Store pushing method, order allocation method, pushing system, equipment and medium
By constructing user profiles and combining them with traffic matching algorithms, the matching priority of stores is calculated, which solves the problems of traffic integration and order allocation in a multi-level distribution system and achieves precise traffic acquisition and intelligent allocation.
Patent Information
- Application Number
- CN202511116505.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-11
- Publication Date
- 2025-11-21
AI Technical Summary
In a multi-level distribution system, how to achieve efficient integration and precise traffic acquisition across platforms, and ensure that orders are intelligently allocated and managed across the entire chain in the multi-level system? Existing technologies lack precise guidance for traffic, resulting in poor traffic acquisition effects.
By acquiring user behavior data from the user end and data from external platforms, user profiles are constructed. Combining spending power and brand preferences, a traffic matching algorithm is used to calculate the store matching priority and push the store with the highest matching priority to the user.
It enables precise guidance and accurate delivery of traffic, optimizes the traffic generation effect at the store level, and ensures intelligent allocation and full-link management of orders across multiple levels.
Smart Images
Figure CN120996902A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application relates to the field of order management, and in particular to a store pushing method, an order allocation method, a pushing system, equipment and a medium. BACKGROUND
[0002] At present, the sales of large-scale commodities usually adopt a multi-level distribution system, for example, the distribution system can include groups, brands, distributor stores and distributors of multiple levels. In the multi-level distribution system, how to efficiently integrate cross-platform traffic and accurately guide traffic while ensuring intelligent allocation and full-link management of orders in the multi-level system is a problem that needs to be solved in the market at present.
[0003] At present, users mainly place orders through mobile application programs (APP), and distributors mainly rely on free channels for traffic guidance. Users see products or brands and then decide whether to place an order, but this technical solution lacks accurate guidance of traffic and has poor effect of traffic guidance. SUMMARY
[0004] The application provides a store pushing method, an order allocation method, a pushing system, equipment and a medium to solve the technical problem of how to improve the accuracy of traffic guidance and optimize the effect of traffic guidance.
[0005] To solve the above technical problem, the application provides a store pushing method, comprising:
[0006] Obtaining user behavior data of a target user from an application program of a user end; and obtaining user basic data of the target user from an external platform in real time through a preset application programming interface;
[0007] Integrating the user behavior data and the user basic data to obtain integrated data; and constructing a portrait of the target user by using the integrated data;
[0008] Analyzing the portrait of the target user to obtain consumption ability and brand preference of the target user;
[0009] According to the consumption ability and the brand preference, and in combination with a preset traffic matching algorithm, calculating a matching priority of the target user and each store;
[0010] Pushing one or more stores with the highest matching priority to the target user.
[0011] As a preferred solution, the consumption ability of the target user is described by a consumption ability index; and the matching priority of the target user and each store is calculated according to the consumption ability and the brand preference in combination with the preset traffic matching algorithm, comprising:
[0012] obtaining a current location of the target user, obtaining service scores of each store preferred by the target user according to the brand preference, and obtaining distances between the target user and each store according to the current location and locations of the stores;
[0013] substituting the distances between the target user and each store, the consumption ability index, the service scores of each store, and a preset dynamic weight coefficient into the traffic matching algorithm to respectively calculate matching priorities of the target user and each store.
[0014] Preferably, the user behavior data includes login frequency and use function preference, and the user basic data includes member level, registration time, and consumption history data.
[0015] The integrating the user behavior data and the user basic data to obtain integrated data comprises: associating and matching the user behavior data and the user basic data through a unified user identifier to obtain the integrated data.
[0016] Preferably, the real-time acquisition of the user basic data of the target user from the external platform through a preset application programming interface comprises:
[0017] The real-time pulling of the browsing record, the purchase record, the collection information, the comment content, and the geographic location information of the target user from the external platform through a preset application programming interface according to a permission authentication mechanism and a data transmission protocol of the external platform.
[0018] Preferably, the construction of the portrait of the target user by using the integrated data comprises: inputting the integrated data into a user label portrait system to obtain the portrait of the target user; wherein the user label portrait system is preset with a plurality of user labels, and the user labels include consumption ability, brand preference, and historical service score.
[0019] In addition, the application further provides a store order distribution method, which comprises:
[0020] The store pushing method in any one of the above embodiments is executed.
[0021] When it is determined that the target user places an order, a corresponding distributor store is determined according to a brand of a commodity in the order of the target user, and current inventory depth, service radius, and coverage community matching degree of all distributor stores are obtained.
[0022] According to the inventory depth, the service radius, and the coverage community matching degree, an order distribution priority of each distributor store is respectively calculated through a preset order distribution weight algorithm.
[0023] According to the order distribution priority, a plurality of dealers' stores with the highest order distribution priority are screened out;
[0024] The order of the target user is distributed to one of the plurality of dealers' stores with the highest order distribution priority.
[0025] As a preferred solution, the order of the target user is distributed to one of the plurality of dealers' stores with the highest order distribution priority, comprising:
[0026] Obtaining service records of the plurality of dealers' stores with the highest order distribution priority;
[0027] According to the service records, when it is determined that a dealer's store has historical service records of the target user, the order of the target user is distributed to the dealer's store with the historical service records of the target user;
[0028] According to the service records, when it is determined that a plurality of dealers' stores have historical service records of the target user, or it is determined that there are no historical service records of the target user, the order of the target user is distributed to the dealer's store with the highest order distribution priority.
[0029] Correspondingly, the present application also provides a store pushing system, comprising a data acquisition module, a portrait module, an analysis module, a calculation module and a pushing module; wherein,
[0030] The data acquisition module is used to acquire user behavior data of a target user from an application program of a user end, and acquire user basic data of the target user from an external platform in real time through a preset application programming interface;
[0031] The portrait module is used to integrate the user behavior data and the user basic data to obtain integrated data, and construct a portrait of the target user by using the integrated data;
[0032] The analysis module is used to analyze the portrait of the target user to obtain consumption ability and brand preference of the target user;
[0033] The calculation module is used to calculate matching priority of the target user and each store according to the consumption ability and the brand preference, and in combination with a preset traffic matching algorithm;
[0034] The pushing module is used to push one or more stores with the highest matching priority to the target user.
[0035] As a preferred solution, the consumption ability of the target user is described by a consumption ability index; the calculation module calculates the matching priority of the target user and each store according to the consumption ability and the brand preference, and in combination with a preset traffic matching algorithm, comprising:
[0036] the current location of the target user, obtaining service scores of each store preferred by the user according to the brand preference, and obtaining distances between the target user and each store according to the current location and the location of each store;
[0037] substituting the distances between the target user and each store, the consumption ability index, the service scores of each store and a preset dynamic weight coefficient into the traffic matching algorithm to respectively calculate the matching priority of the target user and each store.
[0038] Preferably, the user behavior data includes login frequency and use function preference, and the user basic data includes member level, registration time and consumption history data.
[0039] The profiling module integrates the user behavior data and the user basic data to obtain integrated data, including: the profiling module associates and integrates the user behavior data and the user basic data through a unified user identifier to obtain the integrated data.
[0040] Preferably, the data acquisition module acquires the user basic data of the target user from an external platform in real time through a preset application programming interface, including:
[0041] The data acquisition module pulls the browsing record, purchase record, collection information, comment content and geographic location information of the target user from the external platform in real time through a preset application programming interface according to the permission authentication mechanism and data transmission protocol of the external platform.
[0042] Preferably, the profiling module constructs a profile of the target user using the integrated data, including: the profiling module inputs the integrated data into a user label profiling system to obtain the profile of the target user; wherein the user label profiling system is preset with a plurality of user labels, and the user labels include consumption ability, brand preference and historical service score.
[0043] Correspondingly, the present application also provides a store order distribution system, including a store pushing module, a store information acquisition module, a priority calculation module, a screening module and a distribution module; wherein,
[0044] The store pushing module is used to execute the store pushing method of any one of the above-mentioned embodiments.
[0045] The store information acquisition module is used to determine the corresponding distributor store according to the brand of the goods in the order of the target user when the target user places an order, and to acquire the current inventory depth, service radius and coverage community matching degree of all distributor stores.
[0046] The priority calculation module is configured to calculate the order distribution priority of each dealer store by a preset order distribution weight algorithm according to the inventory depth, service radius and community matching degree.
[0047] The screening module is configured to screen a plurality of dealer stores with the highest order distribution priority according to the order distribution priority.
[0048] The distribution module is configured to distribute the order of the target user to one of the plurality of dealer stores with the highest order distribution priority.
[0049] As a preferred solution, the distribution module distributes the order of the target user to one of the plurality of dealer stores with the highest order distribution priority, comprising:
[0050] The distribution module acquires service records of the plurality of dealer stores with the highest order distribution priority.
[0051] According to the service records, when it is determined that a dealer store has historical service records of the target user, the order of the target user is distributed to the dealer store with the historical service records of the target user.
[0052] According to the service records, when it is determined that a plurality of dealer stores have historical service records of the target user, or it is determined that no historical service records of the target user exist, the order of the target user is distributed to the dealer store with the highest order distribution priority.
[0053] Correspondingly, the present application further provides a terminal device, comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the store pushing method or the store order distribution method of claim 6 or 7.
[0054] Correspondingly, the present application further provides a computer readable storage medium, comprising a stored computer program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to execute the store pushing method or the store order distribution method of any one of the above embodiments when the computer program runs.
[0055] Compared with the prior art, the present application has the following beneficial effects:
[0056] The application provides a store pushing method, an order distribution method, a pushing system, equipment and a medium. The store pushing method comprises the following steps: obtaining user behavior data of a target user from an application program of a user end; obtaining user basic data of the target user from an external platform in real time through a preset application programming interface; integrating the user behavior data and the user basic data to obtain integrated data; constructing a portrait of the target user by using the integrated data; analyzing the consumption capacity and brand preference of the target user according to the portrait of the target user; calculating the matching priority of the target user and each store according to the consumption capacity and the brand preference and in combination with a preset traffic matching algorithm; and pushing one or more stores with the highest matching priority to the target user. The application can construct the portrait of the target user by using the integrated data, analyze the consumption capacity and the brand preference of the target user, and then push one or more stores to the target user through the preset traffic matching algorithm, so that the accurate guidance of traffic and the accurate pushing are realized, the required information of the user end is provided, and the effect of flow investment and flow drainage of the store end is optimized. In addition, the application obtains the user behavior data from the application program of the user end, integrates the user basic data obtained from the external platform in real time, can realize the accurate portrait of the user on one hand, and realize the cross-platform data access on the other hand, so as to lay a foundation for the accurate distribution of traffic. BRIEF DESCRIPTION OF DRAWINGS
[0057] Figure 1 FIG. 1 is a flowchart of one embodiment of the store pushing method provided by the application.
[0058] Figure 2 FIG. 2 is a structural diagram of one embodiment of the store pushing system provided by the application. DETAILED DESCRIPTION
[0059] The technical solutions in the embodiments of the application will be clearly and completely described with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the application.
[0060] Embodiment one
[0061] Please refer to Figure 1 , Figure 1 The store pushing method provided by the application comprises steps S101 to S105, and each step is described as follows.
[0062] Step S101: Obtain the user behavior data of the target user from the application program of the user terminal; and obtain the user basic data of the target user from the external platform in real time through a preset application programming interface.
[0063] In the embodiment, the user terminal can be a mobile phone of the target user. The user behavior data of the target user can be obtained from an application program (APP) of the user terminal. The application program can be a self-owned application program of a brand party.
[0064] On the other hand, the user basic data of the target user can be obtained from the external platform in real time through a preset application programming interface (API). By combining the user behavior data and the user basic data, that is, by means of the external platform data, the problem of small amount of user data in the self-owned application program of the brand party can be solved, and a foundation for subsequent accurate user portrait is laid.
[0065] In some embodiments, the user behavior data can include, but is not limited to, the login frequency and the use function preference in the self-owned application program of the brand party. The user basic data can include, but is not limited to, the membership level, the registration time and the consumption history data of the target user in the external platform, and the like. In addition, in some other embodiments, search keywords, geographic location data and the like can also be obtained from the external platform or the self-owned application program of the brand party. The specific application scenarios can be determined as needed.
[0066] Preferably, the obtaining of the user basic data of the target user from the external platform in real time through the preset application programming interface includes: obtaining the browsing records (including browsing commodity categories, stay time), the purchase records (such as purchased commodity brands, models and quantities), the collection information (or the add-to-cart information), the comment content and the geographic location information of the target user from the external platform in real time through the preset application programming interface according to the permission authentication mechanism and the data transmission protocol of the external platform.
[0067] Step S102: Integrate the user behavior data and the user basic data to obtain integrated data; and construct a portrait of the target user by using the integrated data.
[0068] The user behavior data and the user basic data obtained in the above steps can be preprocessed, for example, repeated records, invalid fields and abnormal data are removed, so as to ensure the accuracy and consistency of the data. For example, invalid browsing records with a browsing time less than 3 seconds (may be a false touch) are removed.
[0069] Further, natural language processing and machine learning can be used to extract key features from the pre-processed data. For example, but not limited to, analyzing the content of the comments, using sentiment analysis algorithms to determine the user's satisfaction with the goods or services; according to the purchase records and browsing behavior, using association rule mining algorithms to determine the user's brand preference, consumption frequency, consumption amount interval, etc.
[0070] In some preferred embodiments, the integration of the user behavior data and the user basic data to obtain integrated data comprises: associating and matching the user behavior data and the user basic data through a unified user identifier to obtain the integrated data.
[0071] The unified user identifier can be a mobile phone number, a member ID, or a unique user identity code, etc. In addition to being obtained from the application program, the user behavior data can also be obtained from the group's customer relationship management system (CRM system).
[0072] The embodiment integrates the user behavior data and the user basic data, which helps to update and improve the user portrait. For example, the user's recently purchased product brand information obtained from an external platform can be supplemented into the "brand preference" label of the user portrait.
[0073] The embodiment can use a dynamic user portrait updating mechanism to regularly or triggeringly recalculate and adjust the user portrait label weight according to the user's latest behavior data on each platform, ensuring that the user portrait always reflects the user's latest consumption characteristics and preferences.
[0074] Based on the dynamic user portrait updating mechanism, the embodiment can also call a pre-built user label portrait system and update the user portrait of the target user based on the pre-built user label portrait system.
[0075] In some preferred embodiments, the use of the integrated data to construct the portrait of the target user comprises: inputting the integrated data into a user label portrait system to obtain the portrait of the target user; wherein the user label portrait system is pre-provided with a plurality of user labels, and the user labels include consumption ability, brand preference, and historical service score, and the number of user labels can reach more than two hundred in the case of subdivision.
[0076] Step S103: analyzing the consumption ability and brand preference of the target user according to the portrait of the target user.
[0077] In the embodiment, the consumption capacity can be described by a consumption capacity index. The consumption capacity index can be a self-defined index. The brand preference can be used for preliminary screening of the stores (for example, screening according to the brand) when calculating the matching priority of the target user and each store in the subsequent step.
[0078] In step S104, the matching priority of the target user and each store is calculated according to the consumption capacity and the brand preference in combination with a preset traffic matching algorithm.
[0079] In the embodiment, the traffic matching algorithm can be a pre-configured traffic distribution formula, which can be pre-stored in the server.
[0080] Preferably, the matching priority of the target user and each store is calculated according to the consumption capacity and the brand preference in combination with a preset traffic matching algorithm, including:
[0081] The current location of the target user is obtained, the service score of each store preferred by the user is obtained according to the brand preference, the distance between the target user and each store is obtained according to the current location and the location of each store, and the distance between the target user and each store, the consumption capacity index, the service score of each store and a preset dynamic weight coefficient are substituted into the traffic matching algorithm to calculate the matching priority of the target user and each store, respectively.
[0082] For example, the traffic distribution formula can be represented as: S ij = αC i + βD ij + γS j .
[0083] Wherein, D ij may be the distance between user i and store j (reverse weight, the closer the distance, the higher the score), C i is the consumption capacity index of the user (which can be normalized to the interval between 1 and 10 points), S j may represent the service score of store j (from historical order evaluation, which can be normalized to the interval between 1 and 5 points); α, β and γ are the dynamic weight coefficients.
[0084] The dynamic weight coefficients can be flexibly configured by the operator according to different business objectives and market conditions through the operation background. For example, during the promotion activities, α can be increased to preferentially allocate traffic to high consumption potential users; during the optimization of user experience, the weight of the service score γ of the store can be increased to guide the user to the store with better service quality, so as to realize the dynamic adjustment of the traffic distribution strategy.
[0085] In addition, accurate flow guidance can be performed: the most suitable store for the user can be selected from a plurality of stores according to the priority score calculated by the formula, and the store information and coupons are pushed, so as to realize accurate flow guidance. For example, for a user with high consumption capacity and close distance, even if the service score of a store is slightly low (but still within an acceptable range), the store can obtain a high priority score by reasonably adjusting the weight coefficient, so as to be recommended to the target user, thereby improving the user's store conversion rate, and providing a fair flow acquisition opportunity for each store.
[0086] The distance between the target user and each store, the consumption capacity index, the service score of each store and the preset dynamic weight coefficient are substituted into the flow distribution formula, so as to calculate the matching priority between the target user (assuming the number is i) and the store j.
[0087] In step S105, one or more stores with the highest matching priority are pushed to the target user.
[0088] In the embodiment, according to the needs of the target user, one or more stores with the highest matching priority can be pushed to the target user. For example, when the user browses a certain brand of goods on a certain platform, the matching priority of all stores within a range of thirty kilometers can be calculated according to the above step S104, and the store with the closest distance and a service score of 4 or above is pushed to the target user, and the user is guided to the store for consumption.
[0089] In addition, in some embodiments, for the application scenario of needing distribution, the application also provides a store order distribution method, which comprises: performing the store pushing method in any of the above embodiments; when it is determined that the target user places an order, the corresponding dealer store is determined according to the brand of the goods in the order of the target user.
[0090] Exemplarily, in some embodiments, four levels of groups, brands, dealers and distributors can be used.
[0091] Specifically, in the configuration of the data structure, each level has its corresponding ID, for example, the group has a group ID, a brand list and a group-level salesperson; the brand has a brand ID, a dealer list and a brand traffic pool (a brand-owned traffic source); the dealer has a store ID, a belonging brand, a distributor list, a guide list, a service radius and inventory data; and the distributor has a distributor ID, a belonging store and a covered community.
[0092] For example, when the brand ID of a certain brand is B001, all dealer stores under the brand can be locked.
[0093] Then, according to the inventory depth, service radius and community matching degree, the order distribution priority of each dealer store can be calculated by a preset order distribution weight algorithm; according to the order distribution priority, a plurality of dealer stores with the highest order distribution priority (for example, the top three) are screened out; and the order of the target user is distributed to one of the plurality of dealer stores with the highest order distribution priority.
[0094] Further, the distribution of the order of the target user to one of the plurality of dealer stores with the highest order distribution priority comprises: obtaining service records of the plurality of dealer stores with the highest order distribution priority; according to the service records, when it is determined that a dealer store has historical service (consumption) records of the target user, the order of the target user is distributed to the dealer store having the historical service (consumption) records of the target user; and according to the service records, when it is determined that a plurality of dealer stores have historical service (consumption) records of the target user, or when it is determined that no dealer store has historical service (consumption) records of the target user, the order of the target user is distributed to the dealer store with the highest order distribution priority.
[0095] Correspondingly, as shown in Figure 2 the application further provides a store pushing system 200, comprising a data acquisition module 201, a portrait module 202, an analysis module 203, a calculation module 204 and a pushing module 205; wherein,
[0096] The data acquisition module 201 is configured to acquire user behavior data of a target user from an application program of a user end, and acquire user basic data of the target user from an external platform in real time through a preset application programming interface;
[0097] The portrait module 202 is configured to integrate the user behavior data and the user basic data to obtain integrated data, and construct a portrait of the target user by using the integrated data;
[0098] The analysis module 203 is configured to analyze the portrait of the target user to obtain consumption ability and brand preference of the target user;
[0099] The calculation module 204 is configured to calculate the matching priority of the target user and each store according to the consumption ability and the brand preference, and in combination with a preset traffic matching algorithm;
[0100] The pushing module 205 is configured to push one or more stores with the highest matching priority to the target user.
[0101] As a preferred solution, the consumption ability of the target user is described by a consumption ability index; the calculation module 204 calculates the matching priority of the target user and each store according to the consumption ability and brand preference, combined with a preset traffic matching algorithm, including:
[0102] The calculation module 204 obtains the current location of the target user, and obtains the service score of each store preferred by the user according to the brand preference; and obtains the distance between the target user and each store according to the current location and the location of each store.
[0103] The distance between the target user and each store, the consumption ability index, the service score of each store, and a preset dynamic weight coefficient are substituted into the traffic matching algorithm to calculate the matching priority of the target user and each store, respectively.
[0104] As a preferred solution, the user behavior data includes login frequency and use function preference; and the user basic data includes member level, registration time and consumption history data.
[0105] The portrait module 202 integrates the user behavior data and the user basic data to obtain integrated data, including: the portrait module 202 associates and matches the user behavior data and the user basic data through a unified user identifier, and integrates to obtain the integrated data.
[0106] As a preferred solution, the data acquisition module 201 acquires the user basic data of the target user from an external platform in real time through a preset application programming interface, including:
[0107] The data acquisition module 201 acquires the browsing record, purchase record, collection information, comment content and geographic location information of the target user from the external platform in real time through a preset application programming interface according to the permission authentication mechanism and data transmission protocol of the external platform.
[0108] As a preferred solution, the portrait module 202 constructs a portrait of the target user by using the integrated data, including: the portrait module 202 inputs the integrated data into a user label portrait system 200 to obtain the portrait of the target user; wherein the user label portrait system 200 is preset with a plurality of user labels, and the user labels include consumption ability, brand preference and historical service score.
[0109] Correspondingly, the application also provides a store order distribution system, including a store pushing module, a store information acquisition module, a priority calculation module, a screening module and a distribution module; wherein,
[0110] The store pushing module is configured to perform the store pushing method described in any of the above embodiments.
[0111] The store information obtaining module is configured to, when determining that the target user places an order, determine corresponding distributor stores according to the product brands in the order of the target user, and obtain the current inventory depth, service radius and matching degree of the covered community of all the distributor stores.
[0112] The priority calculating module is configured to calculate the order distribution priority of each distributor store by a preset order distribution weight algorithm according to the inventory depth, service radius and matching degree of the covered community.
[0113] The screening module is configured to screen out a plurality of distributor stores with the highest order distribution priority according to the order distribution priority.
[0114] The distribution module is configured to distribute the order of the target user to one of the plurality of distributor stores with the highest order distribution priority.
[0115] As a preferred solution, the distribution module distributes the order of the target user to one of the plurality of distributor stores with the highest order distribution priority, comprising:
[0116] The distribution module obtains the service records of the plurality of distributor stores with the highest order distribution priority.
[0117] According to the service records, when it is determined that a distributor store has historical service records of the target user, the order of the target user is distributed to the distributor store having the historical service records of the target user.
[0118] According to the service records, when it is determined that a plurality of distributor stores have historical service records of the target user, or it is determined that no historical service records of the target user exist, the order of the target user is distributed to the distributor store with the highest order distribution priority.
[0119] Correspondingly, the present application also provides a terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the store pushing method or the store order distribution method as claimed in claim 6 or 7.
[0120] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.
[0121] The memory can be configured to store the computer program, and the processor can be configured to realize various functions of the terminal by running or executing the computer program stored in the memory and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc.; and the data storage area can store data created according to use of the terminal (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a nonvolatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.
[0122] Correspondingly, the present application further provides a computer readable storage medium, including a stored computer program, wherein when the computer program runs, the device where the computer readable storage medium is located executes the store pushing method or the store order distribution method according to any one of the above-mentioned embodiments.
[0123] The modules integrated by the store pushing system and the store order distribution system can be stored in a computer readable storage medium if they are realized in the form of software function units and sold or used as independent products. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware. The computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, an executable file, or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium.
[0124] Compared with the prior art, the present application has the following beneficial effects:
[0125] The present application provides a store pushing method, an order distribution method, a pushing system, equipment and a medium. The store pushing method comprises the following steps: obtaining user behavior data of a target user from an application program of a user end; obtaining user basic data of the target user from an external platform in real time through a preset application programming interface; integrating the user behavior data and the user basic data to obtain integrated data; constructing a portrait of the target user by using the integrated data; analyzing the consumption ability and brand preference of the target user according to the portrait of the target user; calculating the matching priority of the target user and each store according to the consumption ability and brand preference and in combination with a preset traffic matching algorithm; and pushing one or more stores with the highest matching priority to the target user. The present application can construct a portrait of the target user by using integrated data, analyze the consumption ability and brand preference of the target user, and then push one or more stores to the target user through a preset traffic matching algorithm, so as to realize accurate guidance and accurate pushing of traffic, provide the user end with the required information, and optimize the flow investment and flow guiding effect of the store end. In addition, the present application obtains user behavior data from an application program of a user end, integrates the user behavior data in combination with user basic data obtained from an external platform in real time, can realize accurate portrait of the user on the one hand, and realize cross-platform data access on the other hand, so as to lay a foundation for accurate distribution of traffic.
[0126] The above-described specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above-described specific embodiments are merely examples of the present application and are not intended to limit the protection scope of the present application. It is particularly pointed out that any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. A method for store push, characterized by, The application comprises the following steps: obtaining user behavior data of a target user from an application program of a user terminal; obtaining user basic data of the target user from an external platform in real time through a preset application programming interface; integrating the user behavior data and the user basic data to obtain integrated data; constructing a portrait of the target user by using the integrated data; analyzing the portrait of the target user to obtain consumption ability and brand preference of the target user; calculating matching priorities of the target user and each store according to the consumption ability and the brand preference and in combination with a preset traffic matching algorithm; pushing one or more stores with the highest matching priority to the target user.
2. The method of claim 1, wherein, The consumption ability of the target user is described by a consumption ability index; the matching priorities of the target user and each store are calculated according to the consumption ability and the brand preference and in combination with a preset traffic matching algorithm, which comprises the following steps: obtaining a current location of the target user, obtaining service scores of each store preferred by the target user according to the brand preference, and obtaining distances between the target user and each store according to the current location and locations of the stores; substituting the distances between the target user and each store, the consumption ability index, service scores of each store, and a preset dynamic weight coefficient into the traffic matching algorithm to calculate the matching priorities of the target user and each store respectively.
3. The method of claim 1, wherein, The user behavior data comprises login frequency and function preference; the user basic data comprises member level, registration time, and consumption history data. The integrated data is obtained by associating and matching the user behavior data and the user basic data through a unified user identifier.
4. The method of claim 1, wherein, The user basic data of the target user is obtained from the external platform in real time through a preset application programming interface, which comprises the following steps: pulling browsing records, purchase records, collection information, comment content, and geographic location information of the target user from the external platform in real time through a preset application programming interface according to a permission authentication mechanism and a data transmission protocol of the external platform.
5. The method of claim 1, wherein, The portrait of the target user is constructed by inputting the integrated data into a user label portrait system, wherein the user label portrait system is preset with multiple user labels, and the user labels comprise consumption ability, brand preference, and historical service score.
6. A method of assigning orders to stores, the method comprising: The store order distribution comprises the following steps: executing the store pushing method according to any one of claims 1 to 5; when determining that the target user places an order, determining a corresponding distributor store according to a brand of goods in the order of the target user, and obtaining current inventory depth, service radius, and coverage community matching degree of all distributor stores; calculating order distribution priorities of each distributor store through a preset order distribution weight algorithm according to the inventory depth, the service radius, and the coverage community matching degree; screening out multiple distributor stores with the highest order distribution priorities according to the order distribution priorities. The order of the target user is assigned to one of the multiple dealer stores with the highest order assignment priority.
7. A method of assigning orders to stores as recited in claim 6, wherein, The order of the target user is assigned to one of the multiple dealer stores with the highest order assignment priority. The service records of the multiple dealer stores with the highest order assignment priority are obtained. When it is determined from the service records that a dealer store has a historical service record of the target user, the order of the target user is assigned to the dealer store having the historical service record of the target user. When it is determined from the service records that multiple dealer stores have historical service records of the target user, or when it is determined that no dealer store has a historical service record of the target user, the order of the target user is assigned to the dealer store with the highest order assignment priority.
8. A store push system characterized by comprising: The method comprises a data acquisition module, a profiling module, an analysis module, a calculation module, and a pushing module. The data acquisition module is configured to acquire user behavior data of a target user from an application program of a user terminal, and acquire user basic data of the target user from an external platform in real time through a preset application programming interface. The profiling module is configured to integrate the user behavior data and the user basic data to obtain integrated data, and construct a profile of the target user based on the integrated data. The analysis module is configured to analyze the profile of the target user to obtain a consumption ability and a brand preference of the target user. The calculation module is configured to calculate a matching priority of the target user and each store based on the consumption ability and the brand preference, and a preset traffic matching algorithm. The pushing module is configured to push one or more stores with the highest matching priority to the target user.
9. A terminal device, comprising: The computer readable storage medium comprises a stored computer program, wherein the computer program controls a device in which the computer readable storage medium is located to execute the store pushing method of any one of claims 1 to 5, or the store order assignment method of claim 6 or 7 when the computer program is running.
10. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored computer program, wherein the computer program controls a device in which the computer readable storage medium is located to execute the store pushing method of any one of claims 1 to 5, or the store order assignment method of claim 6 or 7 when the computer program is running.