CN110941773A - Information recommendation method based on Internet of things - Google Patents

Abstract

The invention relates to an information recommendation method based on the Internet of things. The method comprises the following steps: acquiring user information of a target user, wherein the user information comprises position information and/or behavior information; determining candidate information in a target area related to the user information based on a positioning technology; predicting the click rate of the candidate information; generating a pre-sequencing information set according to the candidate information with high click rate; performing diversity reordering on the candidate information in the pre-ordering information set according to the context characteristics of the candidate information in the pre-ordering information set to obtain a reordered information set; and providing information recommendation service for the target user according to the candidate information in the reordering information set. By the scheme provided by the invention, the accuracy of information recommendation is improved.

Description

Information recommendation method based on Internet of things

Technical Field

The invention relates to the technical field of Internet, in particular to an information recommendation method based on the Internet of things.

Background

At present, in the field of information recommendation, user interest and preference are collected based on user historical browsing records, so that corresponding information is pushed based on the interest and preference, however, in such a manner, a large number of browsing behaviors are required to exist for a user, then the user interest and preference are obtained by training based on the browsing behaviors, and then information recommendation is realized based on the interest and preference of the user.

Disclosure of Invention

The invention provides an information recommendation method based on the Internet of things, which is used for improving the accuracy of information recommendation.

The invention provides an information recommendation method based on the Internet of things, which comprises the following steps:

acquiring user information of a target user, wherein the user information comprises position information and/or behavior information;

determining candidate information in a target area related to the user information based on a positioning technology;

predicting the click rate of the candidate information;

generating a pre-sequencing information set according to the candidate information with high click rate;

performing diversity reordering on the candidate information in the pre-ordering information set according to the context characteristics of the candidate information in the pre-ordering information set to obtain a reordered information set;

and providing information recommendation service for the target user according to the candidate information in the reordering information set.

The invention has the beneficial effects that: the candidate information can be determined based on the user position information and the behavior information, then the click rate of the candidate information is predicted, the pre-ordering information set is generated according to the candidate information with high click rate, diversity reordering is carried out on the candidate information in the pre-ordering information set to obtain the reordering information set, finally, information recommendation service is provided for the target user according to the candidate information in the reordering information set, therefore, the information is screened based on the user position information and the behavior information, the pushing accuracy is improved, secondly, the information is subjected to diversity reordering, the information recommendation service is provided for the target user according to the candidate information in the reordering information set, and the information pushing accuracy is further improved.

In one embodiment, determining candidate information within a target area associated with user information based on a location technique comprises:

determining the address and the office address of a target user according to the user information;

calculating the time required by the target user from home to the office according to the address and the office address of the target user;

judging whether the time required by the target user from home to the office is greater than first preset time or not;

when the time required by a target user from home to an office is longer than first preset time, acquiring a target area with the time required for reaching the office of the target user being shorter than second preset time based on a positioning technology;

and acquiring the property information in the target area as candidate information in the target area related to the user information.

The beneficial effect of this embodiment lies in: when the time required by a target user from home to an office is longer than first preset time, acquiring a target area of which the time required for reaching the office of the target user is shorter than second preset time; and the property information in the target area is pushed to the target user, so that when the time required by the target user from the address to the office address is too long, the property information with less time required by the target user to reach the office address is pushed to the target user, the property is actively recommended to the user who may be interested in purchasing the property, the user does not need to actively search and screen, and the time of the user is saved.

In one embodiment, calculating the time required for the target user to travel from home to office based on the target user's home address and office address comprises:

planning one or more lines from home to office of the user according to the target user address and the office address;

calculating the time required by the target user from home to the office according to the current road condition of each line and the user trip mode by combining the traffic rule information of the current time;

wherein the current road condition of the line comprises: the number of the traffic lights which need to pass through, the average waiting time of the crossing where each traffic light which needs to pass through is located, and the length of the congested road section, wherein the traffic regulation information at the current time comprises the traffic control condition and the road sealing condition.

In one embodiment, when the positioning function of the target user terminal is in an on state, the calculating the time required by the target user from home to office according to the address of the target user and the office address includes:

determining the actual time spent by the target user from the address to the office address according to the change of the positioning information in the target user terminal;

determining the actual time spent as the time required by the target user from an address to an office address.

The beneficial effect of this embodiment lies in: the time actually spent by the user from the address to the office address can be acquired based on the user terminal positioning function, so that the determination result of the time required by the target user from the address to the office address is more accurate.

In one embodiment, determining the home address and office address of the target user based on the user information comprises:

receiving the input operation of a target user in a user address input box and the input operation of a user office address input box; acquiring an address input by the target user in a user address input box as a user address; acquiring an address input by the target user in a user office address input box as a user office address;

or

Calculating the position of the target user with the longest residence time in a first preset time period and the position of the target user with the longest residence time in a second preset time period according to the positioning information in the terminal of the target user; determining the position of the target user with the longest residence time in a first preset time period as the address of the target user; and determining the position of the target user with the longest residence time in a second preset time period as the office address of the target user.

The beneficial effect of this embodiment lies in: and determining the position of the target user with the longest residence time in the first preset time period as the address of the target user, and determining the position of the target user with the longest residence time in the second preset time period as the office address of the target user, so that the address and the office address of the user can be actively determined under the condition that the user does not actively enter the home address and the company address.

In one embodiment, the pushing of the property information in the target area to the target user includes:

acquiring average house price information and house product information in sale in the target area;

pushing the average house price information and the house-in-sale property information in the target area to the target user;

the acquiring of the average house price information in the target area includes:

capturing historical trading prices of houses in the target area within a first preset time period from the internet;

and substituting the historical trading price and the price fluctuation into a preset calculation formula to calculate the average price of the house in the target area at the current time.

The beneficial effect of this embodiment lies in: the historical trading price of the house in the target area in the first preset time period can be actively captured from the internet, the acquisition channel of the historical trading price of the house is widened, and the average price of the house in the target area can be calculated based on price fluctuation.

In one embodiment, the acquiring the in-sale property information in the target area comprises:

capturing the in-sale property information in the target area from the Internet, and storing the in-sale property information in the target area captured from the Internet in a local database;

acquiring sensor information in a target property;

judging whether the target property is an in-sale property or not according to the sensor information in the target property;

when the target property is in the state of selling and storing the property, judging whether property information identical to the information of the target property exists in a local database;

and when the local database does not have the information which is the same as the information of the target property, taking the property information of the target property as new in-sale property information and storing the new in-sale property information into the local database.

The beneficial effect of this embodiment lies in: the system can capture the in-sale property information in the target area based on the Internet, and can judge whether the target property is the in-sale property based on the sensor information, so that the acquisition channel of the in-sale property information is widened, and when the local database does not have the information which is the same as the information of the target property, the property information of the target property is used as the new in-sale property information and is stored in the local database, so that the local database is updated.

In one embodiment, the determining whether the target property is a sold property according to the sensor information in the target property includes:

acquiring access control information and thermal infrared sensing information of a target property;

counting the home returning times of the user in a second preset time period according to the access control information and counting the total residence time of the user at home according to the thermal infrared sensor information;

and when the home returning times of the user in the second preset time period are less than the preset times and the total residence time of the user at home is less than the first preset time length, determining that the target property is the in-sale property.

In one embodiment, the determining whether the target property is a sold property according to the sensor information in the target property includes:

counting the visiting times and visiting time of the visitors of the target property according to a digital image sensor connected with the local place;

calculating the average visiting time of each visitor according to the visiting times and visiting time of the visitors of the target property;

and when the average visiting duration of the visitor is longer than the preset duration of the second preset time, determining that the target house property is the house property in sale.

In one embodiment, the time required for a target user to travel from home to the office is calculated according to the following:

step A1, constructing a grid map containing the address of the user and the office address, numbering the grid map, marking the grid corresponding to the address of the target user as start, marking the grid of the office address as end, then using the grid of the black grid other than the road, and eliminating the number of the black grid;

step A2, constructing an initial path to form an initial path library;

step A3, calculating the time needed by each path in the initial path library;

wherein, T_kThe time required for the kth path in the initial path library, the number of road segments contained in the Nth path, D_k,iDistance, V, of the ith road of the kth path_k,iThe speed of the ith section of the kth path, S the number of the traffic lights needing to pass the kth path, m the number of the traffic lights needing to pass at the current time, Td the average waiting time of the traffic lights, and P_k,iIs the probability of traffic jam occurring on the ith road of the kth path, DY_k,iAverage traffic jam distance VY when traffic jam occurs on the ith section of the kth path_k,iThe average running speed is 1, 2 and 3 … N when the traffic jam occurs on the ith section of the kth path;

step A4, optimizing the paths in the initial path library by using an evolutionary algorithm, wherein the method comprises the following steps:

step A401, constructing all paths in an initial path library into an evolution database;

step A402, performing basis transformation on each path in the evolutionary library, and when the basis transformation is performed, firstly determining the number of basis transformation grids;

wherein, Bk is a basis variable data volume of the kth path in the initial path library, η b is a preset basis variable coefficient, the preset value is 0.5 to 1, min T is the minimum value of the required time for evolving all paths in the database, max T is the maximum value of the required time for evolving all paths in the database, and flood is the value rounding in brackets;

BY path_iA change of basis, one value in the path of each change of basis, forms BY_iA plurality of basis variation paths;

calculating the required time corresponding to the base variable paths, and reserving each path and the path corresponding to the minimum required time value in the corresponding base variable paths as new paths so as to construct an alternate evolution database;

step A403, selecting two paths from the alternate evolution database in sequence as ancestor paths, and calculating the number of alternate evolutionary grids according to the ancestor paths;

wherein J is the evolution alternation data volume of the ancestor path, η J is a preset alternation coefficient, the preset value is 0.5 to 1, T max is the maximum value of the required time of the ancestor path, and T min is the minimum value of the required time of the ancestor path;

randomly selecting a grid at a position from the paths of two ancestor paths as an alternate grid, and alternating the continuous J values to form a new ancestor path;

calculating the required time of the ancestor path and the formed descendants, selecting the smaller 3 paths in the required time as paths to be merged into a new population library, and removing the ancestor paths from the alternate evolution database;

step A404, repeating step A403 until the remaining paths in the alternative evolution database are not enough to construct ancestor paths, ending the repeated operation, and calculating the minimum value of the required time of all paths in the new population library as a comparison value;

and step A405, taking the new population library as an evolution database, repeating the steps A402 to A405 until the comparison value is not changed for 10 times continuously, taking the path corresponding to the comparison value as a result path, wherein the comparison value is the time required by the target user from home to office.

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 hereof as well as the appended drawings.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:

fig. 1A is a flowchart of an information recommendation method based on the internet of things in an embodiment of the present invention;

fig. 1B is a flowchart of an information recommendation method based on the internet of things in an embodiment of the present invention;

fig. 2 is a flowchart of an information recommendation method based on the internet of things in an embodiment of the present invention.

Detailed Description

The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.

Fig. 1A is a flowchart of an information recommendation method based on the internet of things according to an embodiment of the present invention, and as shown in fig. 1A, the method may be implemented as the following steps S11-S16:

in step S11, obtaining user information of the target user, where the user information includes location information and/or behavior information;

in step S12, candidate information in the target area related to the user information is determined based on the positioning technology;

in step S13, click rate prediction is performed on the candidate information;

in step S14, a pre-ranking information set is generated from the candidate information with a high click rate;

in step S15, according to the context features of the candidate information in the pre-sorting information set, performing diversity reordering on the candidate information in the pre-sorting information set to obtain a reordered information set;

in step S16, an information recommendation service is provided to the target user according to the candidate information in the re-ordered information set.

In one embodiment, as shown in FIG. 1B, the above step S12 can be implemented as the following steps S121-S125:

in step S121, the address and office address of the target user are determined according to the user information;

in step S122, calculating the time required for the target user to go from home to office according to the address of the target user and the office address;

in step S123, it is determined whether the time required for the target user to go from home to the office is greater than a first preset time;

in step S124, when the time required for the target user to arrive at the office from home is greater than a first preset time, acquiring a target area with the time required for the target user to arrive at the office being less than a second preset time based on a positioning technology;

in step S125, property information in the target area is acquired as candidate information in the target area related to the user information.

At present, in a real estate service platform, users are usually required to actively log in the platform for manual searching and screening, which wastes a lot of time for the users, some users have the intention of purchasing real estate, for example, some users may have homes that are too far from the company, take more time to get on and off duty, these users have a great deal of potential interest in purchasing the property, but, if they do not actively go to the platform to search for the property, the platform is not aware of these users who are interested in purchasing the property, considering that the positioning technology based on the internet of things is very mature today, therefore, the invention aims to adopt the positioning technology of the Internet of things to know the time required by the user to get on and off the work, therefore, users who may purchase the property are analyzed, accurate pushing is achieved, time spent by the users for actively searching the property can be saved, and the property trading volume of the platform can be expanded.

Specifically, in the present embodiment, the address and the office address of the target user are determined according to the user information; calculating the time required by the target user from home to the office according to the address and the office address of the target user; judging whether the time required by the target user from home to the office is greater than first preset time or not; when the time required by the target user from home to the office is longer than the first preset time, acquiring a target area of which the time required for the target user to reach the office is shorter than the second preset time; and acquiring the property information in the target area as candidate information in the target area related to the user information.

And calculating the time required by the target user from home to the office according to the address of the target user and the office address can be realized by the following steps:

firstly, acquiring an address and an office address of a target user; then calculating the distance between the target user address and the office address; and calculating the time required by the user from the address to the office address according to the distance between the target user address and the office address.

In general, if the user commute time is greater than 60 minutes, it is highly likely to consider replacing the address, and therefore, in the present embodiment, the first preset time may be set to 60 minutes.

For example, the address and the office address of the user are obtained, the address and the office address of the user can be the address and the office address actively input by the user, or the position with the longest residence time in the evening and the position with the longest residence time in the daytime of the user are calculated based on the positioning information of the user terminal, the position with the longest residence time in the evening is regarded as the address of the user, and the position with the longest residence time in the daytime is regarded as the office address of the user.

Then calculating the distance between the target user address and the office address; and calculating the time required by the user from the address to the office address according to the distance between the target user address and the office address. And when the time required by the user from the address to the office address is calculated, route planning is carried out according to the position and the distance of the address and the office address of the user, and after the route planning is finished, the prediction is carried out through historical data and the route state in the working and leaving hours. In addition, in the calculation process, traffic conditions such as traffic restriction, traffic regulation, road closure and the like are also considered, and the accuracy of the calculated time is ensured as much as possible.

Of course, if the positioning function of the user terminal is in the on state, the actual time spent by the target user from the address to the office address can be determined according to the change of the positioning information in the target user terminal; the time actually spent by the user from the address to the office address obtained in this way is more objective than the time required by the user predicted from the calculation.

When the time required by the user from the address to the office address is calculated to be more than 60 minutes, the target area with the time required for reaching the office place of the target user to be less than 20 minutes can be obtained and acquired based on the positioning technology, and then the property information in the target area with the time required for reaching the office address to be less than 20 minutes is pushed to the user. Of course, the rented property, which takes less than 20 minutes to reach the office address, may also be pushed to the user.

The invention has the beneficial effects that: when the time required by the target user from home to the office is longer than the first preset time, acquiring a target area of which the time required for the target user to reach the office is shorter than the second preset time; the property information in the target area is pushed to the target user, so that when the time required by the target user from the address to the office address is too long, the property information with less time required by the target user to reach the office address is pushed to the target user, the property is actively recommended to the user who may be interested in purchasing the property, active searching and screening of the user are not needed, and the time of the user is saved.

In one embodiment, as shown in fig. 2, the step S11 can be implemented as the following steps:

in step S21, one or more routes from home to office of the user are planned based on the target user address and the office address;

in step S22, calculating the time required by the target user from home to the office according to the current road condition of each route and the user travel mode, in combination with traffic information of the current time;

the current road condition of the line comprises the following steps: the number of the traffic lights which need to pass through, the average waiting time of the crossing where each traffic light which needs to pass through is located, the length of the congested road section and the like, and the traffic regulation information at the current time comprises the traffic control condition, the road closing condition and the like.

For example, when the time required by a user from an address to an office address is calculated, if the positioning function of the user terminal is not started, route planning is performed according to the position and the distance of the address and the office address of the user, and after the route planning is completed, prediction is performed through historical data and the route state in the working and leaving hours. In addition, in the calculation process, traffic conditions such as traffic restriction, traffic regulation, road closure and the like are also considered, and the accuracy of the calculated time is ensured as much as possible.

Specifically, the time required for the target user to travel from home to the office may be calculated according to the following:

step A1, constructing a grid map containing the address of the user and the office address, numbering the grid map, marking the grid corresponding to the address of the target user as start, marking the grid of the office address as end, then using the grid of the black grid other than the road, and eliminating the number of the black grid;

step A2, constructing an initial path to form an initial path library;

step A3, calculating the time needed by each path in the initial path library;

wherein, T_kThe time required for the kth path in the initial path library, the number of road segments contained in the Nth path, D_k,iDistance, V, of the ith road of the kth path_k,iSpeed of the i-th path of the k-th path, SThe number of the traffic lights needing to pass through for the kth path, m is the number of the traffic lights needing to pass through at the current time and currently being red lights, Td is the average waiting time of the traffic lights, and P is the average waiting time of the traffic lights_k,iIs the probability of traffic jam occurring on the ith road of the kth path, DY_k,iAverage traffic jam distance VY when traffic jam occurs on the ith section of the kth path_k,iThe average running speed is the average running speed when the traffic jam occurs on the ith section of the kth path, wherein i is 1, 2 and 3.. N;

step A4, optimizing the paths in the initial path library by using an evolutionary algorithm, wherein the method comprises the following steps:

step A401, constructing all paths in an initial path library into an evolution database;

step A402, performing basis transformation on each path in the evolutionary library, and when the basis transformation is performed, firstly determining the number of basis transformation grids;

wherein, B_kThe method comprises the steps that base variable data volume of the kth path in an initial path library is obtained, η b is a preset base variable coefficient, the preset value is 0.5-1, min T is the minimum value of required time of all paths in an evolution database, max T is the maximum value of the required time of all paths in the evolution database, and flood is the value rounding in brackets;

BY path_iA change of basis, one value in the path of each change of basis, forms BY_iA plurality of basis variation paths;

calculating the required time corresponding to the base variable paths, and reserving each path and the path corresponding to the minimum required time value in the corresponding base variable paths as new paths so as to construct an alternate evolution database;

step A403, selecting two paths from the alternate evolution database in sequence as ancestor paths, and calculating the number of alternate evolutionary grids according to the ancestor paths;

wherein J is the evolution alternation data volume of the ancestor path, η J is a preset alternation coefficient, the preset value is 0.5 to 1, T max is the maximum value of the required time of the ancestor path, and T min is the minimum value of the required time of the ancestor path;

randomly selecting a grid at a position from the paths of two ancestor paths as an alternate grid, and alternating the continuous J values to form a new ancestor path;

calculating the required time of the ancestor path and the formed descendants, selecting the smaller 3 paths in the required time as paths to be merged into a new population library, and removing the ancestor paths from the alternate evolution database;

step A404, repeating step A403 until the remaining paths in the alternative evolution database are not enough to construct ancestor paths, ending the repeated operation, and calculating the minimum value of the required time of all paths in the new population library as a comparison value;

and step A405, taking the new population library as an evolution database, repeating the steps A402 to A405 until the comparison value is not changed for 10 times continuously, taking the path corresponding to the comparison value as a result path, wherein the comparison value is the time required by the target user from home to office.

In one embodiment, when the positioning function of the target user terminal is in the on state, the above step S121 may be implemented as the following steps B1-B2:

in step B1, determining the actual time spent by the target user from the address to the office address according to the change of the positioning information in the target user terminal;

in step B2, it is determined that the actual time spent is the time required for the target user to travel from home address to office address.

If the positioning function of the user terminal is in an open state, the actual time spent by the target user from the address to the office address can be determined according to the change of the positioning information in the target user terminal; the time actually spent by the user from the address to the office address obtained in this way is more objective than the time required by the user predicted from the calculation.

For example, after the address and the office address of the target user are obtained, the address and the office address of the target user are marked in an electronic map, for example, the user address is marked a, the office address is marked B, the user positioning reference point changes along with the movement of the user, when the user positioning reference point leaves the mark a, the time is 7:00, at this time, the timing is started, and when the user positioning reference point reaches the mark B, the time is 8: 10, ending the timing, wherein the time interval from the beginning of the timing to the end of the timing is the actual time spent by the user from the address to the office address, and the total time is 70 minutes; the time required for the target user to go from the home address to the office address is 70 minutes.

The beneficial effect of this embodiment lies in: the time actually spent by the user from the address to the office address can be acquired based on the user terminal positioning function, so that the determination result of the time required by the target user from the address to the office address is more accurate.

In one embodiment, the above step B1 may be implemented as the following steps C1-C3:

in step C1, receiving an entry operation of a target user in a user address input box and an entry operation of a user office address input box;

in step C2, acquiring the address input by the target user in the user address input box as the user address;

in step C3, the address entered by the target user in the user office address input box is acquired as the user office address.

In one embodiment, the above step B1 can be implemented as the following steps D1-D3:

in step D1, calculating the position where the target user stays for the longest time within the first preset time period and the position where the target user stays for the longest time within the second preset time period according to the positioning information in the terminal of the target user;

in step D2, determining the location where the target user stays for the longest time within the first preset time period as the address of the target user;

in step D3, the position where the target user stays for the longest time within the second preset time period is determined as the office address of the target user.

In the embodiment, the position of the target user with the longest staying time in the first preset time period and the position of the target user with the longest staying time in the second preset time period are calculated according to the positioning information in the terminal of the target user; determining the position of the target user with the longest residence time in the first preset time period as the address of the target user; and determining the position of the target user with the longest residence time in the second preset time period as the office address of the target user.

For example, typically, the working time is 8: 00-18: 00 and rest time 22: 00-6: 00, and thus, may be between 22: 00-6: 00 is set to a first preset time period, and 8: 00-18: 00 is set to a second preset time period, and the user is switched between 22: 00-6: the location with the longest dwell time during the period 00 is typically the user's home, and 8: 00-18: the location where the residence time is longest during the period 00 is typically a company. And the server can obtain the position of the user with the longest stay time in the two time periods based on the positioning information in the target terminal of the user. And determining that the user is at 22: 00-6: 00 the position with the longest residence time in the period is the user address; determining that the user is at 8: 00-18: the position with the longest residence time in the period of 00 is the office address of the user.

The beneficial effect of this embodiment lies in: and determining the position of the target user with the longest residence time in the first preset time period as the address of the target user, and determining the position of the target user with the longest residence time in the second preset time period as the office address of the target user, so that the address and the office address of the user can be actively determined under the condition that the user does not actively enter the home address and the company address.

In one embodiment, the above step S14 can be implemented as the following steps E1-E2:

in step E1, acquiring average price information of houses and in-sale property information in the target area;

in step E2, pushing the average price information of the houses and the in-sale property information in the target area to the target user;

the obtaining of the average price information of the houses in the target area in the above step E1 may be implemented as the following steps F1-F2:

in step F1, capturing historical trading prices of the houses in the target area within a first preset time period from the internet;

in step F2, the average price of the houses in the target area at the current time is calculated by substituting the historical transaction price and the price fluctuation into a preset calculation formula.

The beneficial effect of this embodiment lies in: the historical trading price of the house in the target area in the first preset time period can be actively captured from the internet, the acquisition channel of the historical trading price of the house is widened, and the average price of the house in the target area can be calculated based on price fluctuation.

In one embodiment, the above step E1 of obtaining the in-sale property information in the target area may be implemented as the following steps G1-G5:

in step G1, capturing the in-sale property information in the target area from the Internet, and storing the in-sale property information in the target area captured from the Internet in a local database;

in step G2, sensor information in the target property is acquired;

in step G3, judging whether the target property is an in-sale property according to the sensor information in the target property;

for example, cooperation with various sensor providers may be performed, and then sensor information in a target property, such as various built-in sensors of smart homes, is determined based on a positioning technology, whether a house is occupied or not is determined according to a switching frequency of the sensors provided by the sensor providers, and when no one is occupied, the target property may be considered as a property sold with a possible intention of selling or renting.

The method can also cooperate with the property of the residential area to obtain the access control information of the target property, and determine the switching frequency of the security door according to the access control information so as to judge whether the house is occupied, and when no one is occupied, the target property can be considered to have the intention of selling or renting, and the target property is considered to be the property sold.

In step G4, when the target property is in the state of selling a property, determining whether the property information identical to the information of the target property exists in the local database;

in step G5, when the same information as the target property does not exist in the local database, the property information of the target property is stored in the local database as new in-sale property information.

The beneficial effect of this embodiment lies in: the system can capture the in-sale property information in the target area based on the Internet, and can judge whether the target property is the in-sale property based on the sensor information, so that the acquisition channel of the in-sale property information is widened, and when the local database does not have the information which is the same as the information of the target property, the property information of the target property is used as the new in-sale property information and is stored in the local database, so that the local database is updated.

In one embodiment, the above step G3 may be implemented as the following steps H1-H3:

in step H1, acquiring entrance guard information and thermal infrared sensing information of the target property;

in step H2, counting the number of times that the user returns home within a second preset time period according to the access control information and counting the total time that the user stays at home according to the thermal infrared sensor information;

in step H3, when the number of times of the user returning home in the second preset time period is less than the preset number of times, and the total length of stay of the user at home is less than the first preset length of time, the target property is determined to be an in-sale property.

In one embodiment, the above step G3 may also be implemented as the following steps J1-J3: :

in step J1, counting the visiting times and visiting time of the visitors of the target property according to the digital image sensor connected with the local;

in step J2, calculating the average visit duration of each visitor according to the visit times and visit times of the visitors of the target property;

in step J3, when the average visiting duration of the visitor is longer than the second preset time preset duration, the target property is determined to be a property sold.

In one embodiment, the time required for a target user to travel from home to the office is calculated according to the following:

step A1, constructing a grid map containing the address of the user and the office address, numbering the grid map, marking the grid corresponding to the address of the target user as start, marking the grid of the office address as end, then using the grid of the black grid other than the road, and eliminating the number of the black grid;

step A2, constructing an initial path to form an initial path library;

step A3, calculating the time needed by each path in the initial path library;

wherein, T_kThe time required for the kth path in the initial path library, the number of road segments contained in the Nth path, D_k,iDistance, V, of the ith road of the kth path_k,iThe speed of the ith section of the kth path, S the number of the traffic lights needing to pass the kth path, m the number of the traffic lights needing to pass at the current time, Td the average waiting time of the traffic lights, and P_k,iIs the probability of traffic jam occurring on the ith road of the kth path, DY_k,iAverage traffic jam distance VY when traffic jam occurs on the ith section of the kth path_k,iThe average running speed is the average running speed when the traffic jam occurs on the ith section of the kth path, wherein i is 1, 2 and 3.. N;

step A4, optimizing the paths in the initial path library by using an evolutionary algorithm, wherein the method comprises the following steps:

step A401, constructing all paths in an initial path library into an evolution database;

step A402, performing basis transformation on each path in the evolutionary library, and when the basis transformation is performed, firstly determining the number of basis transformation grids;

wherein, B_kThe method comprises the steps that base variable data volume of the kth path in an initial path library is obtained, η b is a preset base variable coefficient, the preset value is 0.5-1, min T is the minimum value of required time of all paths in an evolution database, max T is the maximum value of the required time of all paths in the evolution database, and flood is the value rounding in brackets;

BY path_iA change of basis, one value in the path of each change of basis, forms BY_iA plurality of basis variation paths;

calculating the required time corresponding to the base variable paths, and reserving each path and the path corresponding to the minimum required time value in the corresponding base variable paths as new paths so as to construct an alternate evolution database;

step A403, selecting two paths from the alternate evolution database in sequence as ancestor paths, and calculating the number of alternate evolutionary grids according to the ancestor paths;

wherein J is the evolution alternation data volume of the ancestor path, η J is a preset alternation coefficient, the preset value is 0.5 to 1, T max is the maximum value of the required time of the ancestor path, and T min is the minimum value of the required time of the ancestor path;

randomly selecting a grid at a position from the paths of two ancestor paths as an alternate grid, and alternating the continuous J values to form a new ancestor path;

calculating the required time of the ancestor path and the formed descendants, selecting the smaller 3 paths in the required time as paths to be merged into a new population library, and removing the ancestor paths from the alternate evolution database;

step A404, repeating step A403 until the remaining paths in the alternative evolution database are not enough to construct ancestor paths, ending the repeated operation, and calculating the minimum value of the required time of all paths in the new population library as a comparison value;

and step A405, taking the new population library as an evolution database, repeating the steps A402 to A405 until the comparison value is not changed for 10 times continuously, taking the path corresponding to the comparison value as a result path, wherein the comparison value is the time required by the target user from home to office.

The above calculation method is further explained in detail below, specifically as follows:

in this embodiment, when the time required for the target user to travel from home to the office is calculated according to the address and the office address of the target user, an optimal path can be automatically planned and the time corresponding to the optimal path is determined, where the specific steps are as follows:

step A1, constructing a grid map containing the address of the user and the office address, numbering the grid map, marking the grid corresponding to the address of the target user as start, marking the grid of the office address as end, then using the grid of the black grid other than the road, and eliminating the number of the black grid;

in the step A1, when the grids are numbered, the position number marked as start is 1, the grids are sequentially increased toward the position marked as end, the position number marked as end is the maximum value,

for example, when a start is at the lower right corner, the values are sequentially increased to the left by taking the lower left corner as 1, that is, the value of one grid at the right of the start is 2, and so on until the grids in the lowest row are numbered completely, and the grid at the right of the lowest row is numbered as K, the value of the grid in the last row of the start is marked as K +1, and the values are sequentially increased to the left by 1 until the numbering of the position marked as end is completed.

Step A2, constructing an initial path to form an initial path library;

wherein, the step A2 can be embodied as the following steps a201 to a 203:

in step a201, the grid corresponding to start is used as the starting position of motion construction, the grid corresponding to end is continuously moved, and the grid through which the motion passes is reserved, that is, the path constructed during path construction.

Wherein, in the course of the continuous movement, the direction of movement each time is limited to a direction that does not make the distance to the position of the grid marked as end farther;

for example, when start is at the bottom right corner, the direction of motion of each time the path is constructed may be five directions, namely, the left direction and the upward direction may make the distance of the grid obtaining end less by 1, the upper right direction and the lower left direction may make the distance of the grid obtaining end unchanged, and the upper left direction may make the distance of the grid obtaining end less by 2.

Meanwhile, the black grids cannot be accessed in the path construction process,

in step a202, if a dead angle or the like occurs during the movement, the path construction is invalid, and the path construction is restarted from the start;

in step a203, the above steps are repeated until the number of paths in the initial path library reaches a preset value, and the number of the same paths does not exceed two.

Step A3, calculating the time needed by each path in the initial path library;

wherein, T_kThe time required for the kth path in the initial path library, the number of road segments contained in the Nth path, D_k,iDistance, V, of the ith road of the kth path_k,iThe speed of the ith section of the kth path, S the number of the traffic lights needing to pass the kth path, m the number of the traffic lights needing to pass at the current time, Td the average waiting time of the traffic lights, and P_k,iIs the probability of traffic jam occurring on the ith road of the kth path, DY_k,iAverage traffic jam distance VY when traffic jam occurs on the ith section of the kth path_k,iTraffic jam occurs for the ith section of the kth pathAverage running speed of time, i ═ 1, 2, 3.. N;

according to the step A3, the required time of each path can be obtained, and the required time of each path not only considers the distance of the path, but also considers the time required by traffic lights and traffic jam.

And A4, optimizing the paths in the initial path library by using an evolutionary algorithm.

The step a4 can be implemented by the following steps:

in step a401, constructing all paths in the initial path library as an evolutionary database;

in step a402, performing basis transformation on each path in the evolutionary library, and when performing basis transformation, determining the number of basis transformation grids at first;

wherein, B_kThe method comprises the steps that base variable data volume of the kth path in an initial path library is obtained, η b is a preset base variable coefficient, the preset value is 0.5-1, min T is the minimum value of required time of all paths in an evolution database, max T is the maximum value of the required time of all paths in the evolution database, and flood is the value rounding in brackets;

BY path_iA change of basis, one value in the path of each change of basis, forms BY_iA plurality of basis variation paths;

for example, the 3 rd path is start → 2 → 7 → 14 → 36 → 41 → 54 → 69 → end, BY₃At 2, the 3 rd path is base-changed 2 times, the base is changed to a random base change,

the first change to grid 7 becomes base 12, forming start → 2 → 12 → 14 → 36 → 41 → 54 → 69 → end;

the second change of the base of the grid 36 to 30 forms start → 2 → 12 → 14 → 30 → 1 → 54 → 69 → end;

calculating the required time corresponding to the base variable paths, and reserving each path and the path corresponding to the minimum required time value in the corresponding base variable paths as new paths so as to construct an alternate evolution database;

according to the step A402, all paths in the evolution database can be subjected to basis transformation, the number of times of basis transformation is determined according to the required time of the paths each time, when the required time of the paths is longer, the paths are poorer at the moment, the number of times of basis transformation is larger, the selection possibility is increased, and the paths with shorter required time are selected from the paths of basis transformation as new paths, so that the paths are continuously evolved.

In step A403, two paths are selected from the alternative evolution database in sequence as ancestor paths, and the number of the alternative evolutionary grids is calculated according to the ancestor paths;

wherein J is the evolution alternation data volume of the ancestor path, η J is a preset alternation coefficient, the preset value is 0.5 to 1, T max is the maximum value of the required time of the ancestor path, and T min is the minimum value of the required time of the ancestor path;

randomly selecting a grid at a position from the paths of two ancestor paths as an alternate grid, and alternating the continuous J values to form a new ancestor path;

for example, the motion trajectory of the ancestor path is as follows, and J is 2:

ancestor path 1: start → 2 → 5 → 7 → 22 → 36 → 40 → 45 → 66 → end

Ancestor path 2: start → 2 → 3 → 12 → 24 → 36 → 38 → 42 → 77 → end

Selecting the fifth grid as an alternate grid to form 4 new descendant paths;

descendant Path 1: start → 2 → 5 → 12 → 24 → 36 → 40 → 45 → 66 → end

Descendant Path 2: start → 2 → 5 → 7 → 22 → 36 → 38 → 42 → 66 → end

Descendant Path 3: start → 2 → 3 → 7 → 22 → 36 → 38 → 42 → 77 → end

Descendant path 4: start → 2 → 3 → 12 → 24 → 36 → 40 → 45 → 77 → end

Calculating the required time of the ancestor path and the formed descendants, selecting the smaller 3 paths in the required time as paths to be merged into a new population library, and removing the ancestor paths from the alternate evolution database;

according to step a403, all paths in the evolution database can be alternately evolved, the amount of data to be alternated is determined according to the required time of the path each time, when the required time of the path is longer, the path is poorer at this time, and the alternation times during the evolution is more, so that the selection probability is increased, and the path with shorter required time is selected from the paths of the descendants and the ancestors after the evolution to be used as a new path, so that the path is continuously evolved.

In step a404, repeating step a403 until the remaining paths in the alternative evolution database are not enough to construct ancestor paths, ending the repeating operation, and calculating the minimum value of the required time of all paths in the new population library as a comparison value;

in step a405, the new population library is used as the evolution database, and steps a402 to a405 are repeated until the comparison value is not changed for 10 times, the path corresponding to the comparison value at this time is used as the result path, and the comparison value is the time required by the target user from home to the office.

The beneficial effect of above-mentioned technique lies in: by utilizing the technology, the optimal path from the address of the target user to the office address can be intelligently selected according to the address and the office address of the target user, the required time is shortest, the distance of the path is not only considered when the required time is determined, but also traffic lights and traffic jam are considered, the number of the traffic lights, the number of the existing red lights and the average waiting strength are considered when the traffic lights are considered, the traffic jam length is considered when the traffic jam occurs, and the probability of traffic jam is also considered, so that the time consideration is more comprehensive.

In the process, an optimal path is obtained, an evolutionary algorithm is adopted to dynamically determine the base variable data volume and the evolutionary alternative data volume, so that the base variable data volume and the alternative data volume can better adapt to the path, only one position is selected for alternation or evolution each time during alternation and evolution, the process can be simpler, and when a new population library is formed, only 1 path with the minimum required time is selected to enter the population library, but 3 paths are selected, so that more selectable paths are selected, and the condition that a local optimal solution is entered during path planning is avoided.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. An information recommendation method based on the Internet of things is characterized by comprising the following steps:

acquiring user information of a target user, wherein the user information comprises position information and/or behavior information;

determining candidate information in a target area related to the user information based on a positioning technology;

predicting the click rate of the candidate information;

generating a pre-sequencing information set according to the candidate information with high click rate;

performing diversity reordering on the candidate information in the pre-ordering information set according to the context characteristics of the candidate information in the pre-ordering information set to obtain a reordered information set;

and providing information recommendation service for the target user according to the candidate information in the reordering information set.

2. The method of claim 1, wherein determining candidate information within a target area associated with user information based on a location technique comprises:

determining the address and the office address of a target user according to the user information;

calculating the time required by the target user from home to the office according to the address and the office address of the target user;

judging whether the time required by the target user from home to the office is greater than first preset time or not;

when the time required by a target user from home to an office is longer than first preset time, acquiring a target area with the time required for reaching the office of the target user being shorter than second preset time based on a positioning technology;

and acquiring the property information in the target area as candidate information in the target area related to the user information.

3. The method of claim 2, wherein calculating the time required for the target user to travel from home to the office location based on the target user's home address and office address comprises:

planning one or more lines from home to office of the user according to the target user address and the office address;

calculating the time required by the target user from home to the office according to the current road condition of each line and the user trip mode by combining the traffic rule information of the current time;

wherein the current road condition of the line comprises: the number of the traffic lights which need to pass through, the average waiting time of the crossing where each traffic light which needs to pass through is located, and the length of the congested road section, wherein the traffic regulation information at the current time comprises the traffic control condition and the road sealing condition.

4. The method of claim 2, wherein calculating the time required for the target user to travel from home to office based on the target user's home address and office address when the positioning function of the target user's terminal is in an on state comprises:

determining the actual time spent by the target user from the address to the office address according to the change of the positioning information in the target user terminal;

determining the actual time spent as the time required by the target user from an address to an office address.

5. The method of claim 3 or 4, wherein determining the home address and office address of the target subscriber based on the subscriber information comprises:

receiving the input operation of a target user in a user address input box and the input operation of a user office address input box; acquiring an address input by the target user in a user address input box as a user address; acquiring an address input by the target user in a user office address input box as a user office address;

or

Calculating the position of the target user with the longest residence time in a first preset time period and the position of the target user with the longest residence time in a second preset time period according to the positioning information in the terminal of the target user; determining the position of the target user with the longest residence time in a first preset time period as the address of the target user; and determining the position of the target user with the longest residence time in a second preset time period as the office address of the target user.

6. The method of claim 2, wherein pushing property information within the target area to the target user comprises:

acquiring average house price information and house product information in sale in the target area;

pushing the average house price information and the house-in-sale property information in the target area to the target user;

the acquiring of the average house price information in the target area includes:

capturing historical trading prices of houses in the target area within a first preset time period from the internet;

and substituting the historical trading price and the price fluctuation into a preset calculation formula to calculate the average price of the house in the target area at the current time.

7. The method of claim 6, wherein obtaining the in-store property information within the target area comprises:

capturing the in-sale property information in the target area from the Internet, and storing the in-sale property information in the target area captured from the Internet in a local database;

acquiring sensor information in a target property;

judging whether the target property is an in-sale property or not according to the sensor information in the target property;

when the target property is in the state of selling and storing the property, judging whether property information identical to the information of the target property exists in a local database;

and when the local database does not have the information which is the same as the information of the target property, taking the property information of the target property as new in-sale property information and storing the new in-sale property information into the local database.

8. The method of claim 7, wherein determining whether the target property is an on-sale property based on the sensor information in the target property comprises:

acquiring access control information and thermal infrared sensing information of a target property;

counting the home returning times of the user in a second preset time period according to the access control information and counting the total residence time of the user at home according to the thermal infrared sensor information;

and when the home returning times of the user in the second preset time period are less than the preset times and the total residence time of the user at home is less than the first preset time length, determining that the target property is the in-sale property.

9. The method of claim 7, wherein determining whether the target property is an on-sale property based on the sensor information in the target property comprises:

counting the visiting times and visiting time of the visitors of the target property according to a digital image sensor connected with the local place;

calculating the average visiting time of each visitor according to the visiting times and visiting time of the visitors of the target property;

and when the average visiting duration of the visitor is longer than the preset duration of the second preset time, determining that the target house property is the house property in sale.

10. The method of claim 3, wherein the time required for the target user to travel from home to the office is calculated according to:

step A1, constructing a grid map containing the address of the user and the office address, numbering the grid map, marking the grid corresponding to the address of the target user as start, marking the grid of the office address as end, then using the grid of the black grid other than the road, and eliminating the number of the black grid;

step A2, constructing an initial path to form an initial path library;

step A3, calculating the time needed by each path in the initial path library;

wherein, T_kThe time required for the kth path in the initial path library, the number of road segments contained in the Nth path, D_k,iDistance, V, of the ith road of the kth path_k,iThe speed of the ith section of the kth path, S the number of the traffic lights needing to pass the kth path, m the number of the traffic lights needing to pass at the current time, Td the average waiting time of the traffic lights, and P_k,iIs the probability of traffic jam occurring on the ith road of the kth path, DY_k,iAverage traffic jam distance VY when traffic jam occurs on the ith section of the kth path_k,iThe average running speed is the average running speed when the traffic jam occurs on the ith section of the kth path, wherein i is 1, 2 and 3.. N;

step A4, optimizing the paths in the initial path library by using an evolutionary algorithm, wherein the method comprises the following steps:

step A401, constructing all paths in an initial path library into an evolution database;

step A402, performing basis transformation on each path in the evolutionary library, and when the basis transformation is performed, firstly determining the number of basis transformation grids;

wherein, B_kThe method comprises the steps that base variable data volume of the kth path in an initial path library is obtained, η b is a preset base variable coefficient, the preset value is 0.5-1, min T is the minimum value of required time of all paths in an evolution database, max T is the maximum value of the required time of all paths in the evolution database, and flood is the value rounding in brackets;

BY path_iA change of basis, one value in the path of each change of basis, forms BY_iA plurality of basis variation paths;

calculating the required time corresponding to the base variable paths, and reserving each path and the path corresponding to the minimum required time value in the corresponding base variable paths as new paths so as to construct an alternate evolution database;

step A403, selecting two paths from the alternate evolution database in sequence as ancestor paths, and calculating the number of alternate evolutionary grids according to the ancestor paths;

wherein J is the evolution alternation data volume of the ancestor path, η J is a preset alternation coefficient, the preset value is 0.5 to 1, Tmax is the maximum value of the required time of the ancestor path, and Tmin is the minimum value of the required time of the ancestor path;

randomly selecting a grid at a position from the paths of two ancestor paths as an alternate grid, and alternating the continuous J values to form a new ancestor path;

calculating the required time of the ancestor path and the formed descendants, selecting the smaller 3 paths in the required time as paths to be merged into a new population library, and removing the ancestor paths from the alternate evolution database;

step A404, repeating step A403 until the remaining paths in the alternative evolution database are not enough to construct ancestor paths, ending the repeated operation, and calculating the minimum value of the required time of all paths in the new population library as a comparison value;

and step A405, taking the new population library as an evolution database, repeating the steps A402 to A405 until the comparison value is not changed for 10 times continuously, taking the path corresponding to the comparison value as a result path, wherein the comparison value is the time required by the target user from home to office.

Images