CN115330498B

CN115330498B - Data processing method and related device in man-machine interactive shopping service system

Info

Publication number: CN115330498B
Application number: CN202211256326.1A
Authority: CN
Inventors: 龙方舟; 韦武杰
Original assignee: Shenzhen Renma Interactive Technology Co Ltd
Current assignee: Shenzhen Renma Interactive Technology Co Ltd
Priority date: 2022-10-14
Filing date: 2022-10-14
Publication date: 2023-01-24
Anticipated expiration: 2042-10-14
Also published as: CN115330498A

Abstract

The embodiment of the application provides a method and a related device for processing data in a man-machine interaction shopping service system, which are applied to a user terminal, wherein the method comprises the following steps: performing intention recognition on a voice command input by a user at a user terminal to obtain an intention recognition result as a shopping intention; confirming the type of the object indicated by the current instruction event of the user according to the intention identification result; if the type of the object is a single product, acquiring first recommendation information of the single product corresponding to the unique brand name for the user, and generating a first recommendation list; and if the type of the object is a product category, acquiring corresponding second recommendation information for the user according to the consumption record of the user, and generating a second recommendation list. According to the method, on the basis of carrying out intention recognition on the voice of the user and obtaining the shopping requirement of the user, the consumption habit of the user is combined to generate a proper recommendation scheme for the user, and the voice interaction experience of the user is improved.

Description

Data processing method and related device in man-machine interactive shopping service system

Technical Field

The present application relates to the general data processing technology field of the internet industry, and in particular, to a method and a related device for processing data in a human-computer interactive shopping service system.

Background

With the continuous development of science and technology, voice assistants are also frequently appeared in our daily life. By using the voice assistant, a user can acquire information, services and the like by speaking and interacting with a computer, and the voice interaction does not need to replace touch interaction, but makes the interaction between the user and the computer simpler and natural in some scenes.

Aiming at the shopping requirements of users, the voice interaction function displayed in the prior art often has the defect that the product recommendation does not conform to the consumption habits of the users. More importantly, the voice assistant function shown in the prior art can only help the user jump to the specific shopping software, and the time spent in the jumping process is long, thereby affecting the use experience of the user. Therefore, how to provide an intelligent product recommendation method more conforming to the consumption habits of users for the users based on the voice interaction function is a problem which needs to be solved urgently by technical personnel in the field.

Disclosure of Invention

The embodiment of the application provides a data processing method and a related device in a man-machine interaction shopping service system, which can perform accurate intention identification according to voice information input by a user, and then generate a personalized recommendation scheme for the user according to the consumption habit (or consumption record) of the user, and are beneficial to improving the voice interaction experience of the user.

In a first aspect, an embodiment of the present application provides a method and a related device for processing data in a human-computer interaction shopping service system, which are applied to a user terminal, where the human-computer interaction shopping service system may include the user terminal and a voice server, the user terminal is provided with a human-computer interaction voice service engine, and the user terminal may communicate with the voice server through the human-computer interaction voice service engine, and the method may include the following steps:

calling a man-machine interaction voice service engine to respond to a wake-up instruction input by a user and displaying a voice service interface, wherein the wake-up instruction can be used for waking up the voice service function of a user terminal; and (c) a second step of,

receiving a voice instruction input by a user, and generating text information according to the voice instruction; and (c) a second step of,

performing user intention identification on the text information to obtain an intention identification result as a shopping intention;

determining the type of the object indicated by the current time of the user according to the intention recognition result, wherein the type can comprise a product category or a single product, the product category refers to the category of the product, and the single product refers to the product with the restricted product name;

if the type of the object indicated by the current event of the user is determined to be a single product, judging whether the single product corresponds to a unique brand name;

if the single product is judged to correspond to the unique brand name, acquiring at least one piece of first recommendation information from the plurality of shopping application servers through the voice server according to the product name of the single product and the brand name of the single product, and generating a first recommendation list for the user according to the at least one piece of first recommendation information;

if the single product does not correspond to the unique brand name, determining that the type of the object indicated by the current event of the user is a product category;

if the type of the object indicated by the current instruction event of the user is determined to be a product category, acquiring consumption records of the user for the product category from a plurality of shopping application servers through a voice server, wherein the consumption records can include consumption amount, and generating a second recommendation list for the user according to the consumption records, wherein the second recommendation list comprises at least one piece of second recommendation information;

and presenting the first recommendation list or the second recommendation list on a voice service interface.

In a second aspect, an embodiment of the present application provides a user terminal, where the user terminal may include the following: the device comprises a control module, a calculation module, an interaction module, a judgment module and a communication module;

the control module can be used for calling a man-machine interaction voice service engine to respond to a wake-up instruction input by a user and displaying a voice service interface, and the wake-up instruction can be used for waking up the voice service function of the user terminal;

the interaction module can be used for receiving a voice instruction input by a user;

the calculation module can be used for generating text information according to the voice instruction;

the computing module can also be used for carrying out user intention identification on the text information to obtain an intention identification result as a shopping intention;

the calculation module can be further used for determining the type of the object indicated by the current instruction event of the user according to the intention recognition result, wherein the type can include a product category or a single product, the product category refers to the category of the product, and the single product refers to the product with the product name constrained;

the judging module can be used for judging whether the single product corresponds to a unique brand name or not when the type of the object indicated by the current instruction event of the user is determined to be the single product;

the communication module can be used for acquiring at least one piece of first recommendation information from a plurality of shopping application servers through a voice server according to the product name of the single product and the brand name corresponding to the single product when the single product corresponds to the unique brand name;

the calculation module can be further used for generating a first recommendation list for the user according to the at least one piece of first recommendation information;

the calculation module can be further used for determining that the type of the object indicated by the current event of the user is a product category when the single product does not correspond to the unique brand name;

the communication module can be further used for acquiring consumption records of the user aiming at the product category from the plurality of shopping application servers through the voice server when the type of the object indicated by the current instruction event of the user is determined to be the product category, wherein the consumption records comprise consumption money;

the calculation module can be further used for generating a second recommendation list for the user according to the consumption record, wherein the second recommendation list comprises at least one piece of second recommendation information;

the control module may be further configured to present the first recommendation list or the second recommendation list to a voice service interface.

In a third aspect, an embodiment of the present application provides a user terminal, where the user terminal may include the following components: a processor, a memory, and a bus;

the processor and the memory are connected by a bus, wherein the memory is adapted to store a set of program codes and the processor is adapted to call the program codes stored in the memory to perform the method according to the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including:

the computer readable storage medium has stored therein instructions which, when run on a computer, implement the method according to the first aspect.

It can be seen that, in the embodiment of the application, the user terminal in the human-computer interaction shopping service system performs intention identification on the voice instruction (the voice instruction with the shopping intention) input by the user, the method of the embodiment of the application determines the type of the object designated by the user in the voice instruction according to the keyword in the voice instruction input by the user, and then adopts different generation modes of the recommendation list according to different object types, so that the generated recommendation list can accurately meet the purchase demand of the user. In addition, when the recommendation list is generated, consumption records of the user on a plurality of shopping applications (or shopping platforms) are considered, so that the recommendation information (or products) in the recommendation list can be ensured to accord with the consumption habits of the user, the shopping requirements of the user can be met, and the shopping experience of the user can be further improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

FIG. 1 is a schematic diagram of an architecture of a human-computer interaction shopping service system according to an embodiment of the present application;

FIG. 2 is a flowchart illustrating a method for processing data in a human-computer interaction shopping service system according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a scenario of generating a first recommendation list according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a scenario for generating a user consumption representation according to an embodiment of the present application;

fig. 5 is a schematic composition diagram of a user terminal according to an embodiment of the present application;

fig. 6 is a schematic composition diagram of another user terminal according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.

The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different elements and not for describing a particular sequential order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, result, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein may be combined with other embodiments.

Referring to fig. 1, fig. 1 is a schematic diagram illustrating an architecture of a human-machine interaction shopping service system provided by a method according to an embodiment of the present application. As shown in FIG. 1, the Man-machine interactive shopping service system 10 may comprise a user terminal 110 and a voice server 120, wherein the user terminal 110 and the voice server 120 are connected in a communication manner. The user terminal 110 includes a man-machine interaction voice service engine, and the user terminal 110 may respond to a wake-up command input by a user by calling the man-machine interaction voice service engine and display a voice service interface. Wherein the wake-up instruction may be used to wake up a voice service function of the user terminal 110. The user terminal 110 may be further configured to receive a voice instruction input by a user, and generate text information according to the voice instruction; the user intention can be identified for the text information, and the intention identification result is the shopping intention; determining the type of the object indicated by the current instruction event of the user according to the intention recognition result, wherein the type can comprise a product category or a single product, the product category refers to the category of the product, and the single product refers to the product with the constrained product name; the method can also be used for judging whether the single product corresponds to the unique brand name or not when the corresponding type indicated by the current instruction event of the user is determined to be the single product; when the unique brand name corresponding to the single product is judged, at least one piece of first recommendation information is acquired from the multiple shopping application servers through the voice server 120 according to the product name of the single product and the brand name corresponding to the single product, and a first recommendation list is generated for the user according to the at least one piece of first recommendation information; the type of the object indicated by the current event of the user can be determined as a product category when the single product is judged not to correspond to the unique brand name; when it is determined that the type of the object indicated by the current instruction event of the user is a product category, obtaining consumption records of the user for the product category from the multiple shopping application servers through the voice server 120, where the consumption records may include consumption amount, and generating a second recommendation list for the user according to the consumption records, where the second recommendation list includes at least one piece of second recommendation information; the first recommendation list or the second recommendation list may also be presented to a voice service interface. The user terminal 110 may also be referred to as a client terminal, and the user terminal 110 may be fixed or mobile. The specific form of the mobile phone can be a mobile phone (mobile phone), a tablet computer (Pad), a computer with a wireless transceiving function, a wearable terminal device and the like. The operating system of the PC-side terminal device, such as a kiosk, may include, but is not limited to, operating systems such as Linux system, unix system, windows series system (e.g., windows xp, windows 7, etc.), mac OS X system (operating system of apple computer), and the like. The operating system of the terminal device at the mobile terminal, such as a smart phone, may include but is not limited to an operating system such as an android system, an IOS (operating system of an apple phone), a Window system, and the like.

Further, the voice server 120 may be a server, a server cluster composed of several servers, or a cloud computing service center. One voice server 120 may correspond to a plurality of user terminals 110 at the same time, or the man-machine interactive shopping service system 10 according to the embodiment of the present invention may include a plurality of voice servers 120, where each voice server 120 corresponds to one or more user terminals 110.

Based on this, the embodiment of the present application provides a method for processing data in a human-computer interaction shopping service system, and the following describes the embodiment of the present application in detail with reference to the accompanying drawings.

Referring to fig. 2, fig. 2 is a flowchart illustrating a method for processing data in a human-computer interaction shopping service system according to an embodiment of the present application, where the method is applied to a user terminal 110 in the human-computer interaction shopping service system 10 shown in fig. 1, the human-computer interaction shopping service system 10 may include the user terminal 110 and a voice server 120, the user terminal 110 is provided with a human-computer interaction voice service engine, and the user terminal 110 communicates with the voice server 120 through the human-computer interaction voice service engine; the method may comprise the steps of:

s201, calling a man-machine interaction voice service engine to respond to a wake-up instruction input by a user and displaying a voice service interface.

The wake-up instruction may be used to wake up a voice service function of the ue.

For example, the wake-up instruction may be that the user sets the preset word as "voice assistant" by issuing a voice instruction to call the preset word, and when the user issues a voice instruction similar to "voice assistant", i want to buy the product 1 "or" voice assistant ", and helps me open the software 1", the user terminal displays a voice service interface and performs intention recognition on the voice instruction (or text information corresponding to the voice instruction) of the user. The awakening instruction can also be an operation instruction for the user to enter the voice service software, and when the user clicks the voice service software on the desktop of the user terminal, the voice service software is entered to display a voice service interface so as to provide a voice service function for the user. The wake-up instruction may also be a shortcut key operation instruction, such as double-clicking a user terminal screen, long-pressing a power key, or drawing a preset pattern on the screen.

S202, receiving the voice instruction input by the user, and generating text information according to the voice instruction.

Possibly, generating text information according to a voice instruction input by a user, wherein the text information can be obtained by carrying out voice recognition by the user terminal according to audio corresponding to the voice instruction; or the user terminal sends the audio corresponding to the voice instruction to the voice server, the voice server performs text conversion on the audio to obtain corresponding text information, and then the text information is sent to the user terminal.

S203, identifying the user intention of the text information, and obtaining an intention identification result as a shopping intention.

Specifically, obtaining the intention-to-recognize result from the text information may include the steps of: and performing intention identification on the text information to obtain an intention identification result, wherein the intention identification result can comprise at least one event triple, and extracting a main triple capable of representing the event type from the intention identification result as a core event of the currently processed text information.

The event triple is matched with a reference triple in an event library, the event triple is composed of a semantic/syntactic relation and two event nodes, the event nodes can comprise a first event node and a second event node, the time node is a single entity, the reference triple is composed of a semantic/syntactic relation and two reference nodes, the reference nodes can comprise a first reference node and a second reference node, the reference nodes are a set composed of entities with a common reference relation, and the entities refer to words or phrases. Wherein, the matching of the event triple with the reference triple in the event library means: the semantic/syntactic relations of the event triples and the reference triples are the same, a first event node of the event triples belongs to the first reference node, and a second event node of the event triples belongs to the second reference node.

Illustratively, a triplet may be characterized in the form of { R (a, B) }, where a refers to an entity at one end of the triplet, B refers to an entity at the other end of the triplet, and P refers to a semantic/syntactic relationship between entities at both ends of the triplet, and the semantic/syntactic relationship is directional, and the triplet { P (a, B) }maybe understood as a semantic/syntactic relationship P between a and B. For example, semantic recognition is performed on a statement "i want to buy the electronic watch", and triplets thereof are available as { celebrity subject (i, want) }, { dependency (want, buy) }, { direct object (buy, electronic watch) }. In the following description, a simple description is given by taking a triple { nominal subject (i, want) } as an example, where "i" is an entity a, "want" is an entity B, and "nominal subject" is a semantic/syntactic relation P, and the direction is pointed to "want" by "i", and the meaning represented by: the nominal subject of "want" is "me".

The semantic/syntactic relations are the same, which means that the relation types and the directions of the relation types of the connection relations between entities at two ends of the triplets are the same, for example, the triplets (1) { noun subject (minuscule, walking) }, and the triplets (2) { noun subject (minired, swimming) }, at this time, the semantic/syntactic relations P of the triplets (1) and (2) are both "noun subject", and the directions are both that the entity B points to the entity a, and then the semantic/syntactic relations of the triplets (1) and (2) are determined to be the same.

To assist understanding, the matching mechanism of event triples and reference triples is illustrated below by way of a specific example. There is a generic self-learning system for semantic recognition in the server, which has a library of events that have undergone a lot of self-learning and historical training, and there is at least one reference triple in the library, a and B of { P (a, B) }, both in the form of sets, and the entities in each set have a common reference relationship, e.g., a can be a set of (twilight + piny red + piny flower + he + she), wherein the entities have a common reference relationship, and similarly, B can be a set of (walk + walk), so P is a "nominal subject" and the direction is pointed to a by B. At this time, if one event triple extracted from the user history sentence input by the user is { noumenon (xiaoming, walking) }, it is determined that the event triple is matched with the reference triple, and the semantic recognition result includes the event triple { noumenon (xiaoming, walking) }. It is understood that the currently processed user sentence may include a plurality of entities, a plurality of semantic/syntactic relations and a plurality of event triples, and the above simple example is only used to assist understanding of the scheme disclosed in the embodiment of the present application, and does not constitute any limitation to the present application.

To assist understanding, the concept of a main triple is explained below by way of a specific example. For example, the currently processed user statement is: "i want to buy an umbrella to see a movie", a triple corresponding to the user statement has a noumenon subject (i, want) }, { move guest relationship (want, buy an umbrella) }, and then it can be analyzed that, of the two event triples, a triple capable of representing an event type is the { move guest relationship (want, buy an umbrella) }, and then the triple is determined to be a main triple, and further, according to the main triple, the core semantic meaning of the user statement, namely, "want to buy an umbrella", is determined, so that the intention result of the user is determined to be "want to buy an umbrella", and further, the object indicated by the current instruction event of the user is determined to be "an umbrella".

S204, determining the type of the object indicated by the current instruction event of the user according to the intention recognition result.

The above types may include a product category, which refers to a product type, or a monomer product, which refers to a product to which a product name is restricted.

Exemplary product types may be cell phone numbers, home office appliances, jewelry, footwear, clothing, skin care cosmetics, snacks or drinks, etc. The product to which the product name is restricted may be an electronic watch, a paper extraction, an umbrella, or the like.

And S205, if the type of the object indicated by the current instruction event of the user is determined to be the single product, judging whether the single product corresponds to the unique brand name.

In a possible implementation manner, if it is determined that the type of the object indicated by the current instruction event of the user is a single product, determining whether the single product corresponds to a unique brand name may include the following steps:

judging whether the current instruction event of the user comprises a brand name or not; and/or the presence of a gas in the atmosphere,

and judging whether the product name corresponding to the monomer product is a preset product name or not.

Wherein the preset product name represents a product name corresponding to the unique brand name.

Specifically, the user terminal may perform keyword extraction/matching on an object of the user's current instruction event, thereby determining a product name and/or a brand name.

For example, if the result obtained after the intention recognition of the user is "want to buy the charger of mobile phone brand 1", the object of the current command event of the user may be determined to be "the charger of mobile phone brand 1", and the "charger of mobile phone brand 1" may be determined to be a single product because the "charger of mobile phone brand 1" belongs to the lower classification of the product category of "mobile phone digital code". Then, the object is further disassembled to obtain keywords 'mobile phone brand 1' and 'charger', the type of the keyword 'mobile phone brand 1' can be determined as a brand name by matching the keywords 'mobile phone brand 1' and 'charger' with an information base (comprising a plurality of product names and brand names) in the voice server, and the type of the keyword 'charger' can be determined as a product name, so that the object of the current instruction event of the user can be judged as a single product corresponding to a unique brand name.

More, the information base of the voice server also stores a plurality of preset product names, and the preset product names generally refer to a specific product of a specific brand in daily life of people. For example, if a product 1 is a preset product name and the product 1 usually represents a "product 1 of brand 1" in daily life, when it is determined that an object of a current instruction event of a user is "want to buy the product 1", the keyword "product 1" can be obtained by further disassembling the object, and after matching with an information base of a voice server, the type of the "product 1" can be determined as the product name, because the product 1 is the preset product name, although the object does not include a keyword of a brand name class, the object of the current instruction event of the user can still be converted into "product 1 of brand 1" to be bought, and then the object of the current instruction event of the user is determined as a single product corresponding to a unique brand name.

According to the method, whether the object of the current instruction event of the user can refer to the single product corresponding to the unique brand name or not is judged by extracting the keywords and matching the keywords of the object of the current instruction event of the user.

S206, if the single product is judged to correspond to the unique brand name, obtaining at least one piece of first recommendation information from a plurality of shopping application servers through the voice server according to the product name of the single product and the brand name corresponding to the single product, and generating a first recommendation list for the user according to the at least one piece of first recommendation information.

Specifically, the method for the user terminal to obtain the first recommendation information from the plurality of shopping application services through the voice server may be: the voice server and the plurality of shopping application services have an authorization relationship in advance, the authorization relationship is used for acquiring relevant data/information in the shopping application servers, and the user terminal can acquire corresponding first recommendation information from the plurality of shopping application servers authorized for the voice server through the voice server. More, the pre-existing authorization relationship may be an authorization agreement that the voice server has reached according to a shopping account number authorized or bound by the user in the voice service software; the platform corresponding to the voice service software and the related shopping application platform can have a cooperative relationship, so that an existing authorization protocol exists. Possibly, the user terminal sends an information acquisition request to the voice server according to the shopping application installed and capable of running in the user terminal, the information acquisition request can include the name of the shopping application, then the voice server can establish protocol contact with the corresponding shopping application server according to the name of the shopping application, and after the voice server establishes protocol contact with the shopping application server, the user terminal can acquire the first recommendation information from the shopping application server through the voice server.

More specifically, the first recommendation information may include a purchase link of the product, a purchase channel corresponding to the purchase link (i.e., a corresponding shopping application), a price of the product, and product-related introduction information (which may include text introduction information and may also include image introduction information). In a possible implementation manner, if it is determined that the single product corresponds to the unique brand name, obtaining, by the voice server, at least one piece of first recommendation information from the plurality of shopping application servers according to the product name of the single product and the brand name corresponding to the single product, and generating a first recommendation list for the user according to the at least one piece of first recommendation information may include the following steps:

judging whether a first consumption record matched with the monomer product exists in a plurality of consumption records of the user, wherein matching refers to a consumption product name and a consumption brand name in the first consumption record, and the product name and the brand name corresponding to the monomer product are the same;

if the first consumption record exists, generating the first recommendation list according to the first consumption record, wherein the first recommendation information is related to the first consumption record;

and if the first consumption record does not exist, acquiring at least one piece of first recommendation information from a plurality of shopping application servers through the voice server, and generating a first recommendation list, wherein the first recommendation information is related to the single product.

For example, if the product 2 of the brand 1 indicated by the object of the current instruction event of the user is assumed, and the user terminal matches the consumption record 1 in the multiple consumption records of the user, and the product information corresponding to the consumption record 1 is the product 2 of the brand 1, the product purchase link corresponding to the consumption record 1 may be used as the first recommendation information, and is presented on the voice service interface according to the product purchase link corresponding to the consumption record 1.

Further, please refer to fig. 3, where fig. 3 is a schematic view of a scenario for generating a first recommendation list according to an embodiment of the present application. As shown in fig. 3, after the user inputs a wake-up command at the user terminal, the user terminal presents a voice service interface as shown in an interface 31, when the user inputs a voice command of "i want to buy a product 3 of brand 1" as shown in fig. 3, after the user terminal identifies and keyword extracts/matches through intention recognition, the brand name of the product required by the user is "brand 1" and the product name of the product is "product 3", and then a consumption record matching process as shown in a flow 32 is performed, it can be seen that consumption records 1 (channel 1, consumption time is 3/11/1) and consumption records 3 (channel 2, consumption time is 2029/6/3) are the same as the product required by the user in a plurality of consumption records of the user, both consumption records 1 and 3 are the first consumption record described above, then corresponding recommendation information 1 is generated according to consumption record 1, recommendation information 2 is generated according to consumption record 3, wherein, the recommendation information 1 is related to the link of the product corresponding to consumption record 1, the purchase information 2 is corresponding to the purchase information 3, and the recommendation information 1 is related to the purchase information 3, and the recommendation list is generated according to the most likely to the time of the purchase information of the user, and the list is the recommendation list of the product that the user is the most likely to be recommended to be arranged in the consumption record list 33 shown in the consumption record list, which the list of the user.

Possibly, for consumption record 1 and consumption record 3 in FIG. 3, they may also be ranked by the frequency of consumption by the user in different channels. For example, if the average consumption frequency of the user in the channel 1 is 3 times/year and the average consumption frequency of the user in the channel 2 is 127 times/year, the user terminal ranks the consumption record 3 at the first place and the consumption record 1 at the second place when generating the first recommendation list.

Possibly, for the case that there are a plurality of first consumption records, the consumption frequency of each first consumption record may also be used as a reference factor for the ranking of the first recommendation list.

More particularly, if the corresponding first consumption record does not exist, the user terminal may obtain the preset first recommendation information from the plurality of shopping application servers. For example, it is preset that the number of the first recommendation information is 3, the voice server and 3 shopping application servers (shopping application server 1, shopping application server 2 and shopping application server 3) have an authorization relationship, and if the brand name of a product required by the user is "brand 2" and the product name is "product 4", the user terminal may obtain, from each of the shopping application server 1, shopping application server 2 and shopping application server 3, a piece of first recommendation information about "product 4 of brand 2", where the screening condition of the first recommendation information may be a product price, a product sales volume, a product goodness rate, a store score, and the like, and is not limited herein; the user terminal may also obtain the first recommendation information only in the server of the preset shopping application of the user, and if the preset shopping application of the user is the shopping application 2, the user terminal may obtain 3 pieces of first recommendation information from the shopping application server 2 through the voice server, and the screening conditions of the first recommendation information may refer to the above.

It can be seen that the method in the embodiment of the present application can flexibly generate the recommendation list according to different consumption record matching situations. When the consumption records same as the products required by the user exist, the method of the embodiment of the application can preferentially recommend the purchase links corresponding to the same consumption records to the user, and is beneficial to better fitting the consumption habits and consumption preferences of the user; when the consumption record which is the same as that of the product required by the user does not exist, the method can select the proper recommendation information for the user by comparing the multiple factors (product price, product sales, good product rating, shop rating and the like), is favorable for ensuring the reliability of the recommendation information, and further ensures the voice interactive shopping experience of the user. More, the method of the embodiment of the application can reasonably sort the recommendation information according to the consumption habits (consumption time, consumption frequency and the like) of the users, and arrange the recommendation information most conforming to the consumption habits of the users above the recommendation list, so that the users can intuitively sense the difference of recommendation priorities among different recommendation information, and the method is beneficial to the users to determine more appropriate recommendation information.

And S207, if the monomer product is judged not to correspond to the unique brand name, determining that the type of the object indicated by the current event of the user is the product category.

And S208, if the type of the object indicated by the current instruction event of the user is determined to be the product category, acquiring consumption records of the user for the product category from the plurality of shopping application servers through the voice server, and generating a second recommendation list for the user according to the consumption records.

The consumption record may be a plurality of consumption records, which may include a consumption amount, and the second recommendation list includes at least one piece of second recommendation information. More, the consumption record may further include a consumption time, consumption product information including a consumption product name, a consumption brand name, and a consumption product category, and a consumption channel.

Specifically, the method in the embodiment of the application generates the consumption image of the user according to the consumption record of the user, then confirms the constraint condition of the corresponding second recommendation information according to the consumption image, and then obtains at least one piece of second recommendation information from the plurality of shopping application servers through the voice server according to the constraint condition, and the specific implementation steps of the method refer to the following method for example.

It should be noted that, based on the "authorization relationship between the voice server and the multiple shopping application servers" mentioned in the related embodiment of step S206, the user may obtain at least one second recommendation information from the multiple shopping application servers through the voice server, and the specific manner of the authorization relationship is not described herein again.

In a possible implementation manner, the user terminal may also search whether a consumption record of the product category exists in the multiple consumption records of the user, and if a consumption record identical to the product category required by the user exists, a purchase link corresponding to the consumption record may be used as the second recommendation information.

For example, if the product type required by the user is "usb disk" and the consumption record of the user includes "U disk of brand 3," the purchase link corresponding to "U disk of brand 3" may be used as the second recommendation information. More particularly, when different channels exist or a plurality of consumption records identical to the product types required by the user exist, the selection of the second recommendation information and the generation manner of the second recommendation list may refer to the selection of the first recommendation information and the generation manner of the first recommendation list, which is not described herein again.

In another possible implementation manner, if it is determined that the type of the object indicated by the current instruction event of the user is a product category, acquiring consumption records of the user for the product category from a plurality of shopping application servers through a voice server, and generating a second recommendation list for the user according to the consumption records, the method may include the following steps:

sending the product categories to a voice server, and acquiring a plurality of consumption records of a user through open interfaces of the voice server and a plurality of shopping application servers;

according to the consumption portrait of the user and the product category, at least one piece of second recommendation information is obtained from a plurality of shopping application servers through a voice server, a second recommendation list is generated for the user according to the at least one piece of second recommendation information, each piece of second recommendation information can comprise a product price and a purchase channel corresponding to the second recommendation information, and the consumption portrait is related to a plurality of consumption records of the user.

Wherein the consumption representation may include an average personal consumption amount of the user in at least one preset product category. Specifically, the method according to the embodiment of the application classifies a plurality of consumption records of a user according to product categories, calculates the personal average consumption amount of the user in each product category according to the consumption amount in the consumption records, and then generates a relation graph or a relation table of "product category-personal average consumption amount". The relationship graph or table may be an expression of a user consumption representation. Moreover, the method of the embodiment of the application can also divide the product categories into secondary product categories, so that the user consumption portrait with more detailed classification can be calculated.

More specifically, like the first recommendation information, the second recommendation information may include a purchase link of the product, a purchase channel corresponding to the purchase link (i.e., a corresponding shopping application), a price of the product, and product-related introduction information (which may include text introduction information and may also include image introduction information).

For example, referring to fig. 4, fig. 4 is a schematic view of a scene for generating a user consumption image. As shown in fig. 4, after determining that the type of the object of the current instruction event of the user is a product class (assuming that the type corresponding to the object 1 in fig. 4 is the product class), the user terminal 40 obtains a plurality of consumption records from the shopping application server 42, the shopping application server 43 and the shopping application server 44 through the voice server 41. As shown in the flow 45, after the user terminal 40 obtains a plurality of consumption records (e.g. consumption records 5 to 12 in fig. 4), the consumption records are grouped according to the product categories corresponding to the consumption records, and then the personal average consumption amount of the user in each product category is calculated to obtain the consumption representation 46. It should be noted that the consumption image 46 shown in fig. 4 is only for describing the method of the embodiment of the present application in more detail, and does not represent that the consumption image is only in the form of the consumption image 46, and the specific consumption image form is set by a skilled person according to the actual situation.

Therefore, the method provided by the embodiment of the application can be used for classifying the consumption records of the user according to the product categories, so that the consumption image of the user is calculated, the consumption capability or the consumption intention of the user in different product categories can be favorably determined, more appropriate recommendation information can be generated for the user according to the consumption capability or the consumption intention of the user in the target product category (namely the product category corresponding to the object of the current instruction event of the user in the above) according to the method provided by the embodiment of the application, and the voice interaction shopping experience of the user can be improved.

In another possible implementation, the method for generating a second recommendation list for a user according to at least one piece of second recommendation information obtained from a plurality of shopping application servers through a voice server according to the user consumption portrait and the product category may include the following steps:

determining the average consumption amount of the first person of the user in the product category according to the consumption portrait;

obtaining at least one piece of second recommendation information from a plurality of shopping application servers through a voice server according to the price of each product in the product category and the average consumption amount of the first person;

and generating a second recommendation list according to the at least one piece of second recommendation information.

Illustratively, if the type of the object indicated by the current instruction of the user is a product category 1, the user terminal confirms an average personal consumption amount 1 of the user in the product category 1 according to the consumption representation of the user, generates a limiting condition of recommendation information according to the average personal consumption amount 1, acquires at least one piece of recommendation information from a plurality of shopping application servers through a voice server, and sorts the second recommendation information to obtain a second recommendation list.

In another possible embodiment, the obtaining, by the voice server, at least one piece of second recommendation information from the plurality of shopping application servers according to the price of each product in the product category and the first average amount of consumption may include:

obtaining a first average consumption amount of the product category from a plurality of shopping application servers through a voice server;

if the average expense amount of the first person is larger than the first average expense amount, the product price of the second recommendation information is not larger than the average expense amount of the first person;

and if the average expense amount of the first person is smaller than or equal to the first average expense amount, the product price of the second recommendation information is not larger than the first average expense amount.

Wherein the first average spending amount is associated with a plurality of spending records for all users stored by the plurality of shopping application servers.

It should be noted that the first average amount of consumption may be generated by the voice server, or may be generated by the user. For example, when the plurality of shopping application servers store average expense amounts of a plurality of product categories (i.e., product categories corresponding to the information base of the voice server), the user terminal may directly obtain the average expense amount corresponding to the product category according to the product category corresponding to the object of the current instruction event of the user; when the plurality of shopping application servers do not store the average consumption amount of a plurality of product categories (namely, the product categories corresponding to the information base of the voice server) or the average consumption amount of the product categories corresponding to the object of the current instruction event of the user, the voice server can obtain a plurality of target consumption records (namely, all consumption records corresponding to the target product categories in the plurality of shopping application servers) of the target product category (namely, the product categories corresponding to the object of the current instruction event of the user) from the plurality of shopping application servers, and record the average consumption amount of the target product category according to the plurality of target consumption records; the user terminal can also obtain a plurality of target consumption records (namely all consumption records corresponding to the target product categories in the plurality of shopping application servers) of the target product categories (namely the product categories corresponding to the objects of the current instruction events of the user) from the plurality of shopping application servers through the voice server, and record the average consumption amount of the target product categories according to the plurality of target consumption records.

Exemplarily, the type of the object of the current instruction event of the user is set as a product category 1 (corresponding to an average consumption amount 1 of 300 yuan), and if the user terminal determines that the average consumption amount 1 of the user in the product category 1 is 430 yuan according to the user representation, that is, under the condition that the average consumption amount of the first person is larger than the average consumption amount of the first person, the product price of the second recommendation information acquired by the user terminal should be smaller than or equal to 430 yuan; if the user terminal determines that the personal average consumption amount 1 of the user in the product category 1 is 200 yuan according to the user image, namely the situation that the first personal average consumption amount is smaller than or equal to the first average consumption amount belongs to, the product price of the second recommendation information acquired by the user terminal is smaller than or equal to 300 yuan. Furthermore, the method according to the embodiment of the present application may further determine the product price limit value of the second recommendation information of the secondary product category in a certain product category according to a proportional relationship between the personal average expense amount of the user and the average expense amount of the product category, where the product category and the secondary product category are in an inclusion relationship, and one product category may include multiple secondary product categories. Illustratively, if the personal consumption amount of the user in the product category 2 (including the secondary product category 21) is 360 yuan, and the average consumption amount of the product category 2 is 300 yuan, it can be found that the personal average consumption amount in the product category 2 is 120% of the average consumption amount, when the secondary product category 21 is recommended to the user, the user terminal may determine the product price limit value of the recommendation information about the secondary product category 21 according to the average consumption amount of the secondary product category 21, and set the average consumption amount of the secondary product category 21 as 100 yuan, the product price about the secondary product category 21 selected by the user terminal for the user is not higher than 120 yuan (100 × 120% = 120).

Possibly, if a product (set as product 4) in the target product category (i.e. the product category corresponding to the object of the current instruction event of the user) meets the consumption habit of the user (the user may purchase other products of the brand to which the product 4 belongs for multiple times), but the price of the product 4 does not meet the preset condition, the user terminal may determine whether the product 4 has a product specification meeting the preset condition, and if so (if the product 4 with the specification of "medium size" meets the preset condition), the product 4 with the specification of "medium size" is purchased; if not, no recommendation information about the product 4 is generated. The preset condition is that when the average personal expense amount is larger than the average expense amount, the product price of the product 4 does not exceed the average personal expense amount of the user in the target product category; alternatively, when the average amount of spending by the individual is less than or equal to the average amount of spending, the product price for product 4 does not exceed the average amount of spending for the target product category.

Therefore, the method of the embodiment of the application determines the limit value of the product price of the recommendation information according to the relation between the personal average consumption amount of the user in a certain product category and the average consumption amount of the product category on the basis of the user consumption figure, and is beneficial to ensuring that the recommendation information determined by the method of the embodiment of the application conforms to the consumption habit of the user. In addition, the method of the embodiment of the application also can determine the product price limit value of the recommendation information of the secondary product category in the product category according to the relation between the personal average consumption amount of the user in a certain product category and the average consumption amount of the product category, is helpful for determining more relevant constraint conditions of the recommendation information corresponding to the product category at a lower level when the classification level of the product category represented by the user is insufficient, and makes the recommendation information have a reference meaning for the user by adopting the 'analogy' mode.

S209, presenting the first recommendation list or the second recommendation list to the voice service interface.

In one possible implementation, the method of the embodiment of the present application may include the following steps:

arranging at least one piece of first recommendation information according to a preset rule, and generating a first recommendation list; or the like, or, alternatively,

and arranging at least one piece of second recommendation information according to a preset rule, and generating a second recommendation list.

Wherein the preset rules may include ranking according to at least one of product price, product sales, product rating, or store safety factor. More, the preset rules can also be used for sequencing the recommendation information according to the shopping frequency of the user in different shopping applications.

In one possible implementation, the voice server may obtain a voice instruction of the user through a man-machine interaction voice service engine of the user terminal, and perform intent recognition on the voice instruction. And determining the type of the object of the current instruction event of the user according to the result of the intention identification, and further generating recommendation information for the user. And the voice server can also generate a recommendation list according to the recommendation information, and then feed the recommendation list back to the user terminal, and the user terminal presents the recommendation list. The step of generating the recommendation information for the user by the voice server according to the type of the object of the current instruction event of the user may refer to the step of acquiring the recommendation information from the plurality of shopping application servers by the user terminal through the voice server, which is not described herein again.

In conclusion, the method provided by the embodiment of the application adopts a triple mode to identify the intention corresponding to the user voice instruction, and the triple identification method is helpful for identifying the key content of the user voice instruction more accurately, so that a foundation is laid for subsequent product recommendation work. In addition, the method of the embodiment of the application can also extract/match the key content (namely the object indicated by the current event of the user) by the key words, which is beneficial to quickly and accurately determining the type of the object indicated by the current event of the user, and further generating a recommendation list for the user. More, according to the method in the embodiment of the application, different recommendation information acquisition schemes are adopted for different types (the type of the object indicated by the current event of the user) according to consumption records of the user in different shopping applications, so that the recommendation information can meet the consumption requirements and consumption habits of the user, and meanwhile, products corresponding to the recommendation information can be better fit with the requirements corresponding to the voice instructions of the user.

The following describes an apparatus according to an embodiment of the present application with reference to the drawings.

Please refer to fig. 5, which is a schematic diagram of a user terminal according to an embodiment of the present disclosure, where the user terminal may include: a control module 510, a calculation module 520, an interaction module 530, a determination module 540, and a communication module 550;

a control module 510, which may be configured to invoke a human-computer interaction voice service engine to respond to a wake-up instruction input by a user and display a voice service interface, where the wake-up instruction may be used to wake up a voice service function of a user terminal;

an interaction module 530, which may be used to receive a voice instruction input by a user;

a calculation module 520, which may be configured to generate text information according to the voice instruction;

the calculating module 520 may be further configured to perform user intention recognition on the text information, and obtain an intention recognition result as a shopping intention;

the calculating module 520 may be further configured to determine, according to the intention recognition result, a type of the object indicated by the current instruction event of the user, where the type may include a product category or a single product, where the product category refers to a category of a product, and the single product refers to a product to which a product name is constrained;

the determining module 540 may be configured to determine whether the single product corresponds to the unique brand name when it is determined that the type of the object indicated by the current instruction event of the user is the single product;

the communication module 550 may be configured to, when a single product corresponds to a unique brand name, obtain at least one piece of first recommendation information from the multiple shopping application servers through the voice server according to the product name of the single product and the brand name corresponding to the single product;

the calculation module 520 may be further configured to generate a first recommendation list for the user according to the at least one piece of first recommendation information;

the calculating module 520 may be further configured to determine that the type of the object indicated by the current event of the user is a product category when the single product does not correspond to the unique brand name;

the communication module 550 may be further configured to, when it is determined that the type of the object indicated by the current instruction event of the user is a product category, obtain, by the voice server, consumption records of the user for the product category from the multiple shopping application servers, where the consumption records include a consumption amount;

the calculating module 520 may be further configured to generate a second recommendation list for the user according to the consumption record, where the second recommendation list includes at least one piece of second recommendation information;

the control module 510 may be further configured to present the first recommendation list or the second recommendation list to a voice service interface.

In one possible implementation, the user terminal may further include:

the communication module 550 may be further configured to send the product categories to the voice server, and obtain a plurality of consumption records of the user through an open interface between the voice server and the plurality of shopping application servers, where each consumption record may further include consumption time, consumption product information and consumption channels, where the consumption product information includes a consumption product name, a consumption brand name and a consumption product category;

the communication module 550 may be further configured to obtain at least one piece of second recommendation information from the plurality of shopping application servers through the voice server according to a consumption figure of the user and the product category, where the consumption figure is related to a plurality of consumption records of the user;

the calculating module 520 may be further configured to generate a second recommendation list for the user according to at least one piece of second recommendation information, where each piece of second recommendation information may include a product price.

In another possible implementation, the user terminal may further include:

the calculating module 520 may be further configured to determine a first average consumption amount of the user in the product category according to the consumption representation, where the consumption representation may include an average consumption amount of the user in at least one preset product category;

the communication module 550 may be further configured to obtain, by using the voice server, at least one piece of second recommendation information from the plurality of shopping application servers according to the price of each product in the product category and the average consumption amount of the first person;

the calculating module 520 may be further configured to generate a second recommendation list according to the at least one piece of second recommendation information.

In another possible implementation, the user terminal may further include:

the communication module 550 may be further configured to obtain, by the voice server, a first average expense amount of the product category from the plurality of shopping application servers, where the first average expense amount is related to the plurality of expense records of all the users stored by the plurality of shopping application servers;

the calculating module 520 may be further configured to determine that the product price of the second recommendation information is not greater than the average expense amount of the first person when the average expense amount of the first person is greater than the first average expense amount;

the calculating module 520 may be further configured to determine that the product price of the second recommendation information is not greater than the first average spending amount when the first average spending amount of the first person is less than or equal to the first average spending amount.

In another possible implementation, the user terminal may further include:

the determining module 540 may further be configured to determine whether the current instruction event of the user includes a brand name; and/or the presence of a gas in the atmosphere,

the determining module 540 may be further configured to determine whether a product name corresponding to the monomer product is a preset product name, where the preset product name may represent a product name corresponding to a unique brand name.

In another possible implementation, the user terminal may further include:

the determining module 540 may be further configured to determine whether a first consumption record matched with the monomer product exists in the multiple consumption records of the user, where matching refers to a consumption product name and a consumption brand name in the first consumption record, and the product name and the brand name corresponding to the monomer product are the same;

the calculation module 520 may be further configured to generate a first recommendation list according to the first consumption record when the first consumption record exists, where the first recommendation information is related to the first consumption record;

the calculating module 520 may be further configured to, when the first consumption record does not exist, obtain at least one piece of first recommendation information from the multiple shopping application servers through the voice server, and generate a first recommendation list, where the first recommendation information is related to the single product.

In another possible implementation, the user terminal may further include:

the calculation module 520 may be further configured to arrange at least one piece of first recommendation information according to a preset rule, and generate a first recommendation list, where the preset rule may include sorting according to at least one of a product price, a product sales volume, a product score, or a store safety factor; or the like, or, alternatively,

the calculating module 520 may be further configured to arrange at least one piece of second recommendation information according to a preset rule, and generate a second recommendation list.

Please refer to fig. 6, which is a schematic diagram illustrating another composition of a ue according to an embodiment of the present disclosure, where the ue may include:

a processor 610, a memory 620, and an I/O interface 630. The processor 610, the memory 620, and the I/O interface 630 may be communicatively coupled, the memory 620 may be configured to store instructions, and the processor 610 may be configured to execute the instructions stored by the memory 620 to perform the corresponding method steps of fig. 2 as described above.

The processor 610 is configured to execute the instructions stored in the memory 620 to control the I/O interface 630 to receive and transmit signals to perform the steps of the above method. The memory 620 may be integrated into the processor 610, or may be provided separately from the processor 610.

Also included in memory 620 are storage system 621, cache 622, and RAM623. The cache 622 is a first-level memory existing between the RAM623 and the CPU, and is composed of a static memory chip (SRAM), the capacity is smaller, but the speed is much higher than that of a main memory and is close to that of the CPU; the RAM623 is an internal memory that directly exchanges data with the CPU, can be read and written at any time (except for refresh), and is fast in speed, and is generally used as a temporary data storage medium for an operating system or other programs in operation. The three combine to implement the memory 620 function.

As an implementation manner, the function of the I/O interface 630 may be realized by a transceiver circuit or a dedicated chip for transceiving. The processor 610 may be considered to be implemented by a dedicated processing chip, processing circuit, processor, or a general-purpose chip.

As another implementation manner, a manner of using a general-purpose computer to implement the apparatus provided in the embodiment of the present application may be considered. I.e., program code that implements the functions of the processor 610 and the i/O interface 630, is stored in the memory 620, and a general-purpose processor implements the functions of the processor 610 and the i/O interface 630 by executing the code in the memory 620.

For the concepts, explanations, details and other steps related to the technical solutions provided in the embodiments of the present application, please refer to the description of the method or the contents of the method steps executed by the apparatus in other embodiments, which are not described herein again.

As another implementation of this embodiment, a computer-readable storage medium is provided, on which instructions are stored, which when executed perform the method in the above-described method embodiment.

As another implementation of the present embodiment, a computer program product is provided, which contains instructions that, when executed, perform the method in the above method embodiments.

Those skilled in the art will appreciate that only one memory and processor are shown in fig. 6 for ease of illustration. In an actual terminal or voice server, there may be multiple processors and memories. The memory may also be referred to as a storage medium or a storage device, and the like, which is not limited in this application.

It should be understood that, in the embodiment of the present Application, the processor may be a Central Processing Unit (CPU), and the processor may also be other general-purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like.

It will also be appreciated that the memory referred to in the embodiments herein may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. The volatile Memory may be a Random Access Memory (RAM) which serves as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), SLDRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

It should be noted that when the processor is a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, the memory (memory module) is integrated in the processor.

It should be noted that the memory described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

The bus may include a power bus, a control bus, a status signal bus, and the like, in addition to the data bus. But for the sake of clarity the various buses are labeled as buses in the figures.

It should also be understood that reference herein to first, second, third, fourth, and various numerical designations is made only for ease of description and should not be used to limit the scope of the present application.

It should be understood that the term "and/or" herein is only one kind of association relationship describing the association object, and means that there may be three kinds of relationships, for example, a and/or B, and may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.

In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The steps of a method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in a processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here.

In the embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Those of ordinary skill in the art will appreciate that the various Illustrative Logical Blocks (ILBs) and steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, digital subscriber line) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk), among others.

The present application further provides a computer storage medium, which stores a computer program, where the computer program is executed by a processor to implement part or all of the steps of the method for processing data in any one of the human-computer interaction shopping service systems as described in the above method embodiments.

Embodiments of the present application also provide a computer program product, which includes a non-transitory computer readable storage medium storing a computer program, the computer program being operable to cause a computer to perform part or all of the steps of the method for data processing in any one of the human-computer interaction shopping service systems as described in the above method embodiments.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for processing data in a human-computer interaction shopping service system is characterized in that the method is applied to a user terminal in the product human-computer interaction shopping service system, the human-computer interaction shopping service system comprises the user terminal and a voice server, the user terminal is provided with a human-computer interaction voice service engine, the user terminal is communicated with the voice server through the human-computer interaction voice service engine, and the method comprises the following steps:

calling a wake-up instruction input by a user and responded by the man-machine interaction voice service engine, and displaying a voice service interface, wherein the wake-up instruction is used for waking up the voice service function of the user terminal; receiving a voice instruction input by the user, and generating text information according to the voice instruction; performing user intention recognition on the text information to obtain an intention recognition result as a shopping intention; determining the type of an object indicated by the current instruction event of the user according to the intention recognition result, wherein the type comprises a product category or a single product, the product category refers to the category of the product, and the single product refers to the product with the restricted product name;

if the type of the object indicated by the current instruction event of the user is determined to be the monomer product, judging whether the monomer product corresponds to a unique brand name;

if the single product is judged to correspond to the unique brand name, acquiring at least one piece of first recommendation information from a plurality of shopping application servers through the voice server according to the product name of the single product and the brand name corresponding to the single product, and generating a first recommendation list for the user according to the at least one piece of first recommendation information;

if the monomer product is judged not to correspond to the unique brand name, determining that the type of the object indicated by the current event of the user is the product category;

if the type of the object indicated by the current instruction event of the user is determined to be the product category, acquiring consumption records of the user aiming at the product category from the plurality of shopping application servers through the voice server, wherein the consumption records comprise consumption money; and generating a consumption representation of the user according to the consumption record, wherein the consumption representation comprises the personal average consumption amount of the user in the product category; and obtaining product information of at least one product corresponding to the product category from the plurality of shopping application servers through the voice server, wherein the product information comprises a product name, a product price and a product specification of the product; and determining whether the product price of the at least one product exceeds the personal average spending amount of the user in the product category;

if the product price of at least one product corresponding to the product category exceeds the personal average expense amount of the user in the product category, determining whether at least one product corresponding to the product category has a product specification meeting a preset condition, wherein the preset condition is related to the personal average expense amount of the user in the product category;

if at least one product corresponding to the product category has a product specification meeting the preset condition, acquiring at least one piece of second recommendation information from a plurality of shopping application servers through the voice server according to the product specification meeting the preset condition and the consumption record of the user;

if at least one product corresponding to the product category does not have the product specification meeting the preset condition, acquiring the at least one piece of second recommendation information from a plurality of shopping application servers through the voice server according to the product information of at least one product except the product which does not have the product specification meeting the preset condition;

if the product price of at least one product corresponding to the product category does not exceed the personal average consumption amount of the user in the product category, acquiring the at least one piece of second recommendation information from a plurality of shopping application servers through the voice server according to the product information of the at least one product of which the product price does not exceed the personal average consumption amount of the user in the product category;

generating a second recommendation list for the user according to the consumption record and the at least one piece of second recommendation information, wherein the second recommendation list comprises the at least one piece of second recommendation information; and presenting the first recommendation list or the second recommendation list to the voice service interface.

2. The method of claim 1, wherein generating a second recommendation list for the user according to the consumption record and the at least one piece of second recommendation information comprises:

sending the product categories to the voice server, and acquiring a plurality of consumption records of the user through open interfaces of the voice server and the shopping application servers, wherein each consumption record further comprises consumption time, consumption product information and a consumption channel, and the consumption product information comprises a consumption product name, a consumption brand name and a consumption product category;

and according to the consumption portrait of the user and the product categories, the at least one piece of second recommendation information is acquired from the plurality of shopping application servers through the voice server, a second recommendation list is generated for the user according to the at least one piece of second recommendation information, each piece of second recommendation information comprises a product price, and the consumption portrait is related to a plurality of consumption records of the user.

3. The method of claim 2, wherein the obtaining, by the voice server, the at least one piece of second recommendation information from the plurality of shopping application servers based on the user's consumption representation and the product category comprises:

obtaining, by the voice server, a first average spending amount for the product category from the plurality of shopping application servers, the first average spending amount being associated with a plurality of spending records for all users stored by the plurality of shopping application servers;

determining the average consumption amount of the first person of the user in the product category according to the consumption representation of the user;

if the average expense amount of the first person is larger than the average expense amount of the first person, the product price of the second recommendation information is not larger than the average expense amount of the first person;

and if the first average consumption amount is less than or equal to the first average consumption amount, the product price of the second recommendation information is not greater than the first average consumption amount.

4. The method according to claim 2, wherein if it is determined that the type of the object indicated by the current instruction event of the user is the single product, determining whether the single product corresponds to a unique brand name comprises the following steps:

judging whether the current instruction event of the user comprises a brand name or not; and/or the presence of a gas in the gas,

and judging whether the product name corresponding to the monomer product is a preset product name or not, wherein the preset product name represents the product name corresponding to the unique brand name.

5. The method according to claim 4, wherein if it is determined that the single product corresponds to a unique brand name, obtaining at least one piece of first recommendation information from a plurality of shopping application servers through the voice server according to the product name of the single product and the brand name corresponding to the single product, and generating a first recommendation list for the user according to the at least one piece of first recommendation information, comprises the following steps:

judging whether a first consumption record matched with the monomer product exists in a plurality of consumption records of the user, wherein the matching refers to a consumption product name and a consumption brand name in the first consumption record, and the product name and the brand name corresponding to the monomer product are the same;

if the first consumption record does not exist, the at least one piece of first recommendation information is obtained from the plurality of shopping application servers through the voice server, and the first recommendation list is generated, wherein the first recommendation information is related to the single product.

6. The method according to claim 3 or 5, characterized in that the method further comprises the steps of:

arranging the at least one piece of first recommendation information according to a preset rule, and generating the first recommendation list, wherein the preset rule comprises sequencing according to at least one of product price, product sales volume, product score or shop safety factor; or the like, or a combination thereof,

and arranging the at least one piece of second recommendation information according to the preset rule, and generating the second recommendation list.

7. A user terminal, characterized in that the user terminal comprises: the device comprises a control module, a calculation module, an interaction module, a judgment module and a communication module;

the control module is used for calling a man-machine interaction voice service engine to respond to a wake-up instruction input by a user and displaying a voice service interface, and the wake-up instruction is used for waking up a voice service function of the user terminal;

the interaction module is used for receiving the voice instruction input by the user;

the computing module is used for generating text information according to the voice instruction;

the computing module is also used for carrying out user intention identification on the text information to obtain an intention identification result as a shopping intention;

the calculation module is further configured to determine, according to the intention recognition result, a type of an object indicated by the current instruction event of the user, where the type includes a product category or a single product, the product category is a product category, and the single product is a product with a constrained product name;

the judging module is used for judging whether the single product corresponds to a unique brand name or not when the type of the object indicated by the current instruction event of the user is determined to be the single product;

the communication module is used for acquiring at least one piece of first recommendation information from a plurality of shopping application servers through a voice server according to the product name of the single product and the brand name corresponding to the single product when the single product corresponds to the unique brand name;

the calculation module is further used for generating a first recommendation list for the user according to the at least one piece of first recommendation information;

the calculation module is further configured to determine, when the single product does not correspond to a unique brand name, that the type of the object indicated by the current event of the user is the product category;

the communication module is further configured to, when it is determined that the type of the object indicated by the current instruction event of the user is the product category, obtain, by the voice server, consumption records of the user for the product category from the plurality of shopping application servers, where the consumption records include a consumption amount;

the calculation module is further used for generating a consumption portrait of the user according to the consumption record, wherein the consumption portrait comprises personal average consumption amount of the user in the product category;

the communication module is further configured to obtain product information of at least one product corresponding to the product category from the plurality of shopping application servers through the voice server, where the product information includes a product name, a product price, and a product specification of the product;

the judging module is further used for judging whether the product price of the at least one product exceeds the personal average consumption amount of the user in the product category;

the judging module is further configured to determine whether at least one product corresponding to the product category has a product specification meeting a preset condition when the product price of the at least one product exceeds the personal average expense amount of the user in the product category, where the preset condition is related to the personal average expense amount of the user in the product category;

the communication module is further configured to, when at least one product corresponding to the product category has a product specification meeting the preset condition, obtain at least one piece of second recommendation information from the plurality of shopping application servers through the voice server according to the product specification meeting the preset condition and the consumption record of the user;

the communication module is further configured to, when at least one product corresponding to the product category does not have a product specification meeting the preset condition, obtain, by the voice server, the at least one piece of second recommendation information from a plurality of shopping application servers according to product information of at least one product other than the product not having the product specification meeting the preset condition;

the communication module is further configured to, when the product price of at least one product corresponding to the product category does not exceed the personal average consumption amount of the user in the product category, obtain, by the voice server, the at least one piece of second recommendation information from a plurality of shopping application servers according to the product information of the at least one product, of which the product price does not exceed the personal average consumption amount of the user in the product category;

the computing module is further configured to generate a second recommendation list for the user according to the consumption record and the at least one piece of second recommendation information, where the second recommendation list includes the at least one piece of second recommendation information;

the control module is further configured to present the first recommendation list or the second recommendation list to the voice service interface.

8. A user terminal, characterized in that the user terminal comprises:

a processor, a memory and a bus, the processor and the memory being connected by the bus, wherein the memory is configured to store a set of program codes, and the processor is configured to call the program codes stored in the memory to execute the method according to any one of claims 1-6.

9. A computer-readable storage medium, comprising:

the computer-readable storage medium has stored therein instructions which, when run on a computer, implement the method of any one of claims 1-6.