CN114429371B

CN114429371B - Unmanned vehicle-based commodity marketing method and device, electronic equipment and storage medium

Info

Publication number: CN114429371B
Application number: CN202210353051.7A
Authority: CN
Inventors: 李俊宁
Original assignee: Neolix Technologies Co Ltd
Current assignee: Neolithic Unmanned Vehicle Songyang Co ltd
Priority date: 2022-04-06
Filing date: 2022-04-06
Publication date: 2022-06-28
Anticipated expiration: 2042-04-06
Also published as: CN114429371A

Abstract

The disclosure relates to the technical field of unmanned selling, and provides a commodity marketing method and device based on an unmanned vehicle, electronic equipment and a storage medium. The method comprises the following steps: the method comprises the steps of obtaining a commodity marketing task, wherein the commodity marketing task comprises commodity label information and marketing indexes of a commodity to be marketed; determining a target unmanned vehicle corresponding to a marketing index, and calling a user data pool associated with the target unmanned vehicle, wherein the user data pool comprises a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user; matching the commodity label information with the user label information to obtain a matching result; and determining a target user according to the matching result, and pushing the sales information of the commodity to be marketed to the target user. The method and the system can actively and accurately identify the purchasing demand of the user, and are favorable for improving the success rate of commodity transaction and further popularizing the marketing mode of unmanned vehicle selling.

Description

Unmanned vehicle-based commodity marketing method and device, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of unmanned sale, in particular to a commodity marketing method and device based on an unmanned vehicle, electronic equipment and a storage medium.

Background

With the continuous development of artificial intelligence technology, the artificial intelligence technology has been pervasively applied to a plurality of application fields, for example, the field of unmanned vending, etc.

In recent years, a research of "unmanned selling mode" has been trended in the commercial product selling industry. However, in the current unmanned selling mode, for example, the selling modes of commodities such as an unmanned supermarket, an unmanned selling cabinet, an unmanned vehicle and the like are still passive selling modes of "static state". That is, what commodity the user needs to buy needs to go to an unmanned supermarket or an unmanned selling cabinet, and then selects and purchases the commodity of the user's own desire. Such a sales model cannot identify the purchasing demand of the user "actively" and precisely, and thus the success rate of the transaction of the goods is not high.

Therefore, the existing unmanned selling mode still has the purchase demand that the user cannot be actively and accurately identified, so that the commodity transaction success rate is low, and the unmanned selling mode is greatly limited in further deep popularization and application.

Disclosure of Invention

In view of this, embodiments of the present disclosure provide a method and an apparatus for merchandise marketing based on an unmanned vehicle, an electronic device, and a storage medium, so as to solve the problem that the existing unmanned selling mode still has a purchase demand that cannot actively and accurately identify a user, which results in a low success rate of merchandise transaction, and the unmanned selling mode is greatly limited in further deep popularization and application.

In a first aspect of the disclosed embodiments, a commodity marketing method based on an unmanned vehicle is provided, which includes:

the method comprises the steps of obtaining a commodity marketing task, wherein the commodity marketing task comprises commodity label information and marketing indexes of a commodity to be marketed;

determining a target unmanned vehicle corresponding to a marketing index, and calling a user data pool having a relationship with the target unmanned vehicle, wherein the user data pool comprises a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user;

matching the commodity label information with the user label information according to a preset label matching strategy to obtain a matching result;

and determining a plurality of target users according to the matching result, and pushing the sales information of the commodity to be marketed to each target user.

In a second aspect of the embodiments of the present disclosure, there is provided an unmanned vehicle-based commodity marketing device, including:

the task acquisition module is configured to acquire a commodity marketing task, and the commodity marketing task comprises commodity label information and a marketing index of a commodity to be marketed;

the system comprises a determining module, a processing module and a processing module, wherein the determining module is configured to determine a target unmanned vehicle corresponding to a marketing index, and call a user data pool having a correlation with the target unmanned vehicle, the user data pool comprises a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user;

the matching module is configured to match the commodity label information with the user label information according to a preset label matching strategy to obtain a matching result;

and the pushing module is configured to determine a plurality of target users according to the matching result, and push the sales information of the commodity to be marketed to each target user.

In a third aspect of the embodiments of the present disclosure, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.

In a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, in which a computer program is stored, which when executed by a processor implements the steps of the above-mentioned method.

Compared with the prior art, the beneficial effects of the embodiment of the disclosure at least comprise: the method comprises the steps that a commodity marketing task is obtained, wherein the commodity marketing task comprises commodity label information and marketing indexes of a commodity to be marketed; determining a target unmanned vehicle corresponding to a marketing index, calling a user data pool having a relationship with the target unmanned vehicle, wherein the user data pool comprises a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user; matching the commodity label information with the user label information according to a preset label matching strategy to obtain a matching result; according to the matching result, a plurality of target users are determined, the sales information of the commodity to be sold is pushed to each target user, the purchase demand of the user can be identified actively and accurately, the success rate of commodity transaction is improved, and meanwhile, the marketing mode of unmanned selling is further promoted deeply.

Drawings

To more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without inventive efforts.

FIG. 1 is a scenario diagram of an application scenario in accordance with an embodiment of the present disclosure;

FIG. 2 is a schematic flow chart diagram of a method for unmanned vehicle based merchandise marketing provided by an embodiment of the present disclosure;

FIG. 3 is a diagram of a user data pool in unmanned vehicle-based merchandise marketing provided by an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an unmanned vehicle-based commodity marketing device according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the disclosed embodiments. However, it will be apparent to one skilled in the art that the present disclosure may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.

Hereinafter, a method and an apparatus for unmanned vehicle based merchandise marketing according to an embodiment of the present disclosure will be described in detail with reference to the accompanying drawings.

Fig. 1 is a scene schematic diagram of an application scenario according to an embodiment of the present disclosure. The application scenario may include an unmanned vehicle 101, a client 102, a remote control 103, and a network 104.

The unmanned vehicle 101 may be a mobile vehicle integrated with a camera device (e.g., a camera), a communication device, a positioning device (e.g., GPS, etc.), and the like. The unmanned vehicle 101 may establish a communication connection with the remote control terminal 103 through the network 104.

The remote control terminal 103 may be a server providing various services, for example, a backend server receiving data sent by the unmanned vehicle with which a communication connection is established, and the backend server may receive, analyze and otherwise process the data sent by the unmanned vehicle and generate a processing result. The server may be one server, may also be a server cluster composed of a plurality of servers, or may also be a cloud computing service center, which is not limited in this disclosure.

The server may be hardware or software. When the server is hardware, it may be various electronic devices that provide various services to the unmanned vehicle. When the server is software, it may be a plurality of software or software modules for providing various services for the unmanned vehicle 101, or may be a single software or software module for providing various services for the unmanned vehicle 101, which is not limited by the embodiment of the present disclosure.

The client 102 may be a terminal device used by a user (e.g., a customer), and the terminal device may be hardware or software. When the terminal device is hardware, it may be various electronic devices having a display screen and supporting communication with the unmanned vehicle, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like; when the terminal device is software, it may be installed in the electronic device as above. The terminal device may be implemented as a plurality of software or software modules, or may be implemented as a single software or software module, which is not limited in the embodiments of the present disclosure. Further, various applications, such as a data processing application, an instant messaging tool, social platform software, a search application, a shopping application, and the like, may be installed on the terminal device.

The network 104 may be a wired network connected by a coaxial cable, a twisted pair cable and an optical fiber, or may be a wireless network that can interconnect various Communication devices without wiring, for example, Bluetooth (Bluetooth), Near Field Communication (NFC), Infrared (Infrared), and the like, which is not limited in the embodiment of the present disclosure.

The remote control terminal 103 may establish a communication connection with the unmanned vehicle 101 through the network 104 to receive or transmit information or the like. Specifically, when a commodity marketing task is obtained, the remote control end 103 determines a target unmanned vehicle corresponding to the marketing index, and calls a user data pool having a relationship with the target unmanned vehicle, where the user data pool includes a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user; further, matching the commodity label information with the user label information according to a preset label matching strategy to obtain a matching result; and then according to the matching result, a plurality of target users are determined, the sales information of the commodity to be marketed is pushed to each target user, the purchase demand of the user can be actively and accurately identified, the success rate of commodity transaction is favorably improved, and meanwhile, the marketing mode of unmanned selling is favorably further deeply popularized.

It should be noted that specific types, numbers and combinations of the unmanned vehicles 101, the client 102, the remote control terminal 103 and the network 104 may be adjusted according to actual requirements of an application scenario, and the embodiment of the disclosure does not limit this.

Fig. 2 is a schematic flow chart of a commodity marketing method based on unmanned vehicles according to an embodiment of the present disclosure. The unmanned vehicle-based merchandise marketing method of fig. 2 may be performed by the remote control terminal 103 of fig. 1. As shown in fig. 2, the unmanned vehicle-based commodity marketing method includes:

step S201, a commodity marketing task is obtained, wherein the commodity marketing task comprises commodity label information and marketing indexes of a commodity to be marketed.

The goods to be marketed can be various goods (goods), including but not limited to food (such as vegetables, fruits, fast food, etc.), daily sundries (such as paper towels), electric appliances (such as various mobile phone accessories, etc.), office supplies (such as pens, ink, paper, etc.).

The commodity label information can endow different commodity labels to various commodities according to the commodity attributes of the commodities to be marketed. In an example, taking the article to be marketed as fast food a as an example, first, the article label information of "brand merchants" (e.g., baishou, kendyn, etc. brand merchants) or "non-brand merchants" can be printed on the fast food a according to whether the supplier of the article is a brand merchant. Secondly, the fast food A can be labeled with the corresponding cuisine according to the cuisine, for example, if the fast food A is of the Sichuan cuisine, the fast food A can be labeled with the 'Sichuan cuisine'. Thirdly, the fast food A can be labeled with corresponding food materials according to the types of the food materials, for example, the main food material of the fast food A is beef, and then the fast food A can be labeled with beef. Fourthly, the product to be marketed can be labeled according to the product name (such as the product A) of the product to be marketed and the marketing target object (such as the age below 20 years).

It should be noted that the specific form and content of the product label information can be flexibly set according to the actual situation, and are not specifically limited in this disclosure.

The marketing index generally refers to a marketing target which is pre-established for the commodity to be marketed, and includes but is not limited to marketing amount, marketing target object, selling time period and the like. For example, if the product to be marketed is chicken fast food of a certain brand of commercial tenant, the marketing target is set in advance to be not less than 300 shares of daily sales, that is, the marketing index of the product to be marketed is "no less than 300 shares of daily sales".

In an embodiment, the obtaining of the commodity marketing task may be that a merchant achieves certain marketing cooperation with an unmanned vehicle operator, and the merchant performs a marketing task on a commodity to be marketed provided by the unmanned vehicle operator. At the moment, the unmanned vehicle operator can input the marketing task into the remote control end, and the remote control end can obtain the commodity marketing task. Or, the merchant directly issues the commodity marketing task to the remote control end, and the remote control end can obtain the corresponding commodity marketing task. The goods marketing task may also include merchant information (such as merchant name, merchant ID, etc.), etc.

Step S202, a target unmanned vehicle corresponding to the marketing index is determined, a user data pool having a relation with the target unmanned vehicle is called, the user data pool comprises a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user.

In practical application, each unmanned vehicle correspondingly serves a planning area (such as an XX community, an XX garden and the like), and one unmanned vehicle corresponds to one user data pool and is used for storing some user data received/acquired by the unmanned vehicle in a selling process of the unmanned vehicle. These user data include, but are not limited to, behavioral data, transactional data, demographic data, generic data of users who purchase goods online through the unmanned vehicle APP or directly on-site in the unmanned vehicle.

Referring to fig. 3, one unmanned vehicle corresponds to one user data pool 301, one user data pool includes a plurality of user data clusters 302, each user data cluster includes a plurality of user tag data sets 303, one user tag data set corresponds to N users (N is a positive integer greater than or equal to 1), and user tag information corresponding to each user.

The user tag information includes, but is not limited to, a user name, an age, facial features, a web browsing log, a product purchase record (e.g., purchase behavior (e.g., purchase 2 or more items of a product), a purchase period, a repeated purchase frequency (e.g., repeated purchase of 2 or more items), and the like), a gender, a occupation, an income status, and the like. The user tag information is a series of related information which can be directly or indirectly acquired by the unmanned vehicle when the user uses an application program (APP) related to shopping with the unmanned vehicle or interacts with the unmanned vehicle in the shopping process.

And step S203, matching the commodity label information with the user label information according to a preset label matching strategy to obtain a matching result.

The tag matching strategy is a matching rule for matching the commodity tag information with the user tag information. Specifically, the matching rule may be a one-dimensional matching rule, for example, the tag information of the product is a product to be marketed of chicken fast food, and the tag information of the user matched with the product may be the age below 20 years. Or a multidimensional matching rule, for example, the product label is a product to be marketed of chicken fast food, the matched user label information can be 20-30 years old, and the monthly income is not less than 5000 yuan.

The matching result indicates the matching degree between the product tag information and the user tag information, for example, complete matching (100%), no matching (0%), incomplete matching (0% -100%, excluding two end points).

And S204, determining a plurality of target users according to the matching result, and pushing the sales information of the commodity to be marketed to each target user.

In an embodiment, a matching threshold may be preset, the matching result of the user tag information and the commodity tag information of each user is compared with the matching threshold, and if the matching result is greater than or equal to the matching threshold, the user may be determined as the target user. For example, if the matching threshold is 60%, the user tag information of the user a is the chicken snack, the commodity tag information is the chicken snack, and the matching result is 100% (more than 60% of the matching threshold), the user a can be determined as the target user.

The sales information may be information on a sales price, a food material, a supplier, a supply period, and the like of the item to be marketed. In an application example, 24 hours a day can be divided into 24 time periods according to the granularity of 1 hour, wherein 0 hour to 1 hour are the first time period, 1 hour to 2 hours are the second time period, and 2 hours to 3 hours are the third time period. Wherein the provision period may be one or more periods thereof.

By pushing the sales information of the commodity to be marketed to the target user, the target user can be helped to quickly know the relevant information of the commodity to be marketed, the purchase desire of the target user is stimulated, and the success rate of transaction is improved.

According to the technical scheme provided by the embodiment of the disclosure, a commodity marketing task is obtained, wherein the commodity marketing task comprises commodity label information and marketing indexes of a commodity to be marketed; determining a target unmanned vehicle corresponding to a marketing index, calling a user data pool having a relationship with the target unmanned vehicle, wherein the user data pool comprises a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user; matching the commodity label information with the user label information according to a preset label matching strategy to obtain a matching result; according to the matching result, a plurality of target users are determined, the sales information of the commodity to be sold is pushed to each target user, the purchase demand of the user can be identified actively and accurately, the success rate of commodity transaction is improved, and meanwhile, the marketing mode of unmanned selling is further promoted deeply.

In some embodiments, the marketing index includes a projected marketing volume and an index projected completion time. Determining a target unmanned vehicle corresponding to a marketing index, comprising:

determining at least one selling period and a patrol selling area corresponding to each selling period according to the planned marketing amount and the index predicted completion time;

and determining the target unmanned vehicle according to the patrol selling area.

The planned sales volume refers to the planned sales volume of the commodity to be marketed. For example, the product to be marketed is chicken fast food, and the planned marketing amount can be 300 portions, 400 portions and the like. In practical applications, the projected sales volume may be determined (contracted) by the unmanned vehicle operator and the merchant specific volume.

The index estimated completion time is an estimated time required for completing the planned sales volume. The predicted completion time of the index can be flexibly set according to actual conditions, for example, the planned marketing amount is 300 shares of chicken fast food, and the predicted required time can be 1 day, 2 days or 3 days.

The selling time period refers to the time period for selling the commodity to be marketed. I.e., the period of time during which the service of selling the item to be marketed is provided. Specifically, the selling period is determined according to the planned marketing amount and the index expected completion time of the commodity to be marketed. For example, if the planned marketing amount is 300, and the index predicted completion time is 1 day, then the historical purchase period during which the user purchases the to-be-marketed goods (or purchases the substitute goods of the to-be-marketed goods) in the user data pool can be called to analyze, in which period or periods the user concentrates on purchasing the goods, and meanwhile, the marketing amount estimated value which can be achieved by the goods in each purchase period can be predicted by analyzing the purchase amount of the goods purchased by the user in the user data pool. Therefore, the marketing amount of 300 copies to be completed in 1 day can be estimated, and the marketing amount of 300 copies needs to be distributed to several selling periods, and the marketing amount reaching the standard of each selling period is the number of the marketing amount. The sum of the up-to-standard marketing and sales volumes corresponding to each selling period is not lower than the planned marketing and sales volume.

And (4) patrolling the selling area, and further determining the area in which unmanned vehicle patrolling selling needs to be carried out to finish the planned selling amount within the predicted completion time by analyzing the number of users who will purchase the to-be-marketed commodity (or purchase a substitute commodity of the to-be-marketed commodity) in the purchase period and the purchase quantity in the user data pool. The map may be divided into a plurality of areas according to a certain area division rule (for example, divided according to the area size), and each area may correspond to a patrol vending service for allocating an unmanned vehicle to the area.

In practical applications, considering factors such as patrol traffic cost and convenience of commodity supply, generally, one patrol selling area is allocated with one unmanned vehicle to take charge of patrol selling services of commodities in the area. In a special case, if the sales volume of the patrol sales area corresponding to one sales period is large, at least two unmanned vehicles may be required to be responsible for the sales service of the patrol sales area. The region may also be subdivided.

As an example, suppose the item to be marketed is a chicken snack provided by a brand of Merchant A with a projected marketing amount of 300 and an index projected completion time of 20XX years X month X days, i.e., 1 day. The granularity can be divided into 24 time intervals by dividing 24 hours a day into 24 time intervals according to 1 hour, wherein 0-1 time interval is a first time interval, 1-2 time intervals are a second time interval, and 2-3 time intervals are third time intervals. According to data analysis, the number of users purchasing the commodities is the largest in three time periods of 12 hours to 13 hours, 15 hours to 16 hours and 18 hours to 19 hours, the purchase number is the largest, and the historical sales number in the three time periods is not lower than 300 points. Therefore, the selling period may be determined as the three periods. Further analysis shows that the areas a and b correspond to patrol sale areas from 12 hours to 13 hours, the areas b and c correspond to patrol sale areas from 15 hours to 16 hours, and the areas a, b and c correspond to patrol sale areas from 18 hours to 19 hours. Further, the unmanned vehicles 01, 02, 03 corresponding to the areas a (corresponding unmanned vehicles 01), b (corresponding unmanned vehicles 02), c (corresponding unmanned vehicles 03) may be determined as target unmanned vehicles.

In some embodiments, the step S203 includes:

screening out a target user data cluster with the highest association degree with the commodity label information from the user data pool;

respectively calculating a correlation value between each user tag data set and the commodity tag information in the target user data cluster;

according to the relevance value, screening out a target user tag data set with the highest relevance value from a plurality of user tag data sets in the target user data cluster;

and matching the commodity label information with the user label information of each user in the target user label data set to obtain a matching result.

Suppose that one unmanned vehicle corresponds to one user data pool, and one user data pool comprises a behavior data cluster, a transaction data cluster, a crowd data cluster and a general data cluster, and the total number of the four user data clusters is four. The behavior data cluster comprises a webpage (commodity) browsing behavior tag data set, a purchasing behavior tag data set, a payment behavior tag data set, a purchasing time period tag data set and a repeated purchasing frequency tag data set. The webpage (commodity) browsing behavior tag data set comprises a plurality of users and webpage (commodity) browsing behavior tag information corresponding to each user. It can be understood that the purchase behavior tag data set includes a plurality of users and purchase behavior tag information corresponding to each user (for example, purchase X-pieces of a certain item, etc.). The payment behavior tag data set comprises a plurality of users and payment behavior tag information corresponding to each user (for example, x-element payment is performed by a WeChat/Payment treasure/Bank card and the like when a certain commodity is purchased).

The transaction data cluster comprises a user quantity tag data set (such as how many users purchased and browsed each commodity, etc.), a consumption capacity tag data set (the consumption capacity of each user can be obtained through statistics according to the historical payment behaviors of the user), a commodity preference tag data set (the commodity preference of each user can be obtained through analysis according to the data of the frequency of repeated purchases and the purchasing behavior of the user), and a category preference tag data set (the category preference of each user can be obtained through analysis according to the data of the browsing behaviors, the frequency of repeated purchases and the purchasing behavior of the user). The crowd data set includes a gender distribution tag data set (e.g., a user is a male or a female), an occupation distribution tag data set (e.g., white collar, blue collar, etc.), an age distribution tag data set (which may be an estimated age value obtained by acquiring a facial image of the user through a camera of an unmanned vehicle during interaction between the user and the unmanned vehicle and performing age analysis on the facial image, or an age value entered by the user through a terminal device at registration of an APP or the like), a marital status tag data set (which may be an estimated value according to the age and occupation of the user, for example, if the user is a 35-year-old white collar, the marital status may be estimated to be married), an income status tag data set (which may be an estimated value according to an office area where the user is located and the occupation, for example, if the user is a blue collar at business building X office, then the calculated average monthly income for the blue collar of the commercial building can be taken as the monthly average income label value for the user). The general data cluster comprises a population quantity tag data set (the population quantity refers to the quantity of population registered by a person making mouth in a certain business circle or area or the average floating population quantity determined according to the historical floating population quantity), a geographic position tag data set (the geographic position can refer to the position of a user end collected when a user browses an unmanned vehicle shopping APP, and also can refer to the position of the unmanned vehicle when the user buys goods on site in the unmanned vehicle), a policy control tag data set (different areas generally have different sale policies and the like), a commuting period tag data set and an affiliated business circle tag data set (the affiliated business circle is the business circle to which the position of the user when shopping).

As an example, assuming that the article to be marketed is a toy K of a certain brand of business a, and the main marketing target object thereof is a user under the age of 20, the article tag information of the toy K may be set to "business a, toy K, user under the age of 20". Further, a user data cluster with the highest association degree with "merchant a, toy K, user under 20 years old" may be screened out from the user data pool as a target user data cluster. Accordingly, it may be determined that the user data cluster having the highest degree of association with the item tag information is a crowd data cluster, and then the crowd data cluster may be determined as a target user data cluster.

Next, association values between the gender distribution tag data set, the occupation distribution tag data set, the age distribution tag data set, the marital status tag data set, and the income status tag data set in the crowd data cluster and the commodity tag information "merchant a, toy K, user under age 20" are respectively calculated.

Assume that the correlation calculation result is: the association degree between the gender distribution tag data set and the product tag information is y1, the association degree between the occupation distribution tag data set and the product tag information is y2, the association degree between the age distribution tag data set and the product tag information is y3, the association degree between the marital status tag data set and the product tag information is y4, and the association degree between the income status tag data set and the product tag information is y 5. If the highest degree of association with the above-mentioned item tag information is y3, the age distribution tag data set may be determined as the target user tag data set.

Then, the product label information is matched with the user label information (age label information) of each user in the age distribution label data set to obtain a matching result.

In other embodiments, step S203 includes:

distributing an associated weight value for each user data cluster in a user data pool which has an associated relation with the target unmanned vehicle according to the commodity label information;

calculating a matching value between the user tag information and the commodity tag information of each user in each user tag data set in each user data cluster according to the associated weight value distributed to each user data cluster;

and overlapping the matching values belonging to the same user to obtain a matching result between the user label information and the commodity label information of each user.

In connection with the above example, assuming that the determined target unmanned vehicle is unmanned vehicle 01 and the merchandise tag information is "merchant a, toy K, user under age 20", an associated weight value W1 (corresponding to the behavioral data cluster), W2 (corresponding to the transactional data cluster), W3 (corresponding to the crowd data cluster), and W4 (corresponding to the general data cluster) may be respectively assigned to the behavioral data cluster, the transaction data cluster, the crowd data cluster, and the general data cluster in the user data pool corresponding to unmanned vehicle 01.

And calculating a matching value between the user tag information and the commodity tag information of each user in each user tag data set in each user data cluster according to the associated weight value distributed to each user data cluster. Taking the crowd data cluster as an example, the matching degree between the user tag information of each user in the gender distribution tag data set, the occupation distribution tag data set, the age distribution tag data set, the marital status tag data set and the income status tag data set in the crowd data cluster and the commodity tag information "merchant a, toy K, user under the age of 20" may be calculated respectively, and then multiplied by the associated weight value W3. Taking the age distribution label data set as an example, the matching degree between the age label information of each user and the commodity label information in the age distribution label data set is calculated, and then the matching degree is multiplied by W3, so that the matching value between the age label information of the user and the commodity label information can be obtained. For example, there are 5 users in the age distribution label data set, which are users 01, 02, 03, 04, and 05, where the age label information corresponding to each user is Q1, Q2, Q3, Q4, and Q5. For example, if the matching degree between Q1 and the above item tag information "merchant a, toy K, user under the age of 20" is calculated as E1, then E1 × W3 is the matching value between the age tag information of the user 01 and the item tag information.

Similarly, for the calculation manner of the matching value between the user tag information and the article tag information of each user in the gender distribution tag data set, the occupation distribution tag data set, the marital status tag data set, and the income status tag data set, reference may be made to the calculation manner of the matching value between the user tag information and the article tag information of each user in the age distribution tag data set, which is not described in detail herein.

As an example, the matching values belonging to the same user are superimposed to obtain a matching result corresponding to each user. Assuming that the matching value between the gender tag of the user 01 and the merchandise tag is a 1W 3, the matching value between the occupation tag and the merchandise tag is B1W 3, the matching value between the marital status tag and the merchandise tag is C1W 3, the matching value between the income status tag and the merchandise tag is D1W 3, and the matching value between the age tag and the merchandise tag is E1W 3, a 1W 3+ B1W 3+ C1W 3+ D1W 3+ E1W 3 is the matching value between the crowd data of the user 01 and the merchandise tag value. Further, according to the above manner, the matching value between the behavior data, transaction data, general data of the user 01 and the article tag can be further calculated. Finally, the matching value between the crowd data of the user 01 and the commodity label value, the matching value between the behavior data and the commodity label value, the matching value between the transaction data and the commodity label value, and the matching value between the general data and the commodity label are superposed, so that the matching result between the user label information of the user 01 and the commodity label information can be obtained.

In the embodiment of the disclosure, according to the relevance degree of the commodity label information and each user data cluster in the user data pool, a relevance weight value is allocated to each user data cluster, the matching value between the user label information and the commodity label information of each user in each user label data set in each user data cluster is calculated, and then the matching values belonging to the same user are superposed to obtain the matching result between the user label information and the commodity label information of each user, so that the commodity purchasing demand of each user can be identified more accurately, and thus the target user of the commodity to be marketed can be locked more accurately, which is beneficial to realizing more accurate commodity marketing and improving the marketing transaction success rate.

In some embodiments, the user data pool includes a first user data cluster, a second user data cluster, a third user data cluster, and a fourth user data cluster. The step S203 includes:

according to the commodity label information, distributing a first weight value for a first user data cluster, distributing a second weight value for a second user data cluster, distributing a third weight value for a third user data cluster, and distributing a fourth weight value for a fourth user data cluster;

According to the commodity label information, a first matching weight value is distributed to each user label data set in a first user data cluster, a second matching weight value is distributed to each user label data set in a second user data cluster, a third matching weight value is distributed to each user label data set in a third user data cluster, and a fourth matching weight value is distributed to each user label data set in a fourth user data cluster;

calculating a matching value between the user tag information and the commodity tag information of each user in each user tag data set in each user data cluster based on the first weight value, the second weight value, the third weight value, the fourth weight value, the first matching weight, the second matching weight, the third matching weight and the fourth matching weight;

and superposing the matching values of the same commodity belonging to the same user to obtain the matching result corresponding to each user.

The first user data cluster refers to the aforementioned behavior data cluster. The second user data cluster refers to the aforementioned transaction data cluster. The third user data cluster refers to the aforementioned crowd data cluster. The fourth user data cluster refers to the aforementioned generic data cluster.

In an embodiment, according to the commodity label information, a first weight value W1 is assigned to the first user data cluster, a second weight value W2 is assigned to the second user data cluster, a third weight value W3 is assigned to the third user data cluster, and a fourth weight value W4 is assigned to the fourth user data cluster.

And allocating a first matching weight value to each user tag data set in the first user data cluster according to the commodity tag information. Specifically, a first matching weight value may be assigned to each of the webpage (commodity) browsing behavior tag data sets, the purchase adding behavior tag data sets, the payment behavior tag data sets, the purchase time period tag data sets, and the repeated purchase frequency tag data sets in the behavior data cluster according to the association degree between each data set and the commodity tag. For example, a first matching weight value S1 is assigned to the web page (commodity) browsing behavior tag data set, a first matching weight value S2 is assigned to the purchasing behavior tag data set, a first matching weight value S3 is assigned to the payment behavior tag data set, a first matching weight value S4 is assigned to the purchasing time slot tag data set, and a first matching weight value S5 is assigned to the repeated purchasing frequency tag data set.

Similarly, a second matching weight value may be assigned to each user tag data set in the second user data cluster according to the commodity tag information, a third matching weight value may be assigned to each user tag data set in the third user data cluster, and a fourth matching weight value may be assigned to each user tag data set in the fourth user data cluster.

In some embodiments, calculating a matching value between the user tag information and the item tag information of each user in each user tag data set in each user data cluster based on the first weight value, the second weight value, the third weight value, the fourth weight value, the first matching weight, the second matching weight, the third matching weight, and the fourth matching weight includes:

calculating a first matching value between the user tag information and the commodity tag information of each user in each user tag data set in the first user data cluster according to the first weight value and the first matching weight value;

calculating a second matching value between the user tag information and the commodity tag information of each user in each user tag data set in the second user data cluster according to the second weight value and the second matching weight value;

Calculating a third matching value between the user tag information and the commodity tag information of each user in each user tag data set in a third user data cluster according to the third weight value and the third matching weight value;

according to the fourth weight value and the fourth matching weight value, a fourth matching value between the user tag information and the commodity tag information of each user in each user tag data set in the fourth user data cluster is calculated;

superposing the matching values belonging to the same user to obtain a matching result corresponding to each user, wherein the steps comprise:

and superposing the first matching value, the second matching value, the third matching value and the fourth matching value to obtain a matching result.

As an example, it is assumed that the web page (product) browsing behavior tag data set, the purchasing behavior tag data set, the payment behavior tag data set, the purchasing period tag data set, and the repeated purchasing frequency tag data set in the first user data cluster each include user tag information of a plurality of users. A specific list of user tag information is shown in table 1 below.

TABLE 1 user tag information List for first user data Cluster

For example, it is assumed that the first time of browsing the article a by the user a is 30 seconds, and the second time of browsing the article a by the user a is 10 seconds; 5 commodities a are purchased for the first time, and 1 commodity a is purchased for the second time; the purchase time period for purchasing the commodity a for the first time is 10-11 hours, and the purchase time period for purchasing the commodity a for the second time is 15-16 hours; the purchase of the article a was repeated 2 times. The user tag information of user A may be collated into a tag list as shown in Table 2 below.

Table 2 user tag information list of user a

As an example, assuming that the article tag information is "article a, selling time interval 9-10 hours, retail price y yuan", in combination with table 2 above, the first matching value of user a may be calculated by the following steps:

firstly, a matching value N1 between a webpage (commodity) browsing behavior tag of the user A and the commodity tag information is calculated, and then N1 is multiplied by a first matching weight value S1, so that a matching value N1 × S1 is obtained. And calculating a matching value N2 between the purchase behavior tag of the user A and the commodity tag information, and multiplying N2 by a second matching weight value S2 to obtain a matching value N2 × S2. And calculating a matching value N3 between the payment behavior tag of the user A and the commodity tag information, and multiplying N3 by a third matching weight value S3 to obtain a matching value N3 × S3. And calculating a matching value N4 between the purchasing time interval label of the user A and the commodity label information, and multiplying N4 by a fourth matching weight value S4 to obtain a matching value N4 × S4. And calculating a matching value N5 between the repeated purchase frequency label of the user A and the commodity label information, and multiplying N5 by a fifth matching weight value S5 to obtain a matching value N5 × S5. Then, the matching value N1 × S1, the matching value N2 × S2, the matching value N3 × S3, the matching value N4 × S4, and the matching value N5 × S5 are superimposed to obtain a first matching value (i.e., N1 × S1+ N2 × S2+ N3S 3+ N4 × S4+ N5 × S5).

Similarly, the calculation method for the second matching value, the third matching value and the fourth matching value may refer to the calculation method for the first matching value, and will not be described herein again. And finally, overlapping the first matching value, the second matching value, the third matching value and the fourth matching value of the same commodity belonging to the same user to obtain a matching result between the user label information and the commodity label information of the user.

In the embodiment of the disclosure, different weight values or matching weight values are allocated to different user data clusters in the user data pool and each user tag data set in each user data cluster according to the commodity tags, so that the commodity purchasing demand of each user can be identified more accurately, a target user of a commodity to be marketed can be locked more accurately, more accurate commodity marketing is facilitated, and the marketing transaction success rate is improved.

In some embodiments, the above method further comprises:

receiving an unmanned vehicle position query request sent by a target user, wherein the unmanned vehicle position query request comprises current position information of the target user;

acquiring real-time position information of the target unmanned vehicle, and calculating a dynamic distance value between the target unmanned vehicle and a target user according to the real-time position information and the current position information;

Calculating the arrival time of the position where the target user is located according to the dynamic distance value and the running speed of the target unmanned vehicle;

and generating a dynamic moving route change diagram according to the dynamic distance value and the arrival time, and pushing the dynamic moving route change diagram to a target user.

As an example, the target user may send an unmanned vehicle location query request to the remote control through the terminal device. After receiving the request, the remote control end can send a position acquisition request to the target unmanned vehicle, so that the target unmanned vehicle starts a preset position acquisition device (such as a GPS) to acquire and report real-time position information of the target unmanned vehicle. The remote control terminal can further calculate a dynamic distance value between the real-time position information of the target unmanned vehicle and the current position information of the target user according to the real-time position information of the target unmanned vehicle and the current position information of the target user after receiving the real-time position information reported by the target unmanned vehicle. Since both the targeted drone vehicle and/or targeted user may be able to move their current location before the encounter. For example, the target unmanned vehicle is moving in real time, and the target user may be moving to the location of the target unmanned vehicle. Therefore, the arrival time of the target unmanned vehicle at the position of the target user is calculated by calculating the dynamic distance value between the target unmanned vehicle and according to the dynamic distance value and the driving speed of the target unmanned vehicle. Furthermore, a dynamic moving route change diagram is generated according to the dynamic distance value and the arrival time and is pushed to the target user, so that the target user can visually see the current position, the driving direction, the approximate time for arrival and other information of the target unmanned vehicle, the arrival time of the target unmanned vehicle can be avoided from missing, and the user experience is improved.

All the above optional technical solutions may be combined arbitrarily to form optional embodiments of the present application, and are not described in detail herein.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.

Fig. 4 is a schematic diagram of a commodity marketing device based on an unmanned vehicle according to an embodiment of the present disclosure. As shown in fig. 4, the unmanned vehicle-based merchandise marketing device includes:

the task obtaining module 401 is configured to obtain a commodity marketing task, where the commodity marketing task includes commodity label information and a marketing index of a commodity to be marketed;

a determining module 402, configured to determine a target unmanned vehicle corresponding to a marketing index, and invoke a user data pool having an association relationship with the target unmanned vehicle, where the user data pool includes a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user;

the matching module 403 is configured to match the commodity tag information with the user tag information according to a preset tag matching policy to obtain a matching result;

And the pushing module 404 is configured to determine a plurality of target users according to the matching result, and push the sales information of the item to be marketed to each target user.

According to the technical scheme provided by the embodiment of the disclosure, a commodity marketing task is obtained through a task obtaining module 401, and the commodity marketing task comprises commodity label information and marketing indexes of a commodity to be marketed; the determining module 402 determines a target unmanned vehicle corresponding to a marketing index, and invokes a user data pool having a relationship with the target unmanned vehicle, where the user data pool includes a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user; the matching module 403 matches the commodity label information with the user label information according to a preset label matching strategy to obtain a matching result; the pushing module 404 determines a plurality of target users according to the matching result, pushes the sales information of the commodity to be marketed to each target user, can actively and accurately identify the purchase demand of the user, is favorable for improving the success rate of commodity transaction, and is favorable for further deeply popularizing the marketing mode of unmanned selling.

In some embodiments, the matching module 403 comprises:

the first screening unit is configured to screen out a target user data cluster with the highest association degree with the commodity label information from the user data pool;

the calculation unit is configured to calculate a correlation value between each user tag data set in the target user data cluster and the commodity tag information respectively;

a second screening unit, configured to screen out a target user tag data set with the highest relevance value from the plurality of user tag data sets in the target user data cluster according to the relevance value;

and the matching unit is configured to match the commodity label information with the user label information of each user in the target user label data set respectively to obtain a matching result.

In other embodiments, the matching module 403 includes:

the weight distribution unit is configured to distribute an associated weight value for each user data cluster in a user data pool which is associated with the target unmanned vehicle according to the commodity label information;

the matching calculation unit is configured to calculate a matching value between the user tag information and the commodity tag information of each user in each user tag data set in each user data cluster according to the associated weight value allocated to each user data cluster;

And the superposition unit is configured to superpose the matching values belonging to the same user to obtain a matching result between the user label information and the commodity label information of each user.

In some embodiments, the user data pool includes a first user data cluster, a second user data cluster, a third user data cluster, and a fourth user data cluster. The matching module 403 includes:

the first distribution unit is configured to distribute a first weight value to the first user data cluster, distribute a second weight value to the second user data cluster, distribute a third weight value to the third user data cluster and distribute a fourth weight value to the fourth user data cluster according to the commodity label information;

the second distributing unit is configured to distribute a first matching weight value to each user tag data set in the first user data cluster, distribute a second matching weight value to each user tag data set in the second user data cluster, distribute a third matching weight value to each user tag data set in the third user data cluster, and distribute a fourth matching weight value to each user tag data set in the fourth user data cluster according to the commodity tag information;

A first calculating unit configured to calculate a matching value between the user tag information and the item tag information of each user in each user tag data set in each user data cluster based on a first weight value, a second weight value, a third weight value, a fourth weight value, a first matching weight, a second matching weight, a third matching weight, and a fourth matching weight;

and the second computing unit is configured to superpose the matching values of the same commodity belonging to the same user to obtain a matching result corresponding to each user.

In some embodiments, the first computing unit may be specifically configured to:

the matching values of the same commodity belonging to the same user are superposed to obtain a matching result corresponding to each user, and the method comprises the following steps:

In some embodiments, the marketing metrics include projected marketing volume and projected time to completion of the metrics. Determining a target unmanned vehicle corresponding to a marketing index, comprising:

determining at least one selling time period and a patrol selling area corresponding to each selling time period according to the planned marketing amount and the index predicted completion time;

In some embodiments, the above apparatus further comprises:

the system comprises a receiving module, a processing module and a display module, wherein the receiving module is configured to receive an unmanned vehicle position query request sent by a target user, and the unmanned vehicle position query request comprises current position information of the target user;

the acquisition module is configured to acquire real-time position information of the target unmanned vehicle and calculate a dynamic distance value between the target unmanned vehicle and a target user according to the real-time position information and the current position information;

The time calculation module is configured to calculate the arrival time of the position where the target user is located according to the dynamic distance value and the running speed of the target unmanned vehicle;

and the generating module is configured to generate a dynamic moving route change diagram according to the dynamic distance value and the arrival time, and push the dynamic moving route change diagram to the target user.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by functions and internal logic of the process, and should not constitute any limitation to the implementation process of the embodiments of the present disclosure.

Fig. 5 is a schematic diagram of an electronic device 5 provided in an embodiment of the present disclosure. As shown in fig. 5, the electronic apparatus 5 of this embodiment includes: a processor 501, a memory 502 and a computer program 503 stored in the memory 502 and executable on the processor 501. The steps in the various method embodiments described above are implemented when the processor 501 executes the computer program 503. Alternatively, the processor 501 implements the functions of each module/unit in each apparatus embodiment described above when executing the computer program 503.

The electronic device 5 may be a desktop computer, a notebook, a palm computer, a cloud server, or other electronic devices. The electronic device 5 may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that fig. 5 is merely an example of the electronic device 5, and does not constitute a limitation of the electronic device 5, and may include more or less components than those shown, or different components.

The Processor 501 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc.

The storage 502 may be an internal storage unit of the electronic device 5, for example, a hard disk or a memory of the electronic device 5. The memory 502 may also be an external storage device of the electronic device 5, such as a plug-in hard disk provided on the electronic device 5, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. The memory 502 may also include both internal and external storage units of the electronic device 5. The memory 502 is used for storing computer programs and other programs and data required by the electronic device.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit.

The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the present disclosure may implement all or part of the flow of the method in the above embodiments, and may also be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the above methods and embodiments. The computer program may comprise computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain suitable additions or additions that may be required in accordance with legislative and patent practices within the jurisdiction, for example, in some jurisdictions, computer readable media may not include electrical carrier signals or telecommunications signals in accordance with legislative and patent practices.

The above examples are only intended to illustrate the technical solution of the present disclosure, not to limit it; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present disclosure, and are intended to be included within the scope of the present disclosure.

Claims

1. A commodity marketing method based on unmanned vehicles is characterized by comprising the following steps:

acquiring a commodity marketing task, wherein the commodity marketing task comprises commodity label information and a marketing index of a commodity to be marketed;

determining a target unmanned vehicle corresponding to the marketing index, and calling a user data pool having a relationship with the target unmanned vehicle, wherein the user data pool comprises a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user;

Determining a plurality of target users according to the matching result, and pushing the sales information of the commodity to be marketed to each target user;

the method comprises the following steps of matching the commodity label information with the user label information according to a preset label matching strategy to obtain a matching result, wherein the matching result comprises the following steps:

respectively calculating a correlation value between each user tag data set in the target user data cluster and the commodity tag information;

according to the relevance value, screening out a target user label data set with the highest relevance value from a plurality of user label data sets in the target user data cluster;

2. The method according to claim 1, wherein matching the commodity tag information with the user tag information according to a preset tag matching policy to obtain a matching result comprises:

Distributing an association weight value for each user data cluster in a user data pool having an association relation with the target unmanned vehicle according to the commodity label information;

calculating a matching value between the user tag information of each user in each user tag data set in each user data cluster and the commodity tag information according to the associated weight value distributed to each user data cluster;

and superposing all the matching values belonging to the same user to obtain a matching result between the user label information and the commodity label information of each user.

3. The method of claim 1, wherein the user data pool comprises a first user data cluster, a second user data cluster, a third user data cluster, and a fourth user data cluster;

according to a preset tag matching strategy, matching the commodity tag information with the user tag information to obtain a matching result, wherein the matching result comprises the following steps:

according to the commodity label information, distributing a first weight value to the first user data cluster, distributing a second weight value to the second user data cluster, distributing a third weight value to the third user data cluster, and distributing a fourth weight value to the fourth user data cluster;

According to the commodity label information, allocating a first matching weight value to each user label data set in the first user data cluster, allocating a second matching weight value to each user label data set in the second user data cluster, allocating a third matching weight value to each user label data set in the third user data cluster, and allocating a fourth matching weight value to each user label data set in the fourth user data cluster;

calculating a matching value between the user tag information of each user in each user tag data set in each user data cluster and the commodity tag information based on the first weight value, the second weight value, the third weight value, the fourth weight value, the first matching weight, the second matching weight, the third matching weight and the fourth matching weight;

and superposing the matching values of the same commodity belonging to the same user to obtain a matching result corresponding to each user.

4. The method of claim 3, wherein calculating a matching value between the user tag information and the item tag information of each user in each user tag data set in each user data cluster based on the first weight value, the second weight value, the third weight value, the fourth weight value, the first matching weight, the second matching weight, the third matching weight, and the fourth matching weight comprises:

According to the first weight value and the first matching weight value, calculating a first matching value between the user tag information of each user in each user tag data set in the first user data cluster and the commodity tag information;

according to the second weight value and the second matching weight value, a second matching value between the user tag information of each user in each user tag data set in the second user data cluster and the commodity tag information is calculated;

according to the third weight value and the third matching weight value, a third matching value between the user tag information of each user in each user tag data set in a third user data cluster and the commodity tag information is calculated;

according to the fourth weight value and the fourth matching weight value, a fourth matching value between the user tag information of each user in each user tag data set in a fourth user data cluster and the commodity tag information is calculated;

superposing the matching values of the same commodity belonging to the same user to obtain the matching result corresponding to each user, wherein the matching result comprises the following steps:

5. The method of claim 1, wherein the marketing metrics include a projected marketing volume and a metric projected completion time;

determining a target unmanned vehicle corresponding to the marketing index, comprising:

and determining a target unmanned vehicle according to the patrol selling area.

6. The method of claim 1, further comprising:

receiving an unmanned vehicle position query request sent by the target user, wherein the unmanned vehicle position query request comprises current position information of the target user;

acquiring real-time position information of the target unmanned vehicle, and calculating a dynamic distance value between the target unmanned vehicle and the target user according to the real-time position information and the current position information;

And generating a dynamic moving route change diagram according to the dynamic distance value and the arrival time, and pushing the dynamic moving route change diagram to the target user.

7. The utility model provides a commodity marketing device based on unmanned car which characterized in that includes:

the system comprises a task acquisition module, a marketing module and a marketing module, wherein the task acquisition module is configured to acquire a commodity marketing task which comprises commodity label information and marketing indexes of a commodity to be marketed;

a determining module configured to determine a target unmanned vehicle corresponding to the marketing index, and invoke a user data pool having an association relationship with the target unmanned vehicle, where the user data pool includes a plurality of user data clusters, one user data cluster corresponds to a plurality of user tag data sets, and one user tag data set corresponds to a plurality of users and user tag information corresponding to each user;

the pushing module is configured to determine a plurality of target users according to the matching result, and push the sales information of the commodity to be marketed to each target user;

wherein, according to a preset tag matching strategy, matching the commodity tag information with the user tag information to obtain a matching result, and the method comprises the following steps:

8. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.