
| CN114972877A (en) | Image classification model training method and device and electronic equipment | |
| CN111767953B (en) | Method and apparatus for training an article coding model | |
| US20240046922A1 (en) | Systems and methods for dynamically updating machine learning models that provide conversational responses | |
| US12061650B2 (en) | Systems, methods, computing platforms, and storage media for comparing non-adjacent data subsets | |
| CN111784411A (en) | Customer prediction method and device, electronic equipment and storage medium | |
| CN112418442A (en) | Data processing method, device, equipment and storage medium for federal transfer learning | |
| US20230325944A1 (en) | Adaptive wellness collaborative media system | |
| CN116737906A (en) | Information display method, device, electronic equipment and storage medium | |
| CN115271257B (en) | Multi-zone atmospheric pollution cooperative regulation and control method and device and electronic equipment | |
| US20220164723A1 (en) | Method for determining boarding information, electronic device, and storage medium | |
| CN114140033A (en) | Service personnel allocation method and device, electronic equipment and storage medium | |
| CN107678816A (en) | A kind of program operation reminding method, device and terminal device based on geographical position | |
| EP4318375A1 (en) | Graph data processing method and apparatus, computer device, storage medium and computer program product | |
| CN113010784B (en) | Method, apparatus, electronic device and medium for generating prediction information | |
| CN113905070B (en) | Service providing method and system | |
| WO2023166564A1 (en) | Estimation device |
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 |