A method and device for recalling ride-sharing orders

Abstract

The present application provides a method and device for recalling ride-sharing orders, wherein the method includes: obtaining an itinerary issued by a target car owner; encoding the itinerary according to a preset coding rule to obtain a first code; matching a preset number of order codes with the highest similarity to the first code from a vector similarity search database as a target order code set; searching for user orders corresponding to each order code in the target order code set, and pushing them to the target car owner as a target order set. The above solution solves the existing problem of being unable to accurately and efficiently match driver and passenger orders, and achieves the technical effect of accurately and efficiently matching driver and passenger orders to improve the conversion rate of ride-sharing orders.

Description

Technical Field

[0001] The present application belongs to the field of Internet technology, and in particular relates to a method and device for recalling a ride-sharing order. Background Art

[0002] With the continuous development of Internet technology, people are increasingly using the Internet to meet their various life needs. Through taxi-hailing platforms, websites, ride-sharing platforms, etc., car owners can post their itineraries to find passengers, and passengers can also post their itineraries to find car owners, thus completing ride-sharing trips based on the Internet.

[0003] However, there is no effective solution yet for how to accurately and efficiently match ride-sharing driver and passenger orders. Summary of the Invention

[0004] The purpose of this application is to provide a method and device for recalling ride-sharing orders, so as to accurately and efficiently match driver and passenger orders, thereby effectively improving the conversion rate of ride-sharing orders.

[0005] This application provides a method and device for recalling ride-sharing orders, which is implemented as follows:

[0006] A method for recalling a ride-sharing order, the method comprising:

[0007] Obtain the itinerary published by the target vehicle owner;

[0008] Encoding the itinerary according to a preset encoding rule to obtain a first code;

[0009] Matching a preset number of order codes that have the highest similarity to the first code from a vector similarity search database as a target order code set;

[0010] Search for user orders corresponding to each order code in the target order code set, and push the order as the target order set to the target car owner.

[0011] In one embodiment, the vector similarity search database is obtained as follows:

[0012] Obtain historical order completion data from the target platform;

[0013] Sort the orders in the historical order completion data according to the order completion order of each vehicle owner to obtain a sorting result;

[0014] According to the sorting results, each order is treated as a graph node, and the same graph nodes are treated as overlapping nodes for association processing to form a topological graph structure;

[0015] Encoding the orders corresponding to each node in the topological graph structure according to the preset encoding rule to obtain the order code of each graph node;

[0016] The order code of each graph node and the association relationship data of each graph node are converted into a node vector, and stored in the vector similarity search database.

[0017] In one embodiment, converting the order code of each graph node and the association relationship data of each graph node into a node vector and storing the vector similarity search database includes:

[0018] Performing random walks on the topological graph structure to form multiple sequential sequences;

[0019] Based on the formed sequential sequence, the association relationship data of each graph node is obtained;

[0020] The order code of each graph node and the association relationship data of each graph node are converted into a node vector, and stored in the vector similarity search database.

[0021] In one embodiment, encoding the itinerary according to a preset encoding rule to obtain a first code includes:

[0022] Acquire multiple dimensions of information from the itinerary, wherein the multiple dimensions of information include: price, starting point distance, ending point distance, departure time difference, starting point longitude and latitude, and ending point longitude and latitude;

[0023] Convert the plurality of dimensional information into coded values ​​according to a preset conversion relationship;

[0024] The encoding values ​​converted from the multiple dimensional information are arranged in order to obtain the first encoding.

[0025] In one embodiment, searching for user orders corresponding to each order code in the target order code set and pushing the order as the target order set to the target vehicle owner includes:

[0026] Searching for user orders corresponding to each order code in the target order code set as the target order set;

[0027] Sorting the target order set according to the degree of convenience with the itinerary issued by the target vehicle owner to obtain an order sorting result;

[0028] According to the order sorting result, the target order set is pushed to the target vehicle owner.

[0029] In one embodiment, the itinerary issued by the target vehicle owner is a ride-sharing itinerary.

[0030] A ride-sharing order recall device, comprising:

[0031] The acquisition module is used to obtain the itinerary published by the target vehicle owner;

[0032] An encoding module, configured to encode the itinerary in accordance with a preset encoding rule to obtain a first code;

[0033] A matching module, configured to match a preset number of order codes having the highest similarity to the first code from a vector similarity search database as a target order code set;

[0034] The push module is used to search for user orders corresponding to each order code in the target order code set and push them to the target car owner as the target order set.

[0035] In one embodiment, the push module includes:

[0036] A search unit, configured to search for user orders corresponding to each order code in the target order code set as the target order set;

[0037] A sorting unit, configured to sort the target order set according to the degree of convenience with the itinerary issued by the target vehicle owner, to obtain an order sorting result;

[0038] A push unit is used to push the target order set to the target vehicle owner according to the order sorting result.

[0039] An electronic device comprises a processor and a memory for storing instructions executable by the processor, wherein the steps of the above method are implemented when the processor executes the instructions.

[0040] A computer-readable storage medium stores computer instructions, which implement the steps of the above method when executed.

[0041] The method and device for recalling ride-sharing orders provided in this application encode the itinerary issued by the target car owner according to the preset coding rules to obtain a first code, and then match a preset number of order codes with the highest similarity to the first code from the vector similarity search database as the target order code set, and then search for the user orders corresponding to each order code in the target order code set, and push them to the target car owner as the target order set. That is, by encoding the itinerary and matching it with each coding vector in the vector similarity database, a code with a high correlation is obtained, and then the order corresponding to the code is matched in the order library, and pushed to the car owner as the target order. The above scheme solves the existing problem of not being able to accurately and efficiently match driver and passenger orders, and achieves the technical effect of accurately and efficiently matching driver and passenger orders to improve the conversion rate of ride-sharing orders. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 This is a method flow chart of an embodiment of the ride-sharing order recall method provided by this application;

[0044] Figure 2 This is a schematic diagram of the topological structure based on a complete sequence provided by this application;

[0045] Figure 3 This is a schematic diagram of the model structure of an embodiment of the order recall system provided by this application;

[0046] Figure 4 It is a logical diagram of the random walk provided by this application;

[0047] Figure 5 This is a hardware structure block diagram of an electronic device for a ride-sharing order recall method according to an embodiment of the present invention;

[0048] Figure 6 This is a structural block diagram of an embodiment of the ride-sharing order recall device provided in this application. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0050] Considering the low recommendation efficiency of existing ride-sharing driver-passenger order matching, in this example, the itinerary is encoded and matched with each encoding vector in the vector similarity database to obtain the required highly correlated code. The order corresponding to the code is then matched in the order database and pushed to the car owner as the target order. The above solution solves the existing problem of inability to accurately and efficiently match driver-passenger orders, achieving the technical effect of accurately and efficiently matching driver-passenger orders to improve the completion conversion rate of ride-sharing.

[0051] Figure 1It is a method flow chart of an embodiment of a ride-sharing order recall method described in the present application. Although the present application provides method operation steps or device structures as shown in the following embodiments or drawings, more or fewer operation steps or module units may be included in the method or device based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure described in the embodiments of the present application and shown in the drawings. When the method or module structure described is applied to an actual device or terminal product, it can be connected according to the method or module structure shown in the embodiment or drawings for sequential execution or parallel execution (for example, a parallel processor or a multi-threaded processing environment, or even a distributed processing environment).

[0052] Specifically, such as Figure 1 As shown, the ride-sharing order recall method provided in this application may include:

[0053] Step 101: Obtain the itinerary published by the target vehicle owner;

[0054] That is, for example, the car owner A publishes a travel itinerary "from the first district of city A to the second district of city B on a certain day of a certain month of a certain year".

[0055] Step 102: Encode the itinerary invoice according to a preset encoding rule to obtain a first code;

[0056] The itinerary can be encoded according to the pre-approved coding rules. Specifically, multiple dimensional information in the itinerary can be obtained, wherein the multiple dimensional information can include but is not limited to: price, starting point distance, end point distance, starting point longitude and latitude and longitude, and end point longitude and latitude; according to the preset conversion relationship, the multiple dimensional information is converted into coding values; the coding values ​​converted from the multiple dimensional information are arranged in order to obtain the first code.

[0057] For multiple codes in the vector similarity search database, completed orders in the historical data may be encoded in the same encoding manner.

[0058] For example, the coding rules can be: price is 10 yuan per level, ranging from 0 to 99; starting point distance is 2 km per level, ranging from 0 to 99; end point distance is 5 km per level, ranging from 0 to 99; departure time difference is 30 minutes per level, ranging from 0 to 99; starting point longitude and latitude are encoded according to H3 resolution 6; end point longitude and latitude are encoded according to H3 resolution 6.

[0059] Table 1 below shows information for five orders:

[0060] Table 1

[0061]

[0062]

[0063] After encoding order 1, the encoding values ​​shown in Table 2 can be obtained:

[0064] Table 2

[0065]

[0066] Correspondingly, after encoding the above five orders, the encoding results shown in Table 3 below can be obtained:

[0067] Table 3

[0068]

[0069]

[0070] Step 103: Matching a preset number of order codes having the highest similarity to the first code from a vector similarity search database as a target order code set;

[0071] The vector similarity search database can store multiple order codes obtained through pre-encoding training. Specifically, considering that historical data can be analyzed to establish the relationship between order codes, more accurate orders can be pushed to car owners. In this example, the historical order relationship is expanded in a graph structure manner. For example, the historical order completion data in the target platform can be obtained; each order in the historical order completion data is sorted according to the order completion order of each car owner to obtain the sorting result; according to the sorting result, each order is treated as a graph node, and the same graph nodes are treated as overlapping nodes for association processing to form a topological graph structure; the orders corresponding to each node in the topological graph structure are encoded according to the preset encoding rules to obtain the order code of each graph node; the order code of each graph node and the association relationship data of each graph node are converted into node vectors and stored in the vector similarity search database.

[0072] During implementation, the order codes of the graph nodes and the association relationship data of the graph nodes are converted into node vectors and stored in the vector similarity search database, which may include: performing random walks on the topological graph structure to form multiple sequential sequences; obtaining the association relationship data of the graph nodes based on the formed sequential sequences; converting the order codes of the graph nodes and the association relationship data of the graph nodes into node vectors, and storing them in the vector similarity search database.

[0073] By integrating hundreds of millions of orders on the platform, we can select orders that appear more than a preset number of times. For example, we can filter out orders that appear less than three times and remove them as outliers. We then use orders with three or more occurrences as the basis for the database, reducing the impact of a small number of sudden orders on the overall matching results. To this end, taking the five orders mentioned above as an example, after arranging them in the order in which the drivers completed their orders, we can obtain the following historical order sequence for driver 1: Order 1 -> Order 2 -> Order 3, which can be abbreviated as A->B->C; and for driver 2: Order 2 -> Order 4 -> Order 5, which can be abbreviated as B->D->E.

[0074] By connecting the complete single sequences in the form of a graph, we can get the following Figure 2 In the topology shown, because both Driver 1 and Driver 2 completed Order 2, the orders of Driver 1 and Driver 2 are linked through Order 2. By expanding the graph in this way, a large topology can be obtained, achieving an orderly association between orders.

[0075] By performing a random walk on the topology graph, we can generate new completed order sequences, for example: Order 1 -> Order 2 -> Order 4, or Order 1 -> Order 2 -> Order 4 -> Order 5. This means that the completed order sequence can be expanded using historical orders, generating more training elements, or matching elements, for matching the driver's trips to corresponding orders. This is primarily due to the fact that, since a driver can accept Order 1, Order 2, and Order 3, it's also possible for them to accept Order 1, Order 2, and Order 4. This effectively expands the database.

[0076] When expanding the database, order codes are used as graph nodes. Identical codes represent identical orders and correspond to the same node in the graph. New completed order sequences are also concatenated and stored using the order codes. Accordingly, when matching, the order codes are obtained from the database. For example, Milvus can be used to calculate the TopK similarity order codes stored. Once these codes are obtained, the passenger order pool can be used to match the user's order.

[0077] Step 104: Search for user orders corresponding to each order code in the target order code set, and push the order as the target order set to the target vehicle owner.

[0078] When pushing a target order set to a target vehicle owner, the user orders corresponding to each order code in the target order code set can be searched to form the target order set. The target order set can then be sorted according to the degree of convenience relative to the itinerary issued by the target vehicle owner to obtain an order sorting result. The target order set can then be pushed to the target vehicle owner based on the order sorting result. Specifically, the orders can be pushed to the target vehicle owner in descending order of convenience, allowing the target vehicle owner to more quickly determine the orders they wish to accept. Furthermore, orders can be pushed to the target vehicle owner using a group order approach. Specifically, based on the relationship between each order in the order set and the itinerary itinerary, a determination is made as to whether there are any orders that could form a group order. These group orders are then pushed to the target vehicle owner. For example, if a vehicle owner is traveling from City A to City B, passing through City C, and one order in the order set is from City A to City C and another is from City C to City B, these two orders can be pushed as a combined order to the target vehicle owner for selection.

[0079] The itinerary posted by the target car owner mentioned above is a ride-sharing itinerary.

[0080] In the above example, the itinerary issued by the target car owner is encoded according to the preset coding rules to obtain a first code, and then a preset number of order codes with the highest similarity to the first code are matched from the vector similarity search database as the target order code set, and then the user orders corresponding to each order code in the target order code set are searched and pushed to the target car owner as the target order set. That is, by encoding the itinerary and matching it with each coding vector in the vector similarity database, a code with a high correlation is obtained, and then the order corresponding to the code is matched in the order library, and pushed to the car owner as the target order. The above solution solves the existing problem of not being able to accurately and efficiently match driver and passenger orders, and achieves the technical effect of accurately and efficiently matching driver and passenger orders to improve the completion conversion rate of ride-sharing.

[0081] The above method is described below in conjunction with a specific embodiment. However, it should be noted that this specific embodiment is only for better illustrating the present application and does not constitute an improper limitation to the present application.

[0082] In this example, an order recall system is provided, which can be used as Figure 3As shown, the car owner posts an order to Milvus, which stores multiple coded data obtained through training of a graph recall algorithm model based on historical order data. Milvus searches for the top k order codes that match the order. Then, it matches the orders corresponding to these k order codes from the passenger order pool in ES (ElasticSearch, a highly scalable and open source full-text search and analysis engine that can store, search, and analyze massive amounts of data in near real time). The order is then sorted in the sorting system, and the sorted results are output to the car owner. This solution enables driver-passenger matching recommendations for ride-sharing. By introducing order codes and a graph recall algorithm, the efficiency of transaction conversion can be effectively improved.

[0083] The purpose of the graph recall algorithm is to recall more high-quality orders by discovering order sequences that were not originally in the completed order sequence based on the correlation between graph nodes, thereby improving the order recall rate.

[0084] That is, during implementation, the order code of each graph node and the association relationship data of each graph node can be converted into a node vector and stored in the vector similarity search database, which may include: performing a random walk on the topological graph structure to form multiple sequential sequences; obtaining the association relationship data of each graph node based on the formed sequential sequences; converting the order code of each graph node and the association relationship data of each graph node into a node vector, and storing it in the vector similarity search database.

[0085] By integrating hundreds of millions of orders on the platform, we can select orders that appear more than a preset number of times. For example, we can filter out orders that appear less than three times and remove them as outliers. We then use orders with three or more occurrences as the basis for the database, reducing the impact of a small number of sudden orders on the overall matching results. To this end, taking the five orders mentioned above as an example, after arranging them in the order in which the drivers completed their orders, we can obtain the following historical order sequence for driver 1: Order 1 -> Order 2 -> Order 3, which can be abbreviated as A->B->C; and for driver 2: Order 2 -> Order 4 -> Order 5, which can be abbreviated as B->D->E.

[0086] By connecting the complete single sequences in the form of a graph, we can get the following Figure 2 In the topology shown, because both Driver 1 and Driver 2 completed Order 2, the orders of Driver 1 and Driver 2 are linked through Order 2. By expanding the graph in this way, a large topology can be obtained, achieving an orderly association between orders.

[0087] By performing a random walk on the topology graph, we can generate new completed order sequences, for example: Order 1 -> Order 2 -> Order 4, or Order 1 -> Order 2 -> Order 4 -> Order 5. This means that the completed order sequence can be expanded using historical orders, generating more training elements, or matching elements, for matching the driver's trips to corresponding orders. This is primarily due to the fact that, since a driver can accept Order 1, Order 2, and Order 3, it's also possible for them to accept Order 1, Order 2, and Order 4. This effectively expands the database.

[0088] When expanding the database, order codes are used as graph nodes. Identical codes represent identical orders and correspond to the same node in the graph. New completed order sequences are also concatenated and stored using the order codes. Accordingly, when matching, the order codes are obtained from the database. For example, Milvus can be used to calculate the TopK similarity order codes stored. Once these codes are obtained, the passenger order pool can be used to match the user's order.

[0089] For passenger orders, it is necessary to discover homogeneous network structures, such as Figure 4 The following is a schematic diagram of the principle of random walk. It is necessary to determine the probability of jumping to each node x (x1, x2 and x3) after jumping from node t to the current node v:

[0090] π vx =α pq (t,x)×w vx

[0091] in,

[0092] Among them, α is Figure 4As shown, parameter p is the return parameter. The smaller p, the more likely the random walk will return to node t, and the algorithm tends to favor structure. Parameter q is the in-out parameter. The smaller q, the more likely the random walk will reach distant nodes, and the algorithm tends to favor homogeneity. By adjusting the random walk weight, the graph recall results can be balanced between network homogeneity and structural equivalence. Network homogeneity refers to the fact that the embeddings (a method of converting discrete variables into continuous vector representations) of nodes with similar distances should be as similar as possible. To detect order homogeneity, q can be controlled to a relatively small value. An embedding uses a low-dimensional vector to represent an object, such as a word, a product, or a movie. The property of an embedding vector is that objects corresponding to similar vectors have similar meanings, reflecting the potential relationships between objects.

[0093] After generating more sequences through random walks, the skip-gram algorithm can be used for training. Each order code can generate an embedding vector. For example, a 128-dimensional vector can be generated for each order code.

[0094] The above solution can effectively improve the car owner's order-taking experience and order conversion rate.

[0095] The method embodiments provided in the above embodiments of the present application can be executed in a mobile terminal, a computer terminal, a processor, a server or a similar computing device. Taking running on an electronic device as an example, Figure 5 This is a hardware structure diagram of an electronic device for a ride-sharing order recall method provided by this application. Figure 5 As shown, the electronic device 10 may include one or more (only one is shown in the figure) processors 02 (the processor 02 may include but is not limited to a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 04 for storing data, and a transmission module 06 for communication functions. It will be understood by those skilled in the art that Figure 5 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 5 More or fewer components than shown, or with Figure 5 Different configurations shown.

[0096] The memory 04 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the ride-sharing order recall method in the embodiment of the present application. The processor 02 executes various functional applications and data processing by running the software programs and modules stored in the memory 04, that is, the ride-sharing order recall method of the above-mentioned application is realized. The memory 04 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 04 may further include a memory remotely located relative to the processor 02, and these remote memories can be connected to the electronic device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0097] The transmission module 06 is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by the communication provider of the electronic device 10. In one embodiment, the transmission module 06 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission module 06 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0098] At the software level, the above-mentioned ride-sharing order recall device can be used as follows: Figure 6 Shown, including:

[0099] Acquisition module 601, used to obtain the itinerary issued by the target vehicle owner;

[0100] An encoding module 602 is configured to encode the itinerary in accordance with a preset encoding rule to obtain a first code;

[0101] A matching module 603 is configured to match a preset number of order codes having the highest similarity to the first code from a vector similarity search database as a target order code set;

[0102] The push module 604 is used to search for user orders corresponding to each order code in the target order code set, and push the orders as the target order set to the target vehicle owner.

[0103] In one embodiment, the push module 604 may include: a search unit for searching for user orders corresponding to each order code in the target order code set as a target order set; a sorting unit for sorting the target order set according to the degree of convenience with the itinerary issued by the target vehicle owner to obtain an order sorting result; and a push unit for pushing the target order set to the target vehicle owner according to the order sorting result.

[0104] In one embodiment, the vector similarity search database may store a plurality of order codes obtained through pre-coding training. Specifically, the vector similarity search database may be obtained as follows:

[0105] S1: Obtain historical order completion data from the target platform;

[0106] S2: Sort the orders in the historical order completion data according to the order completion order of each vehicle owner to obtain a sorting result;

[0107] S3: According to the sorting result, each order is treated as a graph node, and the same graph nodes are treated as overlapping nodes for association processing to form a topological graph structure;

[0108] S4: Encode the order corresponding to each node in the topological graph structure according to the preset encoding rule to obtain the order code of each graph node;

[0109] S5: Convert the order code of each graph node and the association relationship data of each graph node into a node vector, and store the vector vector into the vector similarity search database.

[0110] In one embodiment, converting the order code of each graph node and the association relationship data of each graph node into a node vector and storing them in the vector similarity search database may include: performing a random walk on the topological graph structure to form multiple sequential sequences; obtaining the association relationship data of each graph node based on the formed sequential sequences; converting the order code of each graph node and the association relationship data of each graph node into a node vector and storing them in the vector similarity search database.

[0111] In one embodiment, the itinerary is encoded according to a preset encoding rule to obtain a first code, which may be: obtaining multiple dimensional information in the itinerary, wherein the multiple dimensional information includes: price, starting point distance, end point distance, starting point longitude and latitude and longitude, and end point longitude and latitude; converting the multiple dimensional information into coding values ​​according to a preset conversion relationship; arranging the coding values ​​converted from the multiple dimensional information in order to obtain the first code.

[0112] In one embodiment, the itinerary issued by the target vehicle owner may be a ride-sharing itinerary.

[0113] The embodiments of the present application also provide a specific implementation of an electronic device that can implement all the steps in the ride-sharing order recall method in the above embodiment. The electronic device specifically includes the following contents: a processor, a memory, a communication interface, and a bus; wherein the processor, the memory, and the communication interface communicate with each other through the bus; the processor is used to call the computer program in the memory, and when the processor executes the computer program, all the steps in the ride-sharing order recall method in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0114] Step 1: Obtain the itinerary published by the target car owner;

[0115] Step 2: Encode the itinerary in accordance with a preset encoding rule to obtain a first code;

[0116] Step 3: Match a preset number of order codes with the highest similarity to the first code from the vector similarity search database as the target order code set;

[0117] Step 4: Find the user orders corresponding to each order code in the target order code set, and push them to the target car owner as the target order set.

[0118] From the above description, it can be seen that the embodiment of the present application encodes the itinerary issued by the target car owner according to the preset coding rules to obtain a first code, and then matches a preset number of order codes with the highest similarity to the first code from the vector similarity search database as the target order code set, and then searches for the user orders corresponding to each order code in the target order code set, and pushes them to the target car owner as the target order set. That is, by encoding the itinerary and matching it with each coding vector in the vector similarity database, a code with a high correlation is obtained, and then the order corresponding to the code is matched in the order library, and pushed to the car owner as the target order. The above scheme solves the existing problem of not being able to accurately and efficiently match driver and passenger orders, and achieves the technical effect of accurately and efficiently matching driver and passenger orders to improve the completion conversion rate of ride-sharing.

[0119] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all steps of the ride-sharing order recall method in the above embodiments. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the computer program implements all steps of the ride-sharing order recall method in the above embodiments. For example, when the processor executes the computer program, the following steps are implemented:

[0120] Step 1: Obtain the itinerary published by the target car owner;

[0121] Step 2: Encode the itinerary in accordance with a preset encoding rule to obtain a first code;

[0122] Step 3: Match a preset number of order codes with the highest similarity to the first code from the vector similarity search database as the target order code set;

[0123] Step 4: Find the user orders corresponding to each order code in the target order code set, and push them to the target car owner as the target order set.

[0124] From the above description, it can be seen that the embodiment of the present application encodes the itinerary issued by the target car owner according to the preset coding rules to obtain a first code, and then matches a preset number of order codes with the highest similarity to the first code from the vector similarity search database as the target order code set, and then searches for the user orders corresponding to each order code in the target order code set, and pushes them to the target car owner as the target order set. That is, by encoding the itinerary and matching it with each coding vector in the vector similarity database, a code with a high correlation is obtained, and then the order corresponding to the code is matched in the order library, and pushed to the car owner as the target order. The above scheme solves the existing problem of not being able to accurately and efficiently match driver and passenger orders, and achieves the technical effect of accurately and efficiently matching driver and passenger orders to improve the completion conversion rate of ride-sharing.

[0125] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, the hardware + program embodiments are generally similar to the method embodiments, so their description is relatively simple. For relevant portions, refer to the description of the method embodiments.

[0126] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0127] Although the present application provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative work. The order of steps listed in the embodiments is only one way of executing the steps among many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, in a parallel processor or multi-threaded processing environment).

[0128] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, an in-vehicle human-computer interaction device, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0129] Although the present specification embodiment provides the method operation steps as described in the embodiment or flow chart, more or less operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiment is only one way in the order of execution of many steps and does not represent a unique execution order. When the device or terminal product in practice is executed, it can be performed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (such as a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "comprise", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or equipment including a series of elements not only include those elements, but also include other elements not clearly listed, or also include elements inherent to such process, method, product or equipment. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or equipment including the elements.

[0130] For the convenience of description, the above devices are described in terms of functions divided into various modules. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same or multiple software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0131] Those skilled in the art will also appreciate that, in addition to implementing the controller in pure computer-readable program code, it is entirely possible to implement the same functionality by logically programming the method steps in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, embedded microcontrollers, and the like. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered structures within the hardware component. Alternatively, the devices for implementing various functions can be considered both software modules implementing the method and structures within the hardware component.

[0132] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0136] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0137] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0138] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0139] Embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. Embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In distributed computing environments, program modules may be located in local and remote computer storage media, including storage devices.

[0140] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between the various embodiments can be referenced across them. Each embodiment focuses on the differences from the other embodiments. In particular, since the system embodiments are generally similar to the method embodiments, their description is relatively simple. For relevant parts, reference can be made to the description of the method embodiments. Throughout this specification, reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the embodiments in this specification. In this specification, the schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and integrate the different embodiments or examples, and features of different embodiments or examples, described in this specification, without conflict.

[0141] The above description is merely an example of the embodiments of this specification and is not intended to limit the embodiments of this specification. For those skilled in the art, various modifications and variations of the embodiments of this specification are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of this specification shall be included within the scope of the claims of the embodiments of this specification.

Claims

1. A method for recalling a ride-sharing order, characterized in that: The method comprises: Obtain the itinerary published by the target vehicle owner; Encoding the itinerary according to a preset encoding rule to obtain a first code; Matching a preset number of order codes that have the highest similarity to the first code from a vector similarity search database as a target order code set; Searching for user orders corresponding to each order code in the target order code set, and pushing the order as the target order set to the target vehicle owner; The vector similarity search database is obtained as follows: Obtain historical order completion data from the target platform; Sort the orders in the historical order completion data according to the order completion order of each vehicle owner to obtain a sorting result; According to the sorting results, each order is treated as a graph node, and the same graph nodes are treated as overlapping nodes for association processing to form a topological graph structure; Encoding the orders corresponding to each node in the topological graph structure according to the preset encoding rule to obtain the order code of each graph node; Converting the order code of each graph node and the association relationship data of each graph node into a node vector, and storing the vector vector vector in the vector similarity search database; The process of converting the order code of each graph node and the association relationship data of each graph node into a node vector and storing the vector vector vector into the vector similarity search database includes: Performing random walks on the topological graph structure to form multiple sequential sequences; Based on the formed sequential sequence, the association relationship data of each graph node is obtained; The order code of each graph node and the association relationship data of each graph node are converted into a node vector, and stored in the vector similarity search database.

2. The method according to claim 1, characterized in that Encoding the itinerary in accordance with a preset encoding rule to obtain a first code includes: Acquire multiple dimensions of information from the itinerary, wherein the multiple dimensions of information include: price, starting point distance, ending point distance, departure time difference, starting point longitude and latitude, and ending point longitude and latitude; Convert the plurality of dimensional information into coded values ​​according to a preset conversion relationship; The encoding values ​​converted from the multiple dimensional information are arranged in order to obtain the first encoding.

3. The method according to claim 1, characterized in that Searching for user orders corresponding to each order code in the target order code set and pushing the order as the target order set to the target vehicle owner includes: Searching for user orders corresponding to each order code in the target order code set as the target order set; Sorting the target order set according to the degree of convenience with the itinerary issued by the target vehicle owner to obtain an order sorting result; According to the order sorting result, the target order set is pushed to the target vehicle owner.

4. The method according to any one of claims 1 to 3, characterized in that The itinerary published by the target car owner is a ride-sharing itinerary.

5. A ride-sharing order recall device, characterized in that: include: The acquisition module is used to obtain the itinerary published by the target vehicle owner; An encoding module, configured to encode the itinerary in accordance with a preset encoding rule to obtain a first code; A matching module, configured to match a preset number of order codes having the highest similarity to the first code from a vector similarity search database as a target order code set; A push module, configured to search for user orders corresponding to each order code in the target order code set, and push the orders as the target order set to the target vehicle owner; The vector similarity search database is obtained as follows: Obtain historical order completion data from the target platform; Sort the orders in the historical order completion data according to the order completion order of each vehicle owner to obtain a sorting result; According to the sorting results, each order is treated as a graph node, and the same graph nodes are treated as overlapping nodes for association processing to form a topological graph structure; Encoding the orders corresponding to each node in the topological graph structure according to the preset encoding rule to obtain the order code of each graph node; Converting the order code of each graph node and the association relationship data of each graph node into a node vector, and storing the vector vector vector in the vector similarity search database; The process of converting the order code of each graph node and the association relationship data of each graph node into a node vector and storing the vector vector vector into the vector similarity search database includes: Performing random walks on the topological graph structure to form multiple sequential sequences; Based on the formed sequential sequence, the association relationship data of each graph node is obtained; The order code of each graph node and the association relationship data of each graph node are converted into a node vector, and stored in the vector similarity search database.

6. The device according to claim 5, characterized in that The push module includes: A search unit, configured to search for user orders corresponding to each order code in the target order code set as the target order set; A sorting unit, configured to sort the target order set according to the degree of convenience with the itinerary issued by the target vehicle owner, to obtain an order sorting result; A push unit is used to push the target order set to the target vehicle owner according to the order sorting result.

7. An electronic device comprising a processor and a memory for storing instructions executable by the processor, characterized in that: When the processor executes the instructions, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instructions are executed, the steps of the method according to any one of claims 1 to 4 are implemented.

Images