A method, device, equipment and medium for pushing products

Abstract

The present invention discloses a method, device, equipment and medium for pushing goods, and relates to the field of intelligent vehicle technology. The method for pushing goods includes: obtaining historical behavior data of multiple vehicles and update data of a target vehicle; the historical behavior data is instantaneous data of the corresponding vehicle when a purchase behavior related to the vehicle occurs; the update data is instantaneous data of the target vehicle updated at a preset period; determining the similarity between the historical behavior data and the update data; determining a product recommendation coefficient based on the similarity; and pushing goods to the target vehicle using the product recommendation coefficient. Due to the determination of the similarity, the present invention can obtain a product recommendation coefficient corresponding to a high similarity and push the corresponding goods. At this time, the homepage of the automotive supplies website can push the required personalized goods to the user without searching through the search function of the website, thereby improving the efficiency of users finding personalized goods and the user experience.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicle technology, and in particular to a commodity push method, device, equipment and medium. Background Art

[0002] With the development of intelligent automobiles, vehicles are generally equipped with intelligent vehicle systems, which can collect and analyze a large amount of vehicle data, including mileage, driving habits, vehicle conditions, etc. When a rarely used accessory of a car is damaged and needs to be replaced, when a user purchases the accessory on an automobile supplies website, or purchases automobile-related accessories in an automobile goods mall, the homepage of the automobile supplies website cannot push the personalized products that the user needs. The user can only search through the search function of the website, which reduces the efficiency of users finding personalized products and reduces the user experience.

[0003] In view of the above problems, finding out how to push personalized products to users and improve the user experience is a problem that technicians in this field are trying their best to solve. Summary of the invention

[0004] The purpose of the present invention is to provide a product push method, device, equipment and medium, which are used to solve the problem that the homepage of an automobile supplies website cannot push the personalized products required by users, and users can only search through the search function of the website, which reduces the efficiency of users finding personalized products and reduces the user experience.

[0005] In order to solve the above technical problems, the present invention provides a product push method, comprising:

[0006] Obtaining historical behavior data of multiple vehicles and updated data of a target vehicle; the historical behavior data is instantaneous data of the corresponding vehicle when a purchase behavior related to the vehicle occurs; the updated data is instantaneous data of the target vehicle updated at a preset period;

[0007] Determine the similarity between historical behavior data and updated data;

[0008] Determine the product recommendation coefficient based on similarity;

[0009] Use the product recommendation coefficient to push products to the target vehicle.

[0010] On the other hand, determining the similarity between historical behavior data and updated data includes:

[0011] Determine vehicle attributes, time decay coefficients, and multiple sampling times based on historical behavior data and update data;

[0012] Determine the corresponding vehicle attribute weight value and vehicle attribute similarity according to the vehicle attributes;

[0013] The similarity is determined according to the vehicle attribute weight value, the vehicle attribute similarity, the time decay coefficient, and multiple sampling times.

[0014] On the other hand, when the vehicle attribute similarity is a numerical vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0015] Set reference parameters according to vehicle attribute weight values;

[0016] Obtain multiple vehicle attribute values ​​corresponding to the vehicle attributes;

[0017] determining a maximum value between a reference parameter and a plurality of vehicle attribute values;

[0018] The vehicle attribute similarity is determined based on the maximum value and the plurality of vehicle attribute values.

[0019] On the other hand, when the vehicle attribute similarity is a binary vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0020] Setting a fault flag and a normal flag, wherein the fault flag indicates that the vehicle attribute is in a fault state, and the normal flag indicates that the vehicle attribute is in a normal working state;

[0021] Count the number of fault identifications and normal identifications;

[0022] The vehicle attribute similarity is determined based on the counted number.

[0023] On the other hand, when the vehicle attribute similarity is a category-type vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0024] Determine whether the vehicle attributes are of the same category;

[0025] If so, the vehicle attribute similarity is determined to be 1;

[0026] If not, the vehicle attribute similarity is determined to be 0.

[0027] On the other hand, determining the product recommendation coefficient based on similarity includes:

[0028] The similarities are accumulated to obtain the product recommendation coefficient.

[0029] On the other hand, after determining the product recommendation coefficient based on similarity, it also includes:

[0030] Sort the product recommendation coefficients according to the preset order;

[0031] Extract a preset number of product recommendation coefficients in a preset order;

[0032] Match the corresponding products according to the product recommendation coefficient.

[0033] On the other hand, obtaining updated data of the target vehicle includes:

[0034] Get the updated data of the target vehicle in T+1 manner.

[0035] In order to solve the above technical problems, the present invention further provides a commodity pushing device, comprising:

[0036] The first acquisition module is used to acquire historical behavior data of multiple vehicles and update data of a target vehicle; the historical behavior data is instantaneous data of the corresponding vehicle when a purchase behavior related to the vehicle occurs; the update data is instantaneous data of the target vehicle updated at a preset period;

[0037] A first determination module, used to determine the similarity between the historical behavior data and the updated data;

[0038] The second determination module is used to determine the commodity recommendation coefficient according to the similarity;

[0039] The push module is used to push products to the target vehicle using the product recommendation coefficient.

[0040] In addition, the device also includes the following modules:

[0041] On the other hand, determining the similarity between historical behavior data and updated data includes:

[0042] A third determination module, for determining vehicle attributes, a time decay coefficient, and a plurality of sampling times according to the historical behavior data and the update data;

[0043] A fourth determination module, used to determine a corresponding vehicle attribute weight value and a vehicle attribute similarity according to the vehicle attributes;

[0044] The fifth determination module is used to determine the similarity according to the vehicle attribute weight value, the vehicle attribute similarity, the time decay coefficient, and multiple sampling times.

[0045] On the other hand, when the vehicle attribute similarity is a numerical vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0046] A first setting module, used for setting reference parameters according to vehicle attribute weight values;

[0047] A second acquisition module is used to acquire multiple vehicle attribute values ​​corresponding to the vehicle attributes;

[0048] a sixth determination module, for determining a maximum value between a reference parameter and a plurality of vehicle attribute values;

[0049] The seventh determination module is used to determine the vehicle attribute similarity according to the maximum value and multiple vehicle attribute values.

[0050] On the other hand, when the vehicle attribute similarity is a binary vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0051] A second setting module is used to set a fault flag and a normal flag, wherein the fault flag indicates that the vehicle attribute is in a fault state, and the normal flag indicates that the vehicle attribute is in a normal working state;

[0052] A statistics module is used to count the number of fault identifiers and normal identifiers;

[0053] The eighth determination module is used to determine the vehicle attribute similarity according to the counted number.

[0054] On the other hand, when the vehicle attribute similarity is a category-type vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0055] A judgment module, used to judge whether the vehicle attributes are of the same category;

[0056] If yes, a ninth determination module is triggered to determine that the vehicle attribute similarity is 1;

[0057] If not, the tenth determination module is triggered to determine that the vehicle attribute similarity is 0.

[0058] On the other hand, determining the product recommendation coefficient based on similarity includes:

[0059] The accumulation module is used to accumulate similarities to obtain a product recommendation coefficient.

[0060] On the other hand, after determining the product recommendation coefficient based on similarity, it also includes:

[0061] A sorting module is used to sort the product recommendation coefficients according to a preset order;

[0062] An extraction module, used to extract a preset number of commodity recommendation coefficients in a preset order;

[0063] The matching module is used to match corresponding products according to the product recommendation coefficient.

[0064] On the other hand, obtaining updated data of the target vehicle includes:

[0065] The third acquisition module is used to acquire the updated data of the target vehicle in a T+1 manner.

[0066] In order to solve the above technical problems, the present invention also provides a commodity pushing device, comprising:

[0067] Memory for storing computer programs;

[0068] The processor is used to execute the computer program to implement the steps of the product push method.

[0069] In order to solve the above technical problems, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned whole commodity push method are implemented.

[0070] The present invention provides a method for pushing goods, including: obtaining historical behavior data of multiple vehicles and update data of target vehicles; the historical behavior data is instantaneous data of the corresponding vehicle when a purchase behavior related to the vehicle occurs; the update data is instantaneous data of the target vehicle updated at a preset period; determining the similarity between the historical behavior data and the update data; determining a product recommendation coefficient based on the similarity; and pushing goods to the target vehicle using the product recommendation coefficient. Due to the determination of the similarity, the present invention can obtain a product recommendation coefficient corresponding to a high similarity and push the corresponding goods. At this time, the homepage of the automotive supplies website can push the required personalized goods to the user without searching through the search function of the website, thereby improving the efficiency of users finding personalized goods and the user experience.

[0071] The present invention also provides a commodity pushing device, equipment and medium, with the same effects as above. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0073] Figure 1 A flow chart of a commodity push method provided by an embodiment of the present invention;

[0074] Figure 2 A structural diagram of a commodity pushing device provided by an embodiment of the present invention;

[0075] Figure 3 This is a structural diagram of a commodity push device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] The core of the present invention is to provide a product push method, device, equipment and medium, which can obtain the product recommendation coefficient corresponding to the high similarity and push the corresponding product. At this time, the homepage of the automotive supplies website can push the required personalized products to the user without searching through the search function of the website, thereby improving the efficiency of users in finding personalized products and the user experience.

[0078] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0079] First of all, it should be explained that the product push method involved in the embodiment of the present invention is applied to an automobile product mall, which is used to sell various products related to smart cars, such as: central control display screen, tires, door handles, steering wheels, wipers, etc.; in addition, an intelligent car system is provided in the smart car, and the data in the intelligent car system is exchanged and interacted with the automobile product mall.

[0080] Figure 1 A flow chart of a commodity push method provided by an embodiment of the present invention, such as Figure 1 As shown, the product push method includes:

[0081] S10: Acquire historical behavior data of multiple vehicles and update data of the target vehicle;

[0082] The historical behavior data is the instantaneous data of the corresponding vehicle when the purchase behavior related to the vehicle occurs; it can be understood that when a user purchases a certain product in the automobile product mall, all the instantaneous information of the smart car driven by the user at the current purchase time is collected and saved to the historical behavior database of the recommendation system of the automobile product mall; wherein, all the instantaneous information of the car includes at least the following information: user number, product number, frame number, data update time, car price, total mileage, maintenance standard mileage, maintenance standard time, cruising range (estimated), average energy consumption per 100 kilometers, province, city, 19 fault states and other information;

[0083] The updated data is instantaneous data of the target vehicle updated at a preset period;

[0084] The updated data includes all vehicle information of vehicles driven by multiple users. It is understandable that if a user has not purchased any goods in the automobile goods mall, the user has no historical behavior data stored in the automobile goods mall. It should be noted that when the number of users in the automobile goods mall runs for a certain period of time, the upper limit of the number of users will be reached. When the automobile goods mall starts to operate in the early stage, the number of users therein will be greater than the historical behavior data. With the long-term operation of the automobile goods mall, the number of historical behavior data corresponding to the users therein will gradually exceed the number of users. In this embodiment, the preset period can be one day, one week, one month, etc. As a more preferred embodiment, it is convenient to obtain all the car data of each user in the automobile goods mall in a timely manner, and the instantaneous data of the target vehicle is updated with one day as the preset period; specifically, the updated data of the target vehicle is obtained in a T+1 manner; the T+1 manner can be understood as that the vehicle data collected on the day will be output on the next data processing day, where T is the date of collecting the vehicle data, and T+1 is the day after the date of collecting the vehicle data;

[0085] S11: Determine the similarity between the historical behavior data and the updated data;

[0086] When the vehicle driven by a user in the update data is a sport / suburban utility vehicle (SUV), the target vehicle is an SUV, and the update data includes all vehicle information. The similarity between the updated vehicle information of the SUV and each piece of historical behavior data is determined one by one; in this embodiment, the similarity is recorded as sim(a,b);

[0087] S12: Determine a product recommendation coefficient based on the similarity;

[0088] Specifically, multiple similarities are accumulated to obtain a product recommendation coefficient. In this embodiment, the product recommendation coefficient is recorded as recommend(product i);

[0089] S13: Push products to the target vehicle using the product recommendation coefficient.

[0090] In this embodiment, the product recommendation coefficient corresponding to the high similarity can be obtained according to the determined similarity, and the corresponding product can be pushed. At this time, the homepage of the automotive supplies website can push the personalized products required by the user without searching through the search function of the website, thereby improving the efficiency of users in finding personalized products and the user experience.

[0091] Based on the above embodiment, as a more preferred embodiment, determining the similarity between the historical behavior data and the updated data includes:

[0092] Determine vehicle attributes, time decay coefficients, and multiple sampling times based on historical behavior data and update data;

[0093] Determine the corresponding vehicle attribute weight value and vehicle attribute similarity according to the vehicle attributes;

[0094] The similarity is determined according to the vehicle attribute weight value, the vehicle attribute similarity, the time decay coefficient, and multiple sampling times.

[0095] In this embodiment, the vehicle attribute is recorded as i, and the time decay coefficient is recorded as α i , vehicle attribute weight value w i , the vehicle attribute similarity is recorded as S(a i ,b i ), when there are two types of sampling time, the first sampling time t a The second sampling time t is used to represent the occurrence time of the currently used data information corresponding to the updated data. b To represent the time when the purchase behavior occurred corresponding to the historical behavior data currently used;

[0096] Then, the formula for determining the similarity sim(a,b) is:

[0097]

[0098] Among them, n means that there are n vehicle attributes in total, and one vehicle attribute among the n vehicle attributes is recorded as i.

[0099] Based on the above embodiment, as a more preferred embodiment, the vehicle attribute similarity is divided into three types, namely, numerical vehicle attribute similarity, binary vehicle attribute similarity, and category vehicle attribute similarity.

[0100] When the vehicle attribute similarity is a numerical vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0101] Set reference parameters according to vehicle attribute weight values;

[0102] Obtain multiple vehicle attribute values ​​corresponding to the vehicle attributes;

[0103] determining a maximum value between a reference parameter and a plurality of vehicle attribute values;

[0104] The vehicle attribute similarity is determined based on the maximum value and the plurality of vehicle attribute values.

[0105] In this embodiment, the reference parameter is denoted as β i , then determine the vehicle attribute similarity S(a i ,b i ) is as follows:

[0106]

[0107] Among them, β i It is to prevent a i Value and b i If the value is too small, the vehicle attribute similarity calculation will be abnormal. i Set the maximum value of the i-th vehicle attribute to 1 / 10 of the minimum value.

[0108] When the vehicle attribute similarity is a binary vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0109] Setting a fault flag and a normal flag, wherein the fault flag indicates that the vehicle attribute is in a fault state, and the normal flag indicates that the vehicle attribute is in a normal working state;

[0110] Count the number of fault identifications and normal identifications;

[0111] The vehicle attribute similarity is determined based on the counted number.

[0112] In this embodiment, the fault flag is recorded as 1, and the normal flag is recorded as 0. Take two vehicles as an example, one of the vehicles is recorded as a, and the other vehicle is recorded as b. The number of fault flags and normal flags is counted according to Table 1, which is as follows:

[0113] Table 1 Statistics of fault indications and normal identifications of two vehicles

[0114]

[0115] It should be noted that when both vehicle a and vehicle b use the fault mark to indicate that vehicle a and vehicle b are in a fault state, the statistical number is recorded as q, when vehicle a uses the fault mark to indicate that vehicle a is in a fault state and vehicle b uses the normal mark to indicate that vehicle b is in a normal working state, the statistical number is recorded as s, when vehicle b uses the fault mark to indicate that vehicle b is in a fault state and vehicle a uses the normal mark to indicate that vehicle a is in a normal working state, the statistical number is recorded as r, and when both vehicle a and vehicle b use the normal mark to indicate that vehicle a and vehicle b are in a normal working state, the statistical number is recorded as t. The formula for determining the similarity of vehicle attributes is as follows:

[0116]

[0117] It should be noted that when the numerator q is 0, the vehicle attribute similarity is directly determined to be 0.

[0118] When the vehicle attribute similarity is a category-type vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attributes includes:

[0119] Determine whether the vehicle attributes are of the same category;

[0120] If so, the vehicle attribute similarity is determined to be 1;

[0121] If not, the vehicle attribute similarity is determined to be 0.

[0122] Based on the above embodiment, as a more preferred embodiment, after determining the commodity recommendation coefficient according to the similarity, the method further includes:

[0123] Sort the product recommendation coefficients according to the preset order;

[0124] The preset order may be in descending order according to the product recommendation coefficients, or in descending order according to the vehicle attribute weight values. The preset order may be determined in a specific implementation manner according to a specific implementation scenario;

[0125] Extract a preset number of product recommendation coefficients in a preset order;

[0126]

[0127] The preset number may be a positive integer, and the value of the positive integer is not limited. As a most preferred embodiment, since the automobile product mall needs to display products, the preset number may be set to 10. At this time, the number of products that can be matched according to the product recommendation coefficient is also 10;

[0128] Match the corresponding products according to the product recommendation coefficient.

[0129]

[0130] Finally, a data list is obtained, which includes at least the user name, recommended purchase items, and product recommendation coefficients; wherein the product recommendation coefficients correspond to the recommended purchase items and the user name. At this time, the recommended purchase items are determined according to the user name, and are sorted according to the corresponding product recommendation coefficients. The corresponding products are pushed on the homepage of the automobile product mall according to the size relationship of the product recommendation coefficients. Among them, the top 10 recommended purchase items are obtained according to the size relationship of the product recommendation coefficients and displayed on the homepage of the automobile product mall.

[0131] In the above embodiments, the commodity push method is described in detail, and the present invention also provides a corresponding embodiment of the commodity push device. It should be noted that the present invention describes the embodiment of the device part from two perspectives, one is based on the functional module perspective, and the other is based on the hardware perspective.

[0132] Figure 2A structural diagram of a commodity pushing device provided by an embodiment of the present invention, such as Figure 2 As shown, the present invention also provides a commodity pushing device, comprising:

[0133] The first acquisition module 20 is used to acquire historical behavior data of multiple vehicles and update data of a target vehicle; the historical behavior data is instantaneous data of the corresponding vehicle when a purchase behavior related to the vehicle occurs; the update data is instantaneous data of the target vehicle updated at a preset period;

[0134] A first determination module 21, used to determine the similarity between the historical behavior data and the update data;

[0135] A second determination module 22, used to determine a commodity recommendation coefficient according to the similarity;

[0136] The push module 23 is used to push the product to the target vehicle using the product recommendation coefficient.

[0137] In addition, the device also includes the following modules:

[0138] In some embodiments, determining the similarity between the historical behavior data and the updated data includes:

[0139] A third determination module, for determining vehicle attributes, a time decay coefficient, and a plurality of sampling times according to the historical behavior data and the update data;

[0140] A fourth determination module, used to determine a corresponding vehicle attribute weight value and a vehicle attribute similarity according to the vehicle attributes;

[0141] The fifth determination module is used to determine the similarity according to the vehicle attribute weight value, the vehicle attribute similarity, the time decay coefficient, and multiple sampling times.

[0142] In some embodiments, when the vehicle attribute similarity is a numerical vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0143] A first setting module, used for setting reference parameters according to vehicle attribute weight values;

[0144] A second acquisition module is used to acquire multiple vehicle attribute values ​​corresponding to the vehicle attributes;

[0145] a sixth determination module, for determining a maximum value between a reference parameter and a plurality of vehicle attribute values;

[0146] The seventh determination module is used to determine the vehicle attribute similarity according to the maximum value and multiple vehicle attribute values.

[0147] In some embodiments, when the vehicle attribute similarity is a binary vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0148] A second setting module is used to set a fault flag and a normal flag, wherein the fault flag indicates that the vehicle attribute is in a fault state, and the normal flag indicates that the vehicle attribute is in a normal working state;

[0149] A statistics module is used to count the number of fault identifiers and normal identifiers;

[0150] The eighth determination module is used to determine the vehicle attribute similarity according to the counted number.

[0151] In some embodiments, when the vehicle attribute similarity is a category-based vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes:

[0152] A judgment module, used to judge whether the vehicle attributes are of the same category;

[0153] If yes, a ninth determination module is triggered to determine that the vehicle attribute similarity is 1;

[0154] If not, the tenth determination module is triggered to determine that the vehicle attribute similarity is 0.

[0155] In some embodiments, determining a product recommendation coefficient according to the similarity includes:

[0156] The accumulation module is used to accumulate similarities to obtain a product recommendation coefficient.

[0157] In some embodiments, after determining the commodity recommendation coefficient according to the similarity, the method further includes:

[0158] A sorting module is used to sort the product recommendation coefficients according to a preset order;

[0159] An extraction module, used to extract a preset number of commodity recommendation coefficients in a preset order;

[0160] The matching module is used to match corresponding products according to the product recommendation coefficient.

[0161] In some embodiments, obtaining updated data of the target vehicle includes:

[0162] The third acquisition module is used to acquire the updated data of the target vehicle in a T+1 manner.

[0163] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, which will not be repeated here.

[0164] Figure 3A structural diagram of a commodity push device provided by an embodiment of the present invention, such as Figure 3 As shown, a commodity push device includes:

[0165] A memory 30, for storing computer programs;

[0166] The processor 31 is used to implement the steps of the commodity push method mentioned in the above embodiment when executing the computer program.

[0167] The commodity push device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer, or a desktop computer.

[0168] Among them, the processor 31 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 31 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 31 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 31 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 31 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0169] The memory 30 may include one or more computer-readable storage media, which may be non-transitory. The memory 30 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 30 is at least used to store the following computer program, wherein, after the computer program is loaded and executed by the processor 31, it can implement the relevant steps of the commodity push method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 30 may also include an operating system and data, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system may include Windows, Unix, Linux, etc. The data may include but is not limited to the commodity push method, etc.

[0170] In some embodiments, the commodity push device may further include a display screen, an input and output interface, a communication interface, a power supply, and a communication bus.

[0171] Those skilled in the art will understand that Figure 3 The structure shown in the figure does not constitute a limitation on the commodity pushing device, and may include more or fewer components than those shown in the figure.

[0172] The commodity pushing device provided by the embodiment of the present invention includes a memory 30 and a processor 31. When the processor 31 executes the program stored in the memory 30, the commodity pushing method can be implemented.

[0173] Finally, the present invention also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps recorded in the above method embodiment are implemented.

[0174] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory), ROM, random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0175] The above is a detailed introduction to a commodity push method, device, equipment and medium provided by the present invention. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can refer to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

[0176] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A commodity push method, characterized in that: include: Obtaining historical behavior data of multiple vehicles and update data of a target vehicle; the historical behavior data is instantaneous data of the corresponding vehicle when a purchase behavior related to the vehicle occurs; the update data is instantaneous data of the target vehicle updated at a preset period, and the instantaneous data includes user number, product number, frame number, data update time, vehicle price, total mileage, standard maintenance mileage, standard maintenance time, cruising range, average energy consumption per 100 kilometers, province, city, and fault status; Determining the similarity between the historical behavior data and the updated data; Wherein, the determining of the similarity between the historical behavior data and the update data comprises: determining a vehicle attribute, a time decay coefficient, and a plurality of sampling times according to the historical behavior data and the update data; determining a corresponding vehicle attribute weight value and a vehicle attribute similarity according to the vehicle attribute; determining the similarity according to the vehicle attribute weight value, the vehicle attribute similarity, the time decay coefficient, and a plurality of the sampling times; When the types of the plurality of sampling times are two, the first sampling time represents the occurrence time of the currently used data information corresponding to the update data, and the second sampling time represents the time when the purchase behavior corresponding to the currently used historical behavior data occurs, then the formula for determining the similarity is as follows: Where sim(a,b) represents the similarity, n represents that there are n vehicle attributes, and one of the n vehicle attributes is denoted as i, w i represents the vehicle attribute weight, S(a i ,b i ) represents the vehicle attribute similarity; α i represents the time attenuation coefficient, t a represents the first sampling time, t b represents the second sampling time; Determining a product recommendation coefficient according to the similarity; The commodity recommendation coefficient is used to push commodities to the target vehicle.

2. The commodity push method according to claim 1, characterized in that: When the vehicle attribute similarity is a numerical vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes: Setting reference parameters according to the vehicle attribute weight value; Obtaining multiple vehicle attribute values ​​corresponding to the vehicle attribute; determining a maximum value between the reference parameter and a plurality of the vehicle attribute values; The vehicle attribute similarity is determined according to the maximum value and a plurality of the vehicle attribute values.

3. The commodity push method according to claim 1, characterized in that: When the vehicle attribute similarity is a binary vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes: Setting a fault flag and a normal flag, wherein the fault flag indicates that the vehicle attribute is in a fault state, and the normal flag indicates that the vehicle attribute is in a normal working state; Counting the number of the fault identifications and the normal identifications; The vehicle attribute similarity is determined according to the counted number.

4. The commodity push method according to claim 1, characterized in that: When the vehicle attribute similarity is a category-based vehicle attribute similarity, determining the corresponding vehicle attribute similarity according to the vehicle attribute includes: Determining whether the vehicle attributes are of the same category; If yes, then the vehicle attribute similarity is determined to be 1; If not, the vehicle attribute similarity is determined to be 0.

5. The commodity push method according to claim 1, characterized in that: Determining the commodity recommendation coefficient according to the similarity comprises: The similarities are accumulated to obtain the product recommendation coefficient.

6. The commodity push method according to claim 1, characterized in that: After determining the commodity recommendation coefficient according to the similarity, the method further includes: Sorting the product recommendation coefficients according to a preset order; Extracting a preset number of the commodity recommendation coefficients according to the preset order; The corresponding products are matched according to the product recommendation coefficient.

7. The commodity push method according to claim 1, characterized in that: Acquiring the update data of the target vehicle includes: The updated data of the target vehicle is obtained in a T+1 manner.

8. A commodity pushing device, characterized in that: include: The first acquisition module is used to acquire historical behavior data of multiple vehicles and update data of a target vehicle; the historical behavior data is instantaneous data of the corresponding vehicle when a purchase behavior related to the vehicle occurs; the update data is instantaneous data of the target vehicle updated at a preset period, and the instantaneous data includes user number, product number, frame number, data update time, vehicle price, total mileage, standard maintenance mileage, standard maintenance time, cruising range, average energy consumption per 100 kilometers, province, city and fault status; A first determination module, used to determine the similarity between the historical behavior data and the update data; Wherein, the first determination module is specifically used to determine the vehicle attribute, the time decay coefficient and the multiple sampling times according to the historical behavior data and the update data; determine the corresponding vehicle attribute weight value and vehicle attribute similarity according to the vehicle attribute; determine the similarity according to the vehicle attribute weight value, the vehicle attribute similarity, the time decay coefficient and the multiple sampling times; When the types of the plurality of sampling times are two, the first sampling time represents the occurrence time of the currently used data information corresponding to the update data, and the second sampling time represents the time when the purchase behavior corresponding to the currently used historical behavior data occurs, then the formula for determining the similarity is as follows: Where sim(a,b) represents the similarity, n represents that there are n vehicle attributes, and one of the n vehicle attributes is denoted as i, w i represents the vehicle attribute weight, S(a i ,b i ) represents the vehicle attribute similarity; α i represents the time attenuation coefficient, t a represents the first sampling time, t b represents the second sampling time; A second determination module, used to determine a commodity recommendation coefficient according to the similarity; A push module is used to push commodities to the target vehicle using the commodity recommendation coefficient.

9. A commodity push device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the commodity push method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the commodity push method according to any one of claims 1 to 7 are implemented.

Images