Object recommendation method and device, medium and program product

Abstract

The embodiment of the invention relates to an object recommendation method and device, a medium and a program product. The method comprises the steps of obtaining target session data corresponding to a target customer; wherein the target session data comprises a latest communication record between the target customer and an object recommender; determining a target demand tag corresponding to the target customer based on the target session data; determining a target recommendation object corresponding to the target customer based on the target demand tag; and providing an object recommendation service for the target customer based on the target recommendation object. According to the embodiment of the invention, the object currently required by the target customer can be timely and accurately recommended, and the user satisfaction is well improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to an object recommendation method, device, medium and program product. Background Art

[0002] In the service industry, merchants or brokers are often required to recommend the objects that customers need. Taking the real estate brokerage industry as an example, the link of house recommendation is a key link that affects customer satisfaction and facilitates transactions. The inventor has found through research that the existing house recommendation service is not good and user satisfaction is not high. On the one hand, it is difficult to recommend houses to users in a timely manner, and brokers need to spend a certain amount of time and energy to search; on the other hand, the reason is that the houses automatically recommended to users by the model may not be the houses required by users. Other objects that need to be recommended besides houses are similar, so there is an urgent need for a new object recommendation technology. Summary of the invention

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides an object recommendation method, device, medium and program product.

[0004] An embodiment of the present disclosure provides an object recommendation method, which includes: obtaining target conversation data corresponding to a target customer; wherein the target conversation data includes the latest communication record between the target customer and an object recommender; determining a target demand tag corresponding to the target customer based on the target conversation data; determining a target recommendation object corresponding to the target customer based on the target demand tag; and providing an object recommendation service for the target customer based on the target recommendation object.

[0005] Optionally, determining the target demand tag corresponding to the target customer based on the target session data includes: determining a real-time demand tag corresponding to the target customer based on the target session data; retrieving a pre-stored historical demand tag corresponding to the target customer; wherein the historical demand tag is determined based on the historical session data corresponding to the target customer; and determining the target demand tag corresponding to the target customer based on the real-time demand tag and the historical demand tag.

[0006] Optionally, determining the real-time demand label corresponding to the target customer based on the target session data includes: generating the real-time demand label corresponding to the target customer using a preset target network model based on the target session data and specified label format information.

[0007] Optionally, determining the target demand tag corresponding to the target customer based on the real-time demand tag and the historical demand tag includes: searching for a first tag from the historical demand tags based on the real-time demand tag; wherein the first tag is a tag that conflicts with the real-time demand tag; and deduplicating tags based on tags in the historical demand tags except the first tag and the real-time demand tag to obtain the target demand tag corresponding to the target customer.

[0008] Optionally, determining the target recommended object corresponding to the target customer based on the target demand label includes: obtaining the target candidate object corresponding to the target customer based on specific information of the target customer; screening out a first recommended object that matches the target demand label from the target candidate objects; and determining the target recommended object corresponding to the target customer based on the first recommended object.

[0009] Optionally, the specific information of the target customer includes specific behavior information of the target customer; obtaining the target candidate object corresponding to the target customer based on the specific information of the target customer includes: obtaining a first candidate object corresponding to the target customer based on the specific behavior information of the target customer; searching for similar customers corresponding to the target customer, and obtaining a second candidate object corresponding to the target customer based on the specific behavior information of the similar customers; wherein the similarity between the specific behavior information of the similar customers and the specific behavior information of the target customer is higher than a preset similarity threshold; and obtaining the target candidate object corresponding to the target customer based on the first candidate object and the second candidate object.

[0010] Optionally, determining the target recommended object corresponding to the target customer based on the first recommended object includes: when the number of objects of the first recommended object is higher than a preset number threshold, using the first recommended object as the target recommended object corresponding to the target customer; when the number of objects of the first recommended object is not higher than the preset number threshold, screening a second recommended object that matches the target demand label from an object library, and using the first recommended object and the second recommended object together as the target recommended objects corresponding to the target customer.

[0011] Optionally, providing an object recommendation service to the target customer based on the target recommended object includes: displaying the object information of the target recommended object on the client interface of the object recommender; and sharing the designated object to the client of the target customer in response to receiving a sharing request from the object recommender for a designated object among the target recommended objects.

[0012] An embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the object recommendation method provided by the embodiment of the present disclosure.

[0013] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the object recommendation method provided by the embodiment of the present disclosure.

[0014] The embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements the object recommendation method provided by the embodiments of the present disclosure.

[0015] The above technical solution provided by the embodiment of the present disclosure can determine the target demand label of the target customer based on the target conversation data corresponding to the target customer. Since the target conversation data contains the latest communication record between the target customer and the object recommender, the target demand label determined based on this can also more accurately reflect the current latest demand of the target customer, thereby efficiently determining the target recommendation object based on the target demand label and providing object recommendation service. The above method can timely and accurately recommend the object currently required by the target customer based on the conversation data of the target customer, which helps to improve user satisfaction.

[0016] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A flowchart of an object recommendation method provided by an embodiment of the present disclosure;

[0020] Figure 2 A schematic diagram of generating a demand tag provided in an embodiment of the present disclosure;

[0021] Figure 3A schematic diagram of a process for generating a target recommendation object provided by an embodiment of the present disclosure;

[0022] Figure 4 A schematic diagram of an interface provided by an embodiment of the present disclosure;

[0023] Figure 5 A schematic diagram of the structure of an object recommendation device provided by an embodiment of the present disclosure;

[0024] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0027] The inventor has found through research that the object recommendation service provided by the related technology is difficult to satisfy users. Taking the object as a house source, for example, it is time-consuming and laborious for the broker to find a house based on communication with the customer, and the customer has to wait for a relatively long time. Moreover, the houses obtained by manual screening are not comprehensive. Although some technologies have introduced a network model that can recommend houses, the network model mainly relies on historical behavior data such as the customer's browsing history and the number of appointments for house viewing. This method has great limitations. On the one hand, the reason is that only some customers have enough historical behavior data for model analysis. For customers who have no historical behavior data or have less historical behavior data, it is difficult to use the model to recommend houses; on the other hand, the reason is that the historical behavior data itself has a certain lag and cannot reflect the changes in customer wishes in a timely manner. In many cases, the houses recommended by the model based on historical behavior data are not the houses currently needed by the customer.

[0028] In order to improve at least one of the above problems and enhance customer satisfaction with the object recommendation service, the embodiments of the present disclosure provide an object recommendation method, device, medium and program product, which can timely and accurately recommend the objects currently needed by customers. For ease of understanding, a detailed explanation is given below.

[0029] Figure 1The present invention provides a flowchart of an object recommendation method provided by an embodiment of the present invention. The method can be performed by an object recommendation device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method mainly includes the following steps S102 to S108:

[0030] Step S102, obtaining target conversation data corresponding to the target customer; wherein the target conversation data includes the latest communication record between the target customer and the object recommender.

[0031] The objects mentioned in the embodiments of the present disclosure include but are not limited to commodities such as housing and vehicles, and may also include tourist attractions, courses, etc. Any object that a customer needs to recommend can be used, and there is no restriction here. The object recommender can be a person who recommends the required object to the customer, such as a merchant, a broker, a planner, etc., and there is no restriction here. The target customer and the object recommender can communicate in text through a specific application or web page, so as to obtain a communication record in text form. The target customer and the object recommender can also communicate in voice through a specific application, a web page or a phone, and the communication audio is converted into a communication record in text form for subsequent processing. The embodiments of the present disclosure can obtain the latest communication record between the target customer and the object recommender, that is, obtain the most recent communication record from the current moment, so as to know the latest needs of the target customer. In order to facilitate processing, the target session data corresponding to the target customer can be generated based on the latest communication record. The target session data can not only include the latest communication record, but also include the communication time corresponding to the latest communication record, the ID information of the target customer, the ID information of the object recommender, and the ID information of the target session data. Specifically, the latest communication records collected can be fused and processed so that the target conversation data is presented as a five-tuple data in a unified format (such as: customer ID, communication time, communication content, object recommender ID, conversation ID), which is more convenient for subsequent processing. In practical applications, the target conversation data can also include historical communication records between the target customer and the object recommender, such as N communication records before the latest communication record between the target customer and the object recommender, so that the historical needs of the target customer can be combined with the current needs for comprehensive analysis.

[0032] Step S104: determining a target demand tag corresponding to the target customer based on the target session data.

[0033] For example, the target session data can be analyzed with the help of a network model to extract keywords in the target session data, convert the keywords based on a specified tag format, or perform similarity matching between the keywords and tags in a tag library, thereby obtaining target demand tags corresponding to the target customers. The number of target demand tags can be one or more, which is not limited here. By converting session data into formatted demand tags, user demands can be presented concisely and clearly, making it easier to quickly retrieve objects that meet user demands later.

[0034] Step S106: determining the target recommendation object corresponding to the target customer based on the target demand tag.

[0035] In actual applications, objects in the object library can be attached with their own feature tags. Taking the house as an example, the feature tags of the house may include tags indicating the house type, the floor of the house, the geographical location of the house, the orientation of the house, the price of the house, etc. Therefore, the target recommended objects that match the customer's target demand tags can be filtered. For example, the target recommended objects corresponding to the target demand tags can be directly searched from the object library, and / or the target recommended objects can be filtered out from the objects recommended by the model based on the target demand tags. In the above manner, the feature tags attached to the obtained target recommended objects usually contain at least one target demand tag, which can better meet the user's needs.

[0036] Step S108, based on the target recommended object, provide the target customer with an object recommendation service. In actual applications, the target recommended object can be directly provided to the target customer, or the object recommender can further manually screen the target recommended object to provide the object that best meets the current needs of the target customer. The specific settings can be flexible and are not limited here.

[0037] In summary, the above method can timely and accurately recommend the objects currently needed by the target customers based on the target customers' session data, which helps to improve user satisfaction.

[0038] In some implementations, step S104, i.e., the step of determining the target demand tag corresponding to the target customer based on the target session data, can be performed with reference to the following steps a to c:

[0039] Step a: determining the real-time demand tags corresponding to the target customers based on the target session data.

[0040] Since the target conversation data includes the latest communication record, the target customer's demand label determined based on the latest communication record is a real-time demand label. In some specific implementation examples, the target conversation data and the specified label format information can be used to generate the target customer's corresponding real-time demand label using the preset target network model. For example, the target conversation data and the model prompt information can be input into the target network model to generate the real-time demand label corresponding to the latest communication record in the target conversation data with the help of the target network model, wherein the model prompt information can include the specified label format information, which is used to instruct the model to convert the target conversation data into the corresponding demand label based on the label format information. The label format information can be used to constrain the number of label words, the form of label content, etc. In order to enable the label output by the model to be a standardized label that can be directly used later, in some implementations, the label format information can also include label library information, so that the target network model can directly search for the demand label matching the target conversation data from the label library based on the label library information. In other implementations, the output label of the target network model can be standardized and adjusted to obtain a structured label that meets the requirements. For example, the output label of the target network model may only be extracted by the target network model based on keywords in the target session data, which does not meet the actual label requirements. Therefore, the output label can be matched with the label in the label library for similarity, and the label in the label library that matches the output label of the model (such as the label with the highest similarity) can be used as the target customer's demand label.

[0041] For ease of understanding, in some specific implementation examples, you can refer to Figure 2 The schematic diagram of generating a demand label is shown. The communication record between the customer and the object recommender can be processed by the record processing unit, such as aggregation and five-tuple construction, to obtain session data in the form of five-tuples, and then the session data and model prompt information are provided to the network model, so that the network model generates the demand label corresponding to the session data and stores it in the session label table. The previous demand labels of the target customer can be pre-stored in the session label table, and the real-time demand labels generated based on the latest communication records can also be automatically stored in the session label table after generation, so as to realize the dynamic update of the session label table. In actual applications, the real-time demand labels can be generated instantly based on the current communication records, and the object recommendation system can wait for the generation result of the real-time demand labels by polling, so as to be able to recommend the object that best meets the customer's needs in a timely and fast manner based on the latest acquired real-time demand labels.

[0042] Step b, retrieve the pre-stored historical demand tags corresponding to the target customer; wherein the historical demand tags are determined based on the historical conversation data corresponding to the target customer. The historical conversation data is obtained based on the historical communication records between the target customer and the object recommender, and the demand tags obtained based on the communication records before the latest communication record are the historical demand tags. The specific implementation method of determining the historical demand tags based on the historical conversation data can refer to the aforementioned Figure 2 The generation method of the demand tag shown is not described here. It is understandable that in actual application, the corresponding demand tag can be generated based on the communication record after each communication and stored in the conversation tag list corresponding to the target customer. When needed later, it can be directly retrieved from the conversation tag list corresponding to the target customer.

[0043] Step c, based on the real-time demand tag and the historical demand tag, determine the target demand tag corresponding to the target customer. The disclosed embodiment can combine both the historical demand tag and the real-time demand tag to comprehensively determine the target demand tag that can more accurately and comprehensively present the target customer's needs. In some specific implementation examples, step c can be performed with reference to the following steps c1 to c2:

[0044] Step c1, based on the real-time demand tag, search for the first tag from the historical demand tags; wherein the first tag is a tag that conflicts with the real-time demand tag. For example, if the historical demand tag indicates that a house in District A is needed, and the real-time demand tag indicates that a house in District B is needed, then the address demand tag in the historical demand tag conflicts with the real-time demand tag. For another example, if the historical demand tag indicates that a high floor is needed, and the real-time demand tag indicates that a low floor is needed, then the floor demand tag in the historical demand tag conflicts with the real-time demand tag.

[0045] Step c2, performing deduplication processing based on the tags other than the first tag in the historical demand tags and the real-time demand tags, to obtain the target demand tags corresponding to the target customers.

[0046] When the historical demand label contains a first label that conflicts with the real-time demand label, the user's latest demand should be used as the standard, so the first label can be removed, and only the labels other than the first label in the historical demand label are retained. Considering that there may be duplicate labels in the labels other than the first label in the historical demand label and the real-time demand label, deduplication processing can be performed to obtain the target demand label. For ease of understanding, it is assumed that the real-time demand labels include: A, B, C1 and D; and the historical demand labels include A, C2, E and F; among them, C1 conflicts with C2, and C2 is the aforementioned first label. At this time, after the first label is removed and deduplication processing is performed, the target demand labels include: A, B, C1, D, E and F. In the above manner, the target demand label obtained can not only present the user's latest current needs, but also eliminate the past needs that are inconsistent with the current needs, better cope with the situation of changes in customer needs, and can supplement the needs that are not mentioned in the current communication but mentioned in the historical communication, thereby presenting the user's object needs more accurately and comprehensively.

[0047] In some implementations, the aforementioned step S106, i.e., the step of determining the target recommendation object corresponding to the target customer based on the target demand tag, can be performed with reference to the following steps A to C:

[0048] Step A, based on the specific information of the target customer, obtain the target candidate object corresponding to the target customer. In some specific implementation examples, the specific information of the target customer includes the specific behavior information of the target customer, and the specific behavior information includes but is not limited to the target customer's browsing operations, collection operations and other behavior records on the target application or target page, and may also include the number of visits of the target customer, etc. Taking the object as an example, the specific behavior information may include house viewing behavior information, and the house viewing behavior information may include but is not limited to the target customer's house viewing operations, house collection operations and other online house viewing behaviors on the target application or target page, and may also include information on offline house viewing behaviors such as the number of appointments for house viewing and house viewing trajectories. Step A can be performed with reference to the following steps A1 to A3:

[0049] Step A1, based on the specific behavior information of the target customer, obtain the first candidate object corresponding to the target customer. In actual application, the specific behavior information of the target customer can be input into a preset first network model, and the first network model is used to search the object library for an object matching the specific behavior information as the first candidate object.

[0050] Step A2, searching for similar customers corresponding to the target customer, and obtaining a second candidate object corresponding to the target customer based on specific behavior information of the similar customers; wherein the similarity between the specific behavior information of the similar customers and the specific behavior information of the target customer is higher than a preset similarity threshold.

[0051] In order to provide the target customer with the object he needs as comprehensively as possible, and considering that the specific behavior information of the target customer may not be rich and the amount of information is small, the embodiment of the disclosure can also search for customers with similar specific behavior information to the target customer, that is, search for similar customers corresponding to the target customer, and search for corresponding objects as second candidate objects based on the specific behavior information of the similar customers. In this way, the candidate objects that can be recommended to the target customer can be effectively supplemented.

[0052] Step A3, based on the first candidate object and the second candidate object, obtain a target candidate object corresponding to the target customer. In some implementation examples, the first candidate object and the second candidate object can be used together as the target candidate object.

[0053] Step B: Filter out the first recommended object that matches the target demand label from the target candidate objects. It is understandable that the aforementioned target candidate objects are all objects recommended based on specific behavior information. The disclosed embodiment will further filter and process the target candidate objects in combination with the target demand label, thereby effectively ensuring that the obtained first recommended object meets the actual needs of the customer.

[0054] Step C, based on the first recommended object, determine the target recommended object corresponding to the target customer. In some implementation examples, the first recommended object can be directly used as the target recommended object. In other implementation examples, in order to improve customer satisfaction and allow customers to have more room to choose from the target recommended objects, the number of target recommended objects given to users is guaranteed to be higher than the preset number threshold as much as possible to avoid the situation where too few objects are recommended to users. In this case, step C can be performed with reference to the following steps C1 to C2:

[0055] Step C1: When the number of the first recommended object is higher than a preset number threshold, the first recommended object is used as a target recommended object corresponding to the target customer. The preset number threshold can be flexibly set according to demand and is not limited here.

[0056] Step C2, when the number of objects in the first recommended object is not higher than the preset number threshold, select the second recommended object that matches the target demand label from the object library, and use the first recommended object and the second recommended object together as the target recommended object corresponding to the target customer.

[0057] That is, when the first recommended object is insufficient, the second recommended object can be directly searched from the object library based on the target demand tag. In actual applications, each object in the object library is attached with a corresponding feature tag, and the second recommended object can be searched by matching the target demand tag with the object feature tag. In actual applications, if the feature tag of an object in the object library contains at least one of the target demand tags, or the similarity between the feature tag of an object and at least one of the target demand tags is higher than a preset threshold, the object can be considered to match the target demand tag. In addition, the feature tag of the second recommended object can be further restricted to not contain tags that conflict with the target demand tag.

[0058] Through the above methods, we can provide customers with target recommendations that meet their needs in a more comprehensive manner, ensure the diversity and accuracy of the recommendation results, and improve customer satisfaction.

[0059] For easier understanding, see Figure 3 A schematic diagram of a target recommendation object generation process is shown, which illustrates that a real-time demand tag can be obtained based on the latest communication record of the target customer, a historical demand tag can be obtained based on the historical communication record of the target customer, and a target demand tag can be obtained based on the real-time demand tag and the historical demand tag. In addition, it is also illustrated that a first candidate object can be obtained based on the specific behavior information of the target customer, a second candidate object can be obtained based on the specific behavior information of similar customers, and a target candidate object can be obtained based on the first candidate object and the second candidate object. Then, based on the target demand tag, the target candidate object can be screened to obtain the first recommended object. It can be further determined whether the number of the first recommended objects is higher than a preset number threshold. If so, the first recommended object can be directly used as the target recommended object corresponding to the target customer; if not, the second recommended object matching the target demand tag can be screened from the object library, and the first recommended object and the second recommended object can be used together as the target recommended objects corresponding to the target customer. Figure 3 The specific implementation methods of each step involved can refer to the above-mentioned related content and will not be repeated here. The target recommendation objects obtained by the above method are not only rich and comprehensive, but also can better meet the latest needs of customers, and comprehensively ensure that the recommended objects can effectively cover customer needs, thereby providing timely and accurate object recommendation services.

[0060] In some implementations, the aforementioned step S108, i.e., the step of providing an object recommendation service to the target customer based on the target recommendation object, can be performed with reference to the following steps 1 to 2:

[0061] Step 1: Display the object information of the target recommended object on the client interface of the object recommender. In addition, the target demand tag can also be displayed on the client interface of the object recommender. The specific setting can be flexible and is not limited here. For example, if the object is a house, the object recommender is the broker, that is, the house information of the target recommended house can be displayed on the client interface of the target broker.

[0062] Step 2: in response to receiving a sharing request from the target object recommender for a designated object among the target recommended objects, share the designated object to a client of the target customer.

[0063] It is understandable that the above-mentioned target recommended objects are objects recommended by the background based on the demand tags obtained from the communication records and the analysis of customer behavior information. The object recommender can further screen out the objects that the user is most likely to be interested in based on the target recommended objects and share them with customers first. Of course, the object recommender can also share all the target recommended objects with customers with one click, and there is no restriction here. In actual applications, a check control can be provided for the object recommender in the client interface of the object recommender, so that the object recommender can check the specified object from the target recommended objects and initiate a sharing request for the specified object. Based on the request, the server can share the specified object to the client of the target customer for the target customer to view.

[0064] For easier understanding, please refer to Figure 4 The interface diagram shown in the figure shows that the customer's demand tags can be generated based on the chat content between the broker and the customer, and the listings that meet the customer's current needs can be recommended. The demand tags and recommended listings can be presented on the broker's client interface. Furthermore, the listing recommendation system can also provide corresponding recommendation reasons for each recommended listing for the broker's reference. The broker can select the listing that best suits the customer from the recommended listings, and share the specified listing with the customer by triggering the one-click sharing control. It should be noted that Figure 4 This is for illustrative purposes only and should not be considered limiting. Figure 4 It can be seen that when the broker is chatting with the client, the broker can dynamically obtain recommended properties and share them with the client, and can respond to customer needs in real time, ensure the timeliness and accuracy of property recommendations, shorten the time it takes for customers to find ideal properties, greatly improve customer satisfaction with the property recommendation service, increase transaction opportunities, and better assist brokers in their work. Brokers no longer need to spend time and effort looking for the properties required by customers, thereby greatly improving brokers' work efficiency.

[0065] In actual applications, the operating status of the object recommendation system can be continuously monitored, such as data processing speed, label generation efficiency, etc., and customer feedback on the recommended objects can be collected in the future, so as to further optimize system algorithms such as label generation rules and object recommendation algorithms based on the feedback information. The object recommendation system can also be regularly updated and optimized based on monitoring results and user feedback to continuously improve the accuracy of object recommendations and customer satisfaction, and continuously improve the object recommendation service.

[0066] The above-mentioned object recommendation method provided by the embodiment of the present disclosure can integrate the communication records between the customer and the object recommender and artificial intelligence technology. Specifically, it can effectively integrate the unstructured data in the chat record and convert it into a structured tag that can present the customer's needs through a network model, which is more convenient for subsequent processing. Further, the customer's needs can be updated in real time based on the latest communication record, and a real-time demand tag can be generated, so as to ensure that the object recommendation system can provide the object that best meets the customer's current needs. By combining the real-time demand tag with the historical demand tag, it can be effectively guaranteed that the recommended object can meet the user's needs in a rich and comprehensive manner. In addition, by combining the user's house viewing behavior data and communication records for object recommendation, that is, based on the customer demand tag obtained from the communication record, the candidate objects obtained based on the house viewing behavior data are screened, and when the candidate objects obtained by screening are insufficient, the objects are further supplemented based on the house viewing demand tag, so as to provide customers with a variety of choices, and always ensure that the objects recommended to customers are in line with customer needs, and can flexibly respond to sudden changes in customer needs.

[0067] In summary, the object recommendation method provided by the embodiments of the present disclosure can realize real-time analysis of customers' object needs and provide accurate object recommendations in a timely manner, significantly improve the accuracy and timeliness of object recommendations, enhance customer satisfaction, and assist object recommenders to complete work tasks more efficiently.

[0068] Corresponding to the aforementioned object recommendation method, the embodiment of the present disclosure further provides an object recommendation device, Figure 5 FIG. 1 is a schematic diagram of a structure of an object recommendation device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated in an electronic device, such as Figure 5 As shown, the object recommendation device includes:

[0069] The session data acquisition module 502 is used to acquire the target session data corresponding to the target customer; wherein the target session data includes the latest communication record between the target customer and the object recommender.

[0070] A demand tag determining module 504 is used to determine a target demand tag corresponding to the target customer based on the target session data;

[0071] A recommendation object determination module 506 is used to determine a target recommendation object corresponding to the target customer based on the target demand tag;

[0072] The recommendation service providing module 508 is used to provide object recommendation service for the target customer based on the target recommendation object.

[0073] The above device can timely and accurately recommend the objects currently needed by the target customers based on the conversation data of the target customers, which helps to improve the user satisfaction.

[0074] In some embodiments, the demand tag determination module 504 is specifically used to: determine the real-time demand tag corresponding to the target customer based on the target session data; retrieve the pre-stored historical demand tag corresponding to the target customer; wherein the historical demand tag is determined based on the historical session data corresponding to the target customer; and determine the target demand tag corresponding to the target customer based on the real-time demand tag and the historical demand tag.

[0075] In some implementations, the demand tag determination module 504 is specifically configured to generate a real-time demand tag corresponding to the target customer using a preset target network model based on the target session data and specified tag format information.

[0076] In some embodiments, the demand tag determination module 504 is specifically used to: based on the real-time demand tag, search for a first tag from the historical demand tags; wherein the first tag is a tag that conflicts with the real-time demand tag; and perform deduplication processing based on tags in the historical demand tags other than the first tag and the real-time demand tag to obtain a target demand tag corresponding to the target customer.

[0077] In some embodiments, the recommendation object determination module 506 is specifically used to: obtain the target candidate object corresponding to the target customer based on the specific information of the target customer; filter out the first recommendation object that matches the target demand label from the target candidate objects; and determine the target recommendation object corresponding to the target customer based on the first recommendation object.

[0078] In some embodiments, the specific information of the target customer includes specific behavior information of the target customer; the recommended object determination module 506 is specifically used to: obtain a first candidate object corresponding to the target customer based on the specific behavior information of the target customer; search for similar customers corresponding to the target customer, and obtain a second candidate object corresponding to the target customer based on the specific behavior information of the similar customers; wherein the similarity between the specific behavior information of the similar customers and the specific behavior information of the target customer is higher than a preset similarity threshold; and obtain a target candidate object corresponding to the target customer based on the first candidate object and the second candidate object.

[0079] In some embodiments, the recommendation object determination module 506 is specifically used to: when the number of objects of the first recommendation object is higher than a preset number threshold, use the first recommendation object as the target recommendation object corresponding to the target customer; when the number of objects of the first recommendation object is not higher than the preset number threshold, filter out a second recommendation object that matches the target demand label from the object library, and use the first recommendation object and the second recommended object together as the target recommendation object corresponding to the target customer.

[0080] In some embodiments, the recommendation service providing module 508 is specifically used to: display the object information of the target recommended object on the client interface of the object recommender; in response to receiving a sharing request from the object recommender for a designated object among the target recommended objects, share the designated object to the client of the target customer.

[0081] The object recommendation device provided in the embodiments of the present disclosure can execute the object recommendation method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0082] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device embodiment can refer to the corresponding process in the method embodiment, and will not be repeated here.

[0083] An embodiment of the present disclosure provides an electronic device, which includes: a storage device on which a computer program is stored; and a processing device for executing the computer program in the storage device to implement the steps of any method in the present disclosure.

[0084] Reference below Figure 6, which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0085] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0086] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0087] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program carried on a non-transitory computer-readable medium, the computer program comprising a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0088] In addition to the above-mentioned methods and devices, the embodiments of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, cause the processor to perform the method provided by the embodiments of the present disclosure. The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present disclosure, the programming languages ​​including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as an independent software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0089] In addition, the embodiment of the present disclosure may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the object recommendation method provided by the embodiment of the present disclosure.

[0090] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0091] The embodiment of the present disclosure also provides a computer program product, including a computer program / instruction, which implements the object recommendation method in the embodiment of the present disclosure when executed by a processor.

[0092] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0093] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0094] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0095] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0096] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0097] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An object recommendation method, characterized in that: include: Acquire target conversation data corresponding to the target customer; wherein the target conversation data includes the latest communication record between the target customer and the object recommender; Determine a target demand tag corresponding to the target customer based on the target session data; Based on the target demand tag, determining the target recommendation object corresponding to the target customer; Based on the target recommended object, an object recommendation service is provided for the target customer.

2. The method according to claim 1, characterized in that The determining the target demand tag corresponding to the target customer based on the target session data includes: Determine a real-time demand tag corresponding to the target customer based on the target session data; Retrieving a pre-stored historical demand tag corresponding to the target customer; wherein the historical demand tag is determined based on the historical session data corresponding to the target customer; Based on the real-time demand tag and the historical demand tag, a target demand tag corresponding to the target customer is determined.

3. The method according to claim 2, characterized in that The determining the real-time demand tag corresponding to the target customer based on the target session data includes: Based on the target session data and the specified label format information, a real-time demand label corresponding to the target customer is generated using a preset target network model.

4. The method according to claim 2, characterized in that: The determining, based on the real-time demand tag and the historical demand tag, a target demand tag corresponding to the target customer includes: Based on the real-time demand tag, searching for a first tag from the historical demand tags; wherein the first tag is a tag that conflicts with the real-time demand tag; Based on the tags in the historical demand tags except the first tag and the real-time demand tags, deduplication processing is performed to obtain the target demand tag corresponding to the target customer.

5. The method according to claim 1, characterized in that The determining, based on the target demand tag, a target recommendation object corresponding to the target customer includes: Based on the specific information of the target customer, obtaining target candidate objects corresponding to the target customer; Filtering out a first recommended object that matches the target requirement label from the target candidate objects; Based on the first recommended object, a target recommended object corresponding to the target customer is determined.

6. The method according to claim 5, characterized in that The specific information of the target customer includes specific behavior information of the target customer; and obtaining a target candidate object corresponding to the target customer based on the specific information of the target customer includes: Based on the specific behavior information of the target customer, obtaining a first candidate object corresponding to the target customer; Find similar customers corresponding to the target customer, and obtain a second candidate object corresponding to the target customer based on the specific behavior information of the similar customers; wherein the similarity between the specific behavior information of the similar customers and the specific behavior information of the target customer is higher than a preset similarity threshold; Based on the first candidate object and the second candidate object, a target candidate object corresponding to the target customer is obtained.

7. The method according to claim 5, characterized in that The determining, based on the first recommended object, a target recommended object corresponding to the target customer includes: When the number of the first recommended objects is higher than a preset number threshold, the first recommended objects are used as target recommended objects corresponding to the target customers; When the number of objects of the first recommended object is not higher than the preset number threshold, a second recommended object matching the target demand tag is selected from the object library, and the first recommended object and the second recommended object are used together as target recommended objects corresponding to the target customer.

8. The method according to claim 1, characterized in that The providing the target customer with an object recommendation service based on the target recommended object includes: Displaying the object information of the target recommended object on the client interface of the object recommender; In response to receiving a sharing request from the object recommender for a designated object among the target recommended objects, the designated object is shared with a client of the target customer.

9. An electronic device, characterized in that: The electronic device comprises: a storage device having a computer program stored thereon; A processing device, used to execute the computer program in the storage device to implement the steps of the object recommendation method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the object recommendation method described in any one of claims 1 to 8.

11. A computer program product, characterized in that The invention comprises a computer program, which implements the object recommendation method according to any one of claims 1 to 8 when being executed by a processor.

Images